Grid
Every model in every harness: each cell is that pairing's latest attempt on a prompt, with how it ended, what it cost and how long it took. Earlier attempts are counted in the cell and listed on the result page.
Every prompt
Finished cells of each model in each harness across all prompts (latest attempts). A cell opens those results in the explorer.
| Model | Claude Code | Codex CLI | dsh | Kimi Code CLI | Grok Build | Gemini CLI | OpenCode | Cline CLI | Raw API | Hermes Agent 0.21.5 | Hermes Agent 0.21.5 + Oh-My-Hermes 2.0.5 | Kilo Code CLI 7.7.9 | Oh My Pi (omp) 18.3.1 | Pi 0.87.1 | Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5.5Anthropic | 101 of 104 finished | · | · | · | · | · | 23 of 23 finished | · | 119 of 129 finished | 1 of 7 finished | 0 of 6 finished | 5 of 6 finished | 6 of 6 finished | 7 of 8 finished | 8 of 13 finished |
| Claude Sonnet 5.5Anthropic | 48 of 62 finished | · | · | · | · | · | 4 of 18 finished | · | 2 of 4 finished | · | · | · | · | · | · |
| Claude Fable 5.1Anthropic | 29 of 34 finished | · | · | · | · | · | 23 of 24 finished | · | 107 of 109 finished | · | · | · | · | · | · |
| Claude Haiku 5.5Anthropic | 5 of 5 finished | · | · | · | · | · | · | · | 2 of 2 finished | · | · | · | · | · | · |
| GPT-6 AstraOpenAI | · | 65 of 65 finished | · | · | · | · | 49 of 49 finished | · | 144 of 147 finished | · | · | · | · | · | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | 18 of 21 finished | · | · | · | 42 of 46 finished | 2 of 12 finished | 157 of 161 finished | · | · | · | · | · | · |
| DeepSeek V4 ProDeepSeek | · | · | · | · | · | · | · | · | 167 of 170 finished | · | · | · | · | · | · |
| Grok 4.7xAI | · | · | · | · | 4 of 4 finished | · | 6 of 6 finished | · | No result | · | · | · | · | · | · |
| Gemini 3.8 FlashGoogle | · | · | · | · | · | Not tested | 0 of 1 finished | 8 of 12 finished | No result | · | · | · | · | · | · |
| Kimi K3Moonshot | · | · | · | 14 of 15 finished | · | · | 16 of 20 finished | · | 65 of 69 finished | · | · | · | · | · | · |
| GLM-5.3Z.ai | 14 of 15 finished | · | · | · | · | · | 17 of 24 finished | · | 14 of 52 finished | · | · | · | · | · | · |
| GPT-6 SolOpenAI | · | 98 of 98 finished | · | · | · | · | · | · | 139 of 139 finished | · | · | · | · | · | · |
| Space Bunny AlphaUndisclosed (stealth) | · | · | · | · | · | · | 12 of 13 finished | 11 of 11 finished | · | · | · | · | · | · | · |
| Muse Spark 1.3Meta | · | · | · | · | · | · | 11 of 12 finished | 12 of 12 finished | · | · | · | · | · | · | · |
| LongCat 2.5 PreviewMeituan | · | · | · | · | · | · | 42 of 50 finished | · | · | · | · | · | · | · | · |
| MiMo V2.6 FlashXiaomi | · | · | · | · | · | · | · | 2 of 12 finished | · | · | · | · | · | · | · |
| Claude Sonnet 5Anthropic | · | · | · | · | · | · | · | · | 97 of 99 finished | · | · | · | · | · | · |
| Gemini 3.6 FlashGoogle | · | · | · | · | · | · | · | · | 3 of 11 finished | · | · | · | · | · | · |
| Gemini 3.7 FlashGoogle | · | · | · | · | · | · | · | · | 0 of 2 finished | · | · | · | · | · | · |
| gemini-3.1-pro-preview | · | · | · | · | · | · | · | · | No result | · | · | · | · | · | · |
| gemini-3.5-flashGoogle | · | · | · | · | · | · | · | · | 1 of 2 finished | · | · | · | · | · | · |
| GPT-6 LunaOpenAI | · | · | · | · | · | · | · | · | 134 of 134 finished | · | · | · | · | · | · |
| gpt-6.1-solOpenAI | · | 18 of 20 finished | · | · | · | · | · | · | 11 of 11 finished | · | · | · | · | · | · |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | · | · | · | · | · | · | · | · | 324 of 341 finished | · | · | · | · | · | · |
| minimax-m3unknown | · | · | · | · | · | · | · | · | 48 of 59 finished | · | · | · | · | · | · |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | · | · | · | · | · | · | · | · | 150 of 339 finished | · | · | · | · | · | · |
| qwen3p8-maxAlibaba | · | · | · | · | · | · | · | · | 59 of 62 finished | · | · | · | · | · | · |
PS5 Pro DualSense controller (max-fidelity SVG)
32 cells with a result. Compare the outputs
25 finished cells
Pelican riding a bicycle (control)
33 cells with a result. Compare the outputs
29 finished cells
MacBook Pro 16" realistic 3D render (Playcode benchmark)
25 cells with a result. Compare the outputs
20 finished cells
Lighthouse on a headland at night
26 cells with a result. Compare the outputs
20 finished cells
Isometric SVG town with sprite sheet
26 cells with a result. Compare the outputs
21 finished cells
Animated pelican riding a bicycle (SMIL/CSS)
30 cells with a result. Compare the outputs
25 finished cells
California brown pelican riding a bicycle (detailed spec)
29 cells with a result. Compare the outputs
24 finished cells
Xbox 360 controller
23 cells with a result. Compare the outputs
20 finished cells
BMW M4 Competition, side view (flat vector)
24 cells with a result. Compare the outputs
21 finished cells
PS5 Pro DualSense controller (quick SVG)
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | low (32k cap)OK31 s$0.074Details |
| GPT-6 SolOpenAI | maxOK9m 54s$0.37Details |
PS5 Pro console and controller product shot (SVG)
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | low (32k cap)OK32 s$0.085Details |
| GPT-6 SolOpenAI | maxOK10m 18s$0.40Details |
Cinematic fjord boat scene (Three.js)
21 cells with a result. Compare the outputs
16 finished cells
| Model | Claude Code | Codex CLI | dsh | Kimi Code CLI | OpenCode | Cline CLI | Raw API | Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills) |
|---|---|---|---|---|---|---|---|---|
| Claude Opus 5.5Anthropic | OK2h 52m$35.06try 4/4Details | · | · | · | OK3h 12m$31.08Details | · | low (128k cap)OK5m 06s$0.68Detailslow-1fix (128k cap)OK8m 59s$1.35DetailsmaxDNF MODEL22m 03s$2.56try 6/6 | DNF TIMEOUT52m 41s$1.83 |
| Claude Sonnet 5.5Anthropic | DNF ERROR17m 49s$2.72 | · | · | · | DNF TIMEOUT46m 13s$7.24 | · | · | · |
| Claude Fable 5.1Anthropic | OK31m 18s$7.03try 2/2Details | · | · | · | OK4h 09m$55.76Details | · | · | · |
| GPT-6 AstraOpenAI | · | OK25m 14s$5.57Details | · | · | OK35m 01s$7.27Details | · | · | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | DNF INFRA31m 56s$0.13 | · | · | · | · | · |
| Gemini 3.8 FlashGoogle | · | · | · | · | · | No result QUOTA ×1 | · | · |
| Kimi K3Moonshot | · | · | · | OK2h 50m$13.50Details | OK2h 20m$8.00Details | · | · | · |
| GLM-5.3Z.ai | OK1h 52m$2.89Details | · | · | · | OK2h 15m$9.48Details | · | · | · |
| GPT-6 SolOpenAI | · | OK28m 43s$3.56Details | · | · | · | · | maxOK16m 07s$0.56Details | · |
| Space Bunny AlphaUndisclosed (stealth) | · | · | · | · | · | OK4m 55s$0Details | · | · |
| Gemini 3.6 FlashGoogle | · | · | · | · | · | · | high (66k cap)OK3m 12s$0Details | · |
Animated short film drawn in code (HTML/JS)
19 cells with a result. Compare the outputs
10 finished cells
How an AI model race works: 35-second animated explainer (HTML)
1 cell with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | callOK10m 49snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Chart morph: bars to line to donut (motion graphic)
4 cells with a result. Compare the outputs
4 finished cells
KPI cards with odometer digits (motion graphic)
1 cell with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | callOK7m 37snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Planets: from orbits to a size line-up (motion graphic)
1 cell with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | callOK7m 14snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Dotted world map with flight arcs (motion graphic)
1 cell with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | callOK7m 31snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Shape-morph logo reveal (motion graphic)
1 cell with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | callOK7m 02snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Stock chart: line to candlesticks (motion graphic)
1 cell with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | callOK6m 02snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Scatter to waffle to histogram (motion graphic)
1 cell with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | callOK3m 37snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Venetian canal watercolour, painted live (HTML)
4 cells with a result. Compare the outputs
3 finished cells
AI data centre, inside view (Opus 5.5 demo prompt)
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK17m 28s$3.77try 2/2Details | · |
| GPT-6 SolOpenAI | · | OK3m 20s$0.38Details |
Van Gogh cat-spotting game (Opus 5.5 demo prompt)
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK16m 52s$1.93Details | · |
| GPT-6 SolOpenAI | · | OK8m 09s$0.64Details |
16-bit pixel wizard sprite loop (Opus 5.5 demo prompt)
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK8m 45s$1.39Details | · |
| GPT-6 SolOpenAI | · | OK2m 29s$0.25Details |
"Make a Tron game" (Opus 5.5 demo prompt)
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK4m 52s$0.79Details | · |
| GPT-6 SolOpenAI | · | OK3m 20s$0.34Details |
Santa Monica particle beach (Opus 5.5 demo prompt)
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK22m 26s$4.01try 2/2Details | · |
| GPT-6 SolOpenAI | · | OK4m 56s$0.46Details |
Recursion explainer (Opus 5.5 demo prompt)
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK18m 12s$2.04Details | · |
| GPT-6 SolOpenAI | · | OK10m 07s$0.70Details |
Token bucket explainer (Opus 5.5 demo prompt)
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK3m 30s$0.60Details | · |
| GPT-6 SolOpenAI | · | OK3m 07s$0.32Details |
Train window through four seasons (Opus 5.5 demo prompt)
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK8m 21s$1.53Details | · |
| GPT-6 SolOpenAI | · | OK3m 39s$0.37Details |
Collision music machine (Opus 5.5 demo prompt)
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK15m 56s$2.14Details | · |
| GPT-6 SolOpenAI | · | OK4m 27s$0.40Details |
15-second motion showreel (Opus 5.5 demo prompt)
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK14m 26s$1.72Details | · |
| GPT-6 SolOpenAI | · | OK7m 09s$0.58Details |
blender_donut
3 cells with a result. Compare the outputs
3 finished cells
| Model | Claude Code | Codex CLI | dsh | Kimi Code CLI | OpenCode |
|---|---|---|---|---|---|
| Claude Opus 5.5Anthropic | OK1h 22m$13.54Details | · | · | · | Pending |
| Claude Fable 5.1Anthropic | Pending | · | · | · | Pending |
| GPT-6 AstraOpenAI | · | OK29m 10s$7.78Details | · | · | Pending |
| DeepSeek V4.1 FlashDeepSeek | · | · | Pending | · | Pending |
| Kimi K3Moonshot | · | · | · | Pending | Pending |
| GPT-6 SolOpenAI | · | OK17m 55s$1.64Details | · | · | · |
whale_clouds
20 cells with a result. Compare the outputs
18 finished cells
dolphin_vlog_bicycle
24 cells with a result. Compare the outputs
18 finished cells
folding_road_music
1 cell with a result. Compare the outputs
0 finished cells
| Model | Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills) |
|---|---|
| Claude Opus 5.5Anthropic | DNF TIMEOUT52m 50s$4.64 |
folding_road_threejs
13 cells with a result. Compare the outputs
8 finished cells
| Model | Claude Code | Codex CLI | dsh | Kimi Code CLI | OpenCode | Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills) |
|---|---|---|---|---|---|---|
| Claude Opus 5.5Anthropic | OK1h 50m$18.81Details | · | · | · | OK1h 29m$18.58try 2/2Details | DNF TIMEOUT52m 44s$4.65 |
| Claude Sonnet 5.5Anthropic | · | · | · | · | DNF TIMEOUT45m 59s$6.16 | · |
| Claude Fable 5.1Anthropic | OK53m 55s$14.17Details | · | · | · | OK54m 50s$14.82Details | · |
| GPT-6 AstraOpenAI | · | OK35m 12s$9.52Details | · | · | OK25m 26s$5.22try 2/2Details | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK1h 10m$0.31Details | · | DNF TIMEOUT1h 21m$0.15 | · |
| Kimi K3Moonshot | · | · | · | OK1h 00m$4.01Details | DNF TIMEOUT44m 37s$1.89 | · |
| GLM-5.3Z.ai | No result INFRA ×1 | · | · | · | · | · |
| Space Bunny AlphaUndisclosed (stealth) | · | · | · | · | DNF TIMEOUT58m 28s$0 | · |
gpu_fluid_sim
9 cells with a result. Compare the outputs
6 finished cells
| Model | Claude Code | Codex CLI | dsh | Kimi Code CLI | OpenCode | Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills) |
|---|---|---|---|---|---|---|
| Claude Opus 5.5Anthropic | OK1h 35m$11.37Details | · | · | · | · | OK49m 01s$4.78Details |
| Claude Fable 5.1Anthropic | DNF TIMEOUT39m 19s$9.01 | · | · | · | · | · |
| GPT-6 AstraOpenAI | · | OK22m 35s$5.05Details | · | · | · | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK1h 05m$0.12Details | · | OK54m 00s$0.073Details | · |
| Kimi K3Moonshot | · | · | · | DNF TIMEOUT57m 02s$2.29try 2/2 | · | · |
| GLM-5.3Z.ai | OK19m 31s$0.74Details | · | · | · | · | · |
| LongCat 2.5 PreviewMeituan | · | · | · | · | DNF TIMEOUT14m 26s$0try 2/2 | · |
hyperframes_artemis_ii
14 cells with a result. Compare the outputs
12 finished cells
| Model | Claude Code | Codex CLI | dsh | OpenCode | Hermes Agent 0.21.5 | Hermes Agent 0.21.5 + Oh-My-Hermes 2.0.5 | Kilo Code CLI 7.7.9 | Oh My Pi (omp) 18.3.1 | Pi 0.87.1 | Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills) |
|---|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5.5Anthropic | OK2h 59m$35.28Details | · | · | OK2h 42m$29.64Details | DNF MODEL2h 18m$26.88 | DNF MODEL2h 04m$24.64 | OK2h 18m$33.35Details | OK2h 24m$32.29Details | OK1h 58m$20.24Details | OK2h 26m$22.35try 2/2Details |
| Claude Fable 5.1Anthropic | OK1h 39m$67.51Details | · | · | OK2h 01m$40.74Details | · | · | · | · | · | · |
| GPT-6 AstraOpenAI | · | OK34m 23s$16.60Details | · | OK55m 41s$10.77Details | · | · | · | · | · | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK1h 33m$0.22Details | OK2h 40m$0.32Details | · | · | · | · | · | · |
pelican_car_france
26 cells with a result. Compare the outputs
22 finished cells
pixel_lofi_loop
4 cells with a result. Compare the outputs
1 finished cells
| Model | Claude Code | OpenCode | Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills) |
|---|---|---|---|
| Claude Opus 5.5Anthropic | · | OK52m 30s$11.34Details | DNF MODEL22m 34s$2.64 |
| Claude Sonnet 5.5Anthropic | DNF ERROR17m 41s$2.73 | DNF TIMEOUT46m 06s$9.09 | · |
remotion_sales_chart
2 cells with a result. Compare the outputs
2 finished cells
| Model | Pi 0.87.1 | Pi 0.87.1 + skills kit (ponytail, ECC, vetted skills) |
|---|---|---|
| Claude Opus 5.5Anthropic | OK22m 36s$4.12Details | OK13m 05s$2.19Details |
threejs_dragon_ship
5 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK2h 00m$13.87Details | · | · |
| Claude Fable 5.1Anthropic | OK1h 16m$22.54Details | · | OK1h 44m$34.82Details |
| GPT-6 AstraOpenAI | · | OK27m 52s$8.01Details | OK30m 10s$4.96Details |
| GLM-5.3Z.ai | No result INFRA ×1 | · | · |
threejs_eiffel
8 cells with a result. Compare the outputs
7 finished cells
| Model | Claude Code | Codex CLI | dsh | OpenCode |
|---|---|---|---|---|
| Claude Opus 5.5Anthropic | OK1h 38m$17.87Details | · | · | OK2h 49m$24.70Details |
| Claude Fable 5.1Anthropic | OK22m 54s$7.62Details | · | · | DNF TIMEOUT43m 00s$8.52 |
| GPT-6 AstraOpenAI | · | OK14m 16s$2.65Details | · | OK35m 48s$5.18Details |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK30m 02s$0.11Details | OK28m 46s$0.10Details |
bacterium_to_quantum_zoom
4 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | OpenCode |
|---|---|---|
| Claude Opus 5.5Anthropic | OK2h 32m$20.26Details | · |
| Claude Sonnet 5.5Anthropic | DNF ERROR16m 55s$2.76 | DNF INFRA26m 06s$3.57 |
| Claude Fable 5.1Anthropic | OK56m 22s$15.29Details | · |
001 Ink Bloom Garden
14 cells with a result. Compare the outputs
14 finished cells
002 Pendulum Wave
14 cells with a result. Compare the outputs
13 finished cells
003 Orbital Coffee Landing
14 cells with a result. Compare the outputs
12 finished cells
004 Brick Breaker Neon
14 cells with a result. Compare the outputs
12 finished cells
005 Focus Timer Orbit
13 cells with a result. Compare the outputs
12 finished cells
006 Rainfall Bars
11 cells with a result. Compare the outputs
10 finished cells
007 Kinetic Headline
11 cells with a result. Compare the outputs
11 finished cells
008 Pocket Theremin
11 cells with a result. Compare the outputs
11 finished cells
009 Forest Fire Automaton
11 cells with a result. Compare the outputs
10 finished cells
010 Toggle Switch Gallery
11 cells with a result. Compare the outputs
10 finished cells
011 Pure CSS Sunset
11 cells with a result. Compare the outputs
10 finished cells
012 Magnetic Filings
11 cells with a result. Compare the outputs
10 finished cells
013 Soft Body Blobs
11 cells with a result. Compare the outputs
10 finished cells
014 Snake Reimagined
11 cells with a result. Compare the outputs
11 finished cells
015 Color Palette Studio
11 cells with a result. Compare the outputs
11 finished cells
016 Heartbeat Line
11 cells with a result. Compare the outputs
11 finished cells
017 Typewriter Poem
11 cells with a result. Compare the outputs
10 finished cells
018 Step Sequencer Grid
11 cells with a result. Compare the outputs
11 finished cells
019 Boids Lagoon
8 cells with a result. Compare the outputs
8 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | high (64k cap)OK3m 49s$0.51Details |
| Claude Fable 5.1Anthropic | high (64k cap)OK3m 17s$0.90Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 41snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK1m 51snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Kimi K3Moonshot | default (64k cap)OK10m 49snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Claude Sonnet 5Anthropic | high (64k cap)OK1m 53snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK24 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
020 Pricing Table Trio
6 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | high (64k cap)OK1m 17s$0.20Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 50snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 27snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Kimi K3Moonshot | default (64k cap)OK2m 57snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK25 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
021 Rotating CSS Cube
5 cells with a result. Compare the outputs
5 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 57snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK3m 20snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Kimi K3Moonshot | default (64k cap)OK4m 52snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK4.7 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK24 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
022 Mandala Painter
5 cells with a result. Compare the outputs
4 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 24snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK1m 27snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Kimi K3Moonshot | default (64k cap)OK2m 05snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL35 snot recorded: the run's token counts were never reported, so there is no estimate |
023 Mortgage Calculator
4 cells with a result. Compare the outputs
3 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4 ProDeepSeek | default (64k cap)OK36 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Kimi K3Moonshot | default (64k cap)OK6m 02snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK9.8 snot recorded: the run's token counts were never reported, so there is no estimatetry 2/2Details |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL34 snot recorded: the run's token counts were never reported, so there is no estimate |
024 Tower Stack
3 cells with a result. Compare the outputs
3 finished cells
| Model | Raw API |
|---|---|
| Kimi K3Moonshot | default (64k cap)OK8m 32snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK19 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK34 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
025 Gravity Well
3 cells with a result. Compare the outputs
3 finished cells
| Model | Raw API |
|---|---|
| Kimi K3Moonshot | default (64k cap)OK8m 06snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.9 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK1m 09snot recorded: the run's token counts were never reported, so there is no estimatetry 2/2Details |
026 Aurora Ribbons
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK8.7 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL33 snot recorded: the run's token counts were never reported, so there is no estimate |
027 Momentum Cradle
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK14 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL1m 23snot recorded: the run's token counts were never reported, so there is no estimate |
028 Night Market Zine
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK4.0 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL33 snot recorded: the run's token counts were never reported, so there is no estimate |
029 Asteroid Drift
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK8.9 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK29 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
030 Unit Converter Deck
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.4 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL35 snot recorded: the run's token counts were never reported, so there is no estimate |
031 Population Bubbles
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL38 snot recorded: the run's token counts were never reported, so there is no estimate |
032 Liquid Letters
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL39 snot recorded: the run's token counts were never reported, so there is no estimate |
033 Wind Chimes
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK9.0 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL57 snot recorded: the run's token counts were never reported, so there is no estimate |
034 Sandpile Falling
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL37 snot recorded: the run's token counts were never reported, so there is no estimate |
035 Modal Dialog Set
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL43 snot recorded: the run's token counts were never reported, so there is no estimate |
036 CSS Jellyfish Tank
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK9.6 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL31 snot recorded: the run's token counts were never reported, so there is no estimate |
037 Voronoi Stained Glass
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL35 snot recorded: the run's token counts were never reported, so there is no estimate |
038 Cloth Curtain
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.7 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL32 snot recorded: the run's token counts were never reported, so there is no estimate |
039 Memory Match Cards
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK6.7 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL38 snot recorded: the run's token counts were never reported, so there is no estimate |
040 Markdown Notepad
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.8 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL38 snot recorded: the run's token counts were never reported, so there is no estimate |
041 Solar Radial Clock
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL55 snot recorded: the run's token counts were never reported, so there is no estimate |
042 Split Flap Board
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL49 snot recorded: the run's token counts were never reported, so there is no estimate |
043 Drone Pad Synth
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.4 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL36 snot recorded: the run's token counts were never reported, so there is no estimate |
044 Traffic Intersection
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimatetry 2/2Details |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL43 snot recorded: the run's token counts were never reported, so there is no estimate |
045 Form Validation Demo
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.6 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK30 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
046 Pure CSS Loaders
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.4 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL50 snot recorded: the run's token counts were never reported, so there is no estimate |
047 Flow Field Threads
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK37 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
048 Marble Run Ramps
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK8.8 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL39 snot recorded: the run's token counts were never reported, so there is no estimate |
049 Maze Runner
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK8.6 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK31 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
050 Budget Pie Planner
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.7 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK47 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
051 Tidal Moiré
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.4 snot recorded: the run's token counts were never reported, so there is no estimatetry 2/2Details |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK17 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
052 Catapult Castle
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK18 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL44 snot recorded: the run's token counts were never reported, so there is no estimate |
053 Portfolio Grid
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK31 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
054 Flappy Paper Plane
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK13 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK36 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
055 Password Forge
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL36 snot recorded: the run's token counts were never reported, so there is no estimate |
056 Commute Heatmap
2 cells with a result. Compare the outputs
0 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)DNF MODEL3.6 snot recorded: the run's token counts were never reported, so there is no estimatetry 2/2 |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL36 snot recorded: the run's token counts were never reported, so there is no estimate |
057 Variable Weight Wave
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK3.6 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK21 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
058 Bubble Wrap Pop
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK7.0 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK32 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
059 Predator Prey Meadow
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK9.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL39 snot recorded: the run's token counts were never reported, so there is no estimate |
061 CSS Candle Flame
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK31 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
062 Recursive Tree Wind
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK4.8 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL39 snot recorded: the run's token counts were never reported, so there is no estimate |
063 Rope Bridge
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK7.1 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL45 snot recorded: the run's token counts were never reported, so there is no estimate |
064 Minesweeper Classic
2 cells with a result. Compare the outputs
0 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)DNF MODEL4.0 snot recorded: the run's token counts were never reported, so there is no estimatetry 2/2 |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL47 snot recorded: the run's token counts were never reported, so there is no estimate |
065 Habit Streak Tracker
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK15 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL40 snot recorded: the run's token counts were never reported, so there is no estimate |
066 Stock Candlesticks
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK9.9 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL33 snot recorded: the run's token counts were never reported, so there is no estimate |
067 Glitch Title Card
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK7.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK33 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
068 Piano Keys Mini
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK14 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK20 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
069 Ant Colony Trails
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK14 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL49 snot recorded: the run's token counts were never reported, so there is no estimate |
070 Card Hover Effects
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL31 snot recorded: the run's token counts were never reported, so there is no estimate |
071 CSS Pixel Portrait
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK17 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL37 snot recorded: the run's token counts were never reported, so there is no estimate |
072 Starfield Warp
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK9.0 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK33 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
073 Water Ripple Pond
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)DNF MODEL6.5 snot recorded: the run's token counts were never reported, so there is no estimatetry 2/2 |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
074 Word Guess Five
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK19 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL41 snot recorded: the run's token counts were never reported, so there is no estimate |
075 Tip Splitter
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.1 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL37 snot recorded: the run's token counts were never reported, so there is no estimate |
076 Reaction Diffusion
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK36 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
077 Double Pendulum Chaos
2 cells with a result. Compare the outputs
0 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)DNF MODEL6.9 snot recorded: the run's token counts were never reported, so there is no estimatetry 2/2 |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL32 snot recorded: the run's token counts were never reported, so there is no estimate |
078 Event Poster Page
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.6 snot recorded: the run's token counts were never reported, so there is no estimatetry 2/2Details |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL33 snot recorded: the run's token counts were never reported, so there is no estimate |
079 Tetromino Drop
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK18 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL41 snot recorded: the run's token counts were never reported, so there is no estimate |
080 Regex Playground
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK9.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL38 snot recorded: the run's token counts were never reported, so there is no estimate |
081 Election Hemicycle
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL42 snot recorded: the run's token counts were never reported, so there is no estimate |
082 Circular Text Badge
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK8.8 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK29 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
083 Sine Chord Pad
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK22 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
084 Epidemic Grid
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK9.2 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK35 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
086 CSS Ocean Waves
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK15 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK37 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
087 Particle Text Morph
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK8.1 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL40 snot recorded: the run's token counts were never reported, so there is no estimate |
088 Spring Mass Chain
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK35 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
089 Pixel Paint Paddles
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK14 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL43 snot recorded: the run's token counts were never reported, so there is no estimate |
090 Countdown Builder
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL45 snot recorded: the run's token counts were never reported, so there is no estimate |
091 Treemap Budget
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK15 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL39 snot recorded: the run's token counts were never reported, so there is no estimate |
092 Scroll Story Words
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK8.0 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL41 snot recorded: the run's token counts were never reported, so there is no estimate |
093 Arpeggio Machine
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK9.7 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL40 snot recorded: the run's token counts were never reported, so there is no estimate |
094 Lava Lamp Metaballs
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK7.9 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL40 snot recorded: the run's token counts were never reported, so there is no estimate |
095 Notification Centre
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.6 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL36 snot recorded: the run's token counts were never reported, so there is no estimate |
096 CSS Solar System
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK27 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
097 Wave Interference
1 cell with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK14 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Zoom to the Atom
4 cells with a result. Compare the outputs
3 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 39snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK2m 59snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK18 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL53 snot recorded: the run's token counts were never reported, so there is no estimate |
Koi Pond Garden
12 cells with a result. Compare the outputs
5 finished cells
Twin-Bell Alarm Clock
14 cells with a result. Compare the outputs
12 finished cells
Alien Planet
14 cells with a result. Compare the outputs
14 finished cells
Ant Colony Cutaway
14 cells with a result. Compare the outputs
12 finished cells
Flat App Icon Set
14 cells with a result. Compare the outputs
14 finished cells
Art Deco Skyscraper
14 cells with a result. Compare the outputs
13 finished cells
Floating Astronaut
14 cells with a result. Compare the outputs
13 finished cells
Stargazer with Telescope
14 cells with a result. Compare the outputs
12 finished cells
Autumn Forest Path
14 cells with a result. Compare the outputs
13 finished cells
Ballet Dancer
14 cells with a result. Compare the outputs
12 finished cells
Barn Owl in Flight
14 cells with a result. Compare the outputs
12 finished cells
Battery Level Icons
14 cells with a result. Compare the outputs
14 finished cells
Breakfast Skillet
14 cells with a result. Compare the outputs
12 finished cells
Bubble Tea
14 cells with a result. Compare the outputs
12 finished cells
Exploded Burger
14 cells with a result. Compare the outputs
14 finished cells
Calendar Month View
14 cells with a result. Compare the outputs
14 finished cells
Canyon River
14 cells with a result. Compare the outputs
12 finished cells
svg_cargo_ship_containers__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK3m 24s$0Details |
Container Ship
14 cells with a result. Compare the outputs
12 finished cells
Chameleon on a Branch
14 cells with a result. Compare the outputs
11 finished cells
Chat Conversation UI
14 cells with a result. Compare the outputs
12 finished cells
Chef Flipping a Pan
14 cells with a result. Compare the outputs
10 finished cells
Circuit Board Close-Up
14 cells with a result. Compare the outputs
12 finished cells
Corgi Catching a Frisbee
14 cells with a result. Compare the outputs
13 finished cells
Cyberpunk Alley
14 cells with a result. Compare the outputs
11 finished cells
Sales Dashboard Card
14 cells with a result. Compare the outputs
14 finished cells
Desert Dunes at Night
12 cells with a result. Compare the outputs
12 finished cells
Desk Lamp and Books
11 cells with a result. Compare the outputs
10 finished cells
Noir Detective
10 cells with a result. Compare the outputs
10 finished cells
Group Selfie
10 cells with a result. Compare the outputs
9 finished cells
Dragon Coiled on a Tower
10 cells with a result. Compare the outputs
9 finished cells
Dragonfly Over Pond
10 cells with a result. Compare the outputs
10 finished cells
Quadcopter Drone
10 cells with a result. Compare the outputs
10 finished cells
Windmill by a Canal
10 cells with a result. Compare the outputs
10 finished cells
Pyramids at Sunset
10 cells with a result. Compare the outputs
9 finished cells
Elephant Calf Mud Bath
13 cells with a result. Compare the outputs
11 finished cells
File Upload Dropzone
10 cells with a result. Compare the outputs
10 finished cells
35mm Film Camera
10 cells with a result. Compare the outputs
9 finished cells
Flamingo on One Leg
10 cells with a result. Compare the outputs
10 finished cells
Floating Islands
10 cells with a result. Compare the outputs
9 finished cells
Fountain Pen and Ink
10 cells with a result. Compare the outputs
9 finished cells
Fruit Bowl Still Life
10 cells with a result. Compare the outputs
9 finished cells
Retro Handheld Console
10 cells with a result. Compare the outputs
10 finished cells
Gardener Watering Plants
10 cells with a result. Compare the outputs
9 finished cells
Giraffe Side Profile
13 cells with a result. Compare the outputs
11 finished cells
Victorian Glasshouse
10 cells with a result. Compare the outputs
9 finished cells
Good Vibes Retro Type
10 cells with a result. Compare the outputs
10 finished cells
Gothic Cathedral Facade
10 cells with a result. Compare the outputs
9 finished cells
Greek Temple
9 cells with a result. Compare the outputs
8 finished cells
Over-Ear Headphones
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK2m 45s$0.46Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK51 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 42snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 44snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK52 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)DNF MODEL6.9 snot recorded: the run's token counts were never reported, so there is no estimate |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK18 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Hedgehog Under Mushroom
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK3m 51s$0.61Details |
| DeepSeek V4.1 FlashDeepSeek | default (33k cap)OK38 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (33k cap)OK2m 30snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 29snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 12snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL38 snot recorded: the run's token counts were never reported, so there is no estimate |
Rescue Helicopter
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK4m 22s$0.68Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 03snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 43snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 56snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 19snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.6 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL40 snot recorded: the run's token counts were never reported, so there is no estimate |
Hello Neon Sign
7 cells with a result. Compare the outputs
5 finished cells
Honeybee on Honeycomb
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK4m 04s$0.73Details |
| DeepSeek V4.1 FlashDeepSeek | default (33k cap)OK1m 04snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (33k cap)OK3m 01snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 58snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 15snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK21 snot recorded: the run's token counts were never reported, so there is no estimatetry 2/2Details |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL56 snot recorded: the run's token counts were never reported, so there is no estimate |
Hot Air Balloons
7 cells with a result. Compare the outputs
7 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK3m 21s$0.62Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 07snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 48snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK2m 14snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 01snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.0 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK22 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Hourglass
7 cells with a result. Compare the outputs
7 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK1m 42s$0.31Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK57 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK4m 03snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 01snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 33snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK6.0 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK18 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
svg_hummingbird_flower__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK13m 00s$0Details |
Hummingbird at Flower
7 cells with a result. Compare the outputs
7 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK3m 30s$0.54Details |
| DeepSeek V4.1 FlashDeepSeek | default (33k cap)OK45 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (33k cap)OK2m 41snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 36snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 00snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK8.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK31 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Melting Ice Cream Cone
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK2m 27s$0.47Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 16snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 27snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 58snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK55 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL40 snot recorded: the run's token counts were never reported, so there is no estimate |
Five-Storey Pagoda
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK4m 33s$0.78Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 29snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK3m 12snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK2m 11snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 21snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK9.0 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL1m 03snot recorded: the run's token counts were never reported, so there is no estimate |
Ring of Keys
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK3m 18s$0.60Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 06snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 32snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 46snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 30snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK8.4 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL1m 02snot recorded: the run's token counts were never reported, so there is no estimate |
Kids Building a Snowman
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK4m 55s$0.81Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK46 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 28snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 51snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK58 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK21 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL39 snot recorded: the run's token counts were never reported, so there is no estimate |
Kingfisher Diving
7 cells with a result. Compare the outputs
7 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK3m 47s$0.66Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK44 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 03snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 50snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 10snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK6.6 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK30 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Knight in Armour
7 cells with a result. Compare the outputs
7 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK3m 47s$0.78Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK56 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 20snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 55snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 01snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK27 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
svg_ladybug_leaf__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK9m 10s$0Details |
Ladybug on a Leaf
7 cells with a result. Compare the outputs
5 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK3m 21s$0.61Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK53 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 17snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 40snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK56 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)DNF MODEL10 snot recorded: the run's token counts were never reported, so there is no estimate |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL36 snot recorded: the run's token counts were never reported, so there is no estimate |
Latte Art
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK2m 27s$0.46Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK3m 48snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 52snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK2m 20snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK59 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK5.7 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL38 snot recorded: the run's token counts were never reported, so there is no estimate |
Lavender Fields
5 cells with a result. Compare the outputs
5 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 04snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 54snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 15snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK8.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK26 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Layer Cake Slice
4 cells with a result. Compare the outputs
4 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 14snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 18snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK32 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Line Icon Set
4 cells with a result. Compare the outputs
4 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK36 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK1m 33snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK9.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK21 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Login Screen
4 cells with a result. Compare the outputs
4 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK34 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK1m 21snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK21 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Giant Mech
3 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK44 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK9.9 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL35 snot recorded: the run's token counts were never reported, so there is no estimate |
Mechanical Keyboard
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK13 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL56 snot recorded: the run's token counts were never reported, so there is no estimate |
Medieval Castle
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK6.1 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK26 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Mermaid on a Rock
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK9.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK27 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Monarch Butterfly
4 cells with a result. Compare the outputs
3 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (33k cap)OK47 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (33k cap)OK3m 18snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK9.6 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL40 snot recorded: the run's token counts were never reported, so there is no estimate |
Monster Truck Jump
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL39 snot recorded: the run's token counts were never reported, so there is no estimate |
Domed Mosque
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK14 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK27 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Mountain Lake at Dawn
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.9 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL37 snot recorded: the run's token counts were never reported, so there is no estimate |
Music Player UI
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK4.7 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK18 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Northern Lights
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK17 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Octopus Juggling Teacups
13 cells with a result. Compare the outputs
11 finished cells
Old Fisherman
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.7 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL34 snot recorded: the run's token counts were never reported, so there is no estimate |
Painter at an Easel
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK27 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
svg_panda_bamboo__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK13m 45s$0Details |
Panda Eating Bamboo
11 cells with a result. Compare the outputs
11 finished cells
Peacock Tail Display
4 cells with a result. Compare the outputs
3 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (33k cap)OK1m 09snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (33k cap)OK2m 42snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK8.2 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL35 snot recorded: the run's token counts were never reported, so there is no estimate |
Emperor Penguin Huddle
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK9.4 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK48 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Phoenix Rising
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK6.4 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK21 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Pizza Slice Cheese Pull
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK9.6 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL40 snot recorded: the run's token counts were never reported, so there is no estimate |
Polar Bear on Ice Floe
7 cells with a result. Compare the outputs
7 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK3m 28s$0.52Details |
| DeepSeek V4.1 FlashDeepSeek | default (33k cap)OK49 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (33k cap)OK2m 42snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK2m 00snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK51 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK5.7 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK32 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Potted Succulents
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK15 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK28 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Fitness Activity Rings
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK3.4 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK14 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Bowl of Ramen
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.7 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK24 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Double-Decker Bus
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK17 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL40 snot recorded: the run's token counts were never reported, so there is no estimate |
svg_red_fox_snow__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK7m 31s$0Details |
Red Fox in Snow
13 cells with a result. Compare the outputs
12 finished cells
Retro Desktop Computer
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.2 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK24 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Rice Terraces
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK32 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Robot Vacuum
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK6.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK7.0 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Robot Tending a Flower
2 cells with a result. Compare the outputs
0 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)DNF MODEL9.2 snot recorded: the run's token counts were never reported, so there is no estimate |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL37 snot recorded: the run's token counts were never reported, so there is no estimate |
Colourful Row Houses
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL34 snot recorded: the run's token counts were never reported, so there is no estimate |
Sailboat Regatta
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK5.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL41 snot recorded: the run's token counts were never reported, so there is no estimate |
Swimming Sea Turtle
12 cells with a result. Compare the outputs
11 finished cells
Server Rack
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK9.9 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Vintage Sewing Machine
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK4.2 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK31 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Skateboarder Ollie
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK9.2 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL36 snot recorded: the run's token counts were never reported, so there is no estimate |
Sleeping Curled Cat
14 cells with a result. Compare the outputs
14 finished cells
Exploded Smartphone
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK13 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL37 snot recorded: the run's token counts were never reported, so there is no estimate |
Smartwatch
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK8.2 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK33 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Running Shoe
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL37 snot recorded: the run's token counts were never reported, so there is no estimate |
Rocket Launch
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK15 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK24 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Starfighter in a Hangar
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL1m 07snot recorded: the run's token counts were never reported, so there is no estimate |
Stack of Pancakes
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL37 snot recorded: the run's token counts were never reported, so there is no estimate |
svg_steam_locomotive__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK9m 58s$0Details |
Steam Locomotive
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL35 snot recorded: the run's token counts were never reported, so there is no estimate |
Steampunk Airship
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK4.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Deep-Sea Submarine
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK3.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL40 snot recorded: the run's token counts were never reported, so there is no estimate |
Sushi Platter
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK3.7 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK26 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Suspension Bridge in Fog
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK22 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Multi-Tool Pocket Knife
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK5.9 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK23 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Trio of Tacos
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK13 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL41 snot recorded: the run's token counts were never reported, so there is no estimate |
Prairie Thunderstorm
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK9.7 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK20 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Settings Toggles
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK2.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Open Toolbox
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK8.1 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL38 snot recorded: the run's token counts were never reported, so there is no estimate |
Toucan on a Branch
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK3.9 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL36 snot recorded: the run's token counts were never reported, so there is no estimate |
Cable Car on a Hill
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK14 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Treehouse
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK6.9 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL34 snot recorded: the run's token counts were never reported, so there is no estimate |
Tropical Beach
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK6.1 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK29 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Open Umbrella in Rain
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK31 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Kelp Forest
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK8.2 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL38 snot recorded: the run's token counts were never reported, so there is no estimate |
Unicorn in a Meadow
2 cells with a result. Compare the outputs
0 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)DNF MODEL12 snot recorded: the run's token counts were never reported, so there is no estimate |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL38 snot recorded: the run's token counts were never reported, so there is no estimate |
Vintage Biplane
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL45 snot recorded: the run's token counts were never reported, so there is no estimate |
Vintage Scooter
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK13 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL44 snot recorded: the run's token counts were never reported, so there is no estimate |
Vintage Typewriter
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK32 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Erupting Volcano
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK5.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL43 snot recorded: the run's token counts were never reported, so there is no estimate |
VR Headset
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK6.4 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK26 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Jungle Waterfall
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.4 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL1m 05snot recorded: the run's token counts were never reported, so there is no estimate |
Weather Widget
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK7.1 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK33 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Wizard Casting a Spell
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (33k cap)OK8.4 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL54 snot recorded: the run's token counts were never reported, so there is no estimate |
Wolf Howling at Moon
9 cells with a result. Compare the outputs
8 finished cells
threejs_ant_vs_gardener
8 cells with a result. Compare the outputs
6 finished cells
| Model | Claude Code | Codex CLI | dsh | OpenCode |
|---|---|---|---|---|
| Claude Opus 5.5Anthropic | · | · | · | OK2h 01m$23.38try 2/2Details |
| Claude Sonnet 5.5Anthropic | DNF TIMEOUT46m 03snot recorded: the run's token counts were never reported, so there is no estimate | · | · | · |
| Claude Fable 5.1Anthropic | · | · | · | OK58m 55s$19.74try 2/2Details |
| GPT-6 AstraOpenAI | · | OK28m 07s$7.00Details | · | OK26m 33s$5.25Details |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK34m 56s$0.19Details | OK26m 41s$0.15Details |
| Kimi K3Moonshot | · | · | · | DNF INFRA1m 18snot recorded: the run's usage was never recorded |
Garden Automation Tutorial
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK5.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL45 snot recorded: the run's token counts were never reported, so there is no estimate |
threejs_jellyfish
8 cells with a result. Compare the outputs
7 finished cells
| Model | Claude Code | Codex CLI | dsh | OpenCode |
|---|---|---|---|---|
| Claude Opus 5.5Anthropic | OK2h 30m$27.01try 2/2Details | · | · | OK2h 00m$18.44try 2/2Details |
| Claude Fable 5.1Anthropic | OK50m 56s$17.42try 2/2Details | · | · | OK44m 58s$19.05try 2/2Details |
| GPT-6 AstraOpenAI | · | OK32m 03s$7.53Details | · | OK18m 28s$4.51Details |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK45m 32s$0.26Details | DNF INFRA18 snot recorded: the run's usage was never recorded |
threejs_momijigari
8 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | dsh | OpenCode |
|---|---|---|---|---|
| Claude Opus 5.5Anthropic | OK2h 47m$28.88try 3/3Details | · | · | OK1h 29m$16.80try 2/2Details |
| Claude Fable 5.1Anthropic | DNF TIMEOUT43m 04s$12.85 | · | · | OK1h 00m$8.29try 2/2Details |
| GPT-6 AstraOpenAI | · | OK25m 18s$6.73Details | · | OK25m 34s$4.77Details |
| DeepSeek V4.1 FlashDeepSeek | · | · | DNF INFRA7.2 snot recorded: the run's token counts were never reported, so there is no estimate | · |
| LongCat 2.5 PreviewMeituan | · | · | · | DNF TIMEOUT42m 53s$0 |
Night Train
9 cells with a result. Compare the outputs
6 finished cells
Paris Tower
6 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK3m 46snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK3m 31snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK2m 42snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK2m 28snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK15 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK19 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
threejs_space_bunny
6 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | DNF STOPPED2h 30m$24.21try 2/2 | · | OK1h 04m$13.43try 2/2Details |
| Claude Fable 5.1Anthropic | OK1h 00m$24.27try 2/2Details | · | OK1h 26m$18.82try 2/2Details |
| GPT-6 AstraOpenAI | · | OK27m 34s$8.89Details | OK16m 08s$4.23Details |
threejs_tidewater
7 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK1h 58m$19.27try 2/2Details | · | OK1h 58m$22.05try 2/2Details |
| Claude Fable 5.1Anthropic | DNF TIMEOUT42m 34s$13.03 | · | OK1h 40m$24.39try 2/2Details |
| GPT-6 AstraOpenAI | · | OK31m 46s$8.67Details | OK33m 21s$6.88Details |
| LongCat 2.5 PreviewMeituan | · | · | DNF TIMEOUT12m 24s$0try 2/2 |
x16_engine
11 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK2h 48m$25.18try 2/2Details | · | OK1h 34m$17.07try 2/2Details |
| Claude Sonnet 5.5Anthropic | · | · | DNF TIMEOUT46m 03s$5.99 |
| Claude Fable 5.1Anthropic | DNF TIMEOUT42m 34s$11.59 | · | OK28m 06s$8.67try 2/2Details |
| GPT-6 AstraOpenAI | · | OK27m 14s$7.71Details | OK13m 57s$2.84Details |
| Kimi K3Moonshot | · | · | DNF INFRA16m 25s$0.67 |
| GLM-5.3Z.ai | DNF INFRA3m 08snot recorded: the run's usage was never recorded | · | DNF INFRA19m 36s$0.28 |
| LongCat 2.5 PreviewMeituan | · | · | DNF TIMEOUT42m 56s$0 |
blender_lowpoly_dragon
5 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | dsh | OpenCode |
|---|---|---|---|---|
| Claude Opus 5.5Anthropic | No result HARNESS ×1 | · | · | No result INFRA ×1 |
| Claude Fable 5.1Anthropic | No result INFRA ×1 | · | · | No result INFRA ×1 |
| GPT-6 AstraOpenAI | · | OK22m 04s$6.83try 2/2Details | · | OK49m 50s$6.57Details |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK1h 07m$0.17try 2/2Details | OK1h 26m$0.15Details |
| Kimi K3Moonshot | · | · | · | OK1h 21m$2.31Details |
blender_chess_set_midgame
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 AstraOpenAI | OK38m 49s$12.22Details |
blender_cosy_isometric_study
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 AstraOpenAI | OK44m 24s$13.23Details |
blender_lighthouse_diorama
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 AstraOpenAI | OK21m 11s$6.65Details |
blender_sci_fi_helmet
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 AstraOpenAI | OK37m 20s$9.48Details |
blender_vintage_rangefinder_camera
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 AstraOpenAI | OK50m 03s$12.77Details |
Acoustic Guitar
14 cells with a result. Compare the outputs
11 finished cells
Illustrated Alphabet A B C
14 cells with a result. Compare the outputs
11 finished cells
svg_astronaut_floating__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK7m 46s$0Details |
Bohr Model of an Atom
14 cells with a result. Compare the outputs
12 finished cells
Fruit Sales Bar Chart
14 cells with a result. Compare the outputs
14 finished cells
Baseball Stadium
14 cells with a result. Compare the outputs
12 finished cells
Basketball Slam Dunk
14 cells with a result. Compare the outputs
13 finished cells
Bauhaus Composition
14 cells with a result. Compare the outputs
14 finished cells
Labelled Bicycle Diagram
14 cells with a result. Compare the outputs
11 finished cells
svg_boxing_ring__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK8m 33s$0Details |
Boxing Ring
14 cells with a result. Compare the outputs
13 finished cells
Butterfly Life Cycle
14 cells with a result. Compare the outputs
12 finished cells
Campus Map
14 cells with a result. Compare the outputs
11 finished cells
svg_chat_interface__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK6m 56s$0Details |
Chessboard Mid-Game
14 cells with a result. Compare the outputs
10 finished cells
svg_city_park_top_down__agent
1 cell with a result. Compare the outputs
0 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | DNF TIMEOUT33m 56s$0 |
Top-Down City Park
14 cells with a result. Compare the outputs
12 finished cells
Chalkboard Coffee Lettering
14 cells with a result. Compare the outputs
12 finished cells
svg_cyberpunk_alley__agent
1 cell with a result. Compare the outputs
0 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | DNF TIMEOUT12m 54s$0 |
Cycling Peloton
14 cells with a result. Compare the outputs
10 finished cells
svg_detective_noir__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK15m 15s$0Details |
Festival Oil Lamps
10 cells with a result. Compare the outputs
10 finished cells
DNA Double Helix
10 cells with a result. Compare the outputs
9 finished cells
Energy Mix Donut Chart
10 cells with a result. Compare the outputs
10 finished cells
svg_dragon_sleeping_castle__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK12m 04s$0Details |
3D Block Letters
10 cells with a result. Compare the outputs
9 finished cells
Drum Kit
10 cells with a result. Compare the outputs
9 finished cells
Basket of Painted Eggs
10 cells with a result. Compare the outputs
9 finished cells
Fantasy World Map
10 cells with a result. Compare the outputs
8 finished cells
svg_film_camera__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK3m 25s$0Details |
Coffee Decision Flowchart
10 cells with a result. Compare the outputs
10 finished cells
svg_food_pyramid__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK12m 48s$0Details |
Food Pyramid
10 cells with a result. Compare the outputs
9 finished cells
Fractal Tree
10 cells with a result. Compare the outputs
10 finished cells
Straw in a Glass
10 cells with a result. Compare the outputs
9 finished cells
Glitch Text
10 cells with a result. Compare the outputs
10 finished cells
svg_grand_piano__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK28m 58s$0Details |
Grand Piano
9 cells with a result. Compare the outputs
7 finished cells
svg_halloween_drippy_boo__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK9m 22s$0Details |
Drippy BOO Lettering
7 cells with a result. Compare the outputs
7 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK2m 45s$0.49Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK58 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 02snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 35snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK56 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK7.4 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK22 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
svg_hand_five_fruits__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK5m 44s$0Details |
Hand Holding Five Fruits
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK3m 30s$0.54Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 18snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 51snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK2m 05snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK58 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK8.1 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL42 snot recorded: the run's token counts were never reported, so there is no estimate |
svg_hello_neon_sign__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK22m 42s$0Details |
Human Eye Diagram
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK3m 05s$0.48Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 38snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK3m 12snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 31snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 44snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL36 snot recorded: the run's token counts were never reported, so there is no estimate |
svg_human_heart_anatomy__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK27m 20s$0Details |
Human Heart Anatomy
7 cells with a result. Compare the outputs
5 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK3m 35s$0.59Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)DNF MODEL4m 32snot recorded: the run's token counts were never reported, so there is no estimate |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK3m 28snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 33snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK2m 03snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK7.0 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL41 snot recorded: the run's token counts were never reported, so there is no estimate |
svg_human_skeleton_front__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK3m 24s$0Details |
Human Skeleton
7 cells with a result. Compare the outputs
7 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK2m 49s$0.49Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK60 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK4m 17snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 38snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 13snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK5.8 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK30 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
svg_islamic_star_tiling__agent
1 cell with a result. Compare the outputs
0 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | DNF TIMEOUT24m 58s$0 |
Geometric Star Tiling
7 cells with a result. Compare the outputs
5 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)DNF MODEL2m 16s$0.40 |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 26snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK4m 05snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 13snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 20snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL37 snot recorded: the run's token counts were never reported, so there is no estimate |
Isometric Coffee Shop
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK4m 31s$1.00Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 46snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK5m 43snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK2m 21snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 12snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK18 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL58 snot recorded: the run's token counts were never reported, so there is no estimate |
Isometric Cube Illusion
7 cells with a result. Compare the outputs
7 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK40 s$0.098Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 14snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK7m 13snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 28snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 48snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK15 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK24 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Isometric Farm
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK5m 03s$0.82Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 34snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK6m 04snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK2m 30snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 28snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK17 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL39 snot recorded: the run's token counts were never reported, so there is no estimate |
Isometric Harbour
7 cells with a result. Compare the outputs
5 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK5m 28s$0.90Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK3m 15snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)DNF MODEL4m 01snot recorded: the run's token counts were never reported, so there is no estimate |
| GPT-6 SolOpenAI | high (64k cap)OK2m 36snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK58 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK23 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL34 snot recorded: the run's token counts were never reported, so there is no estimate |
Isometric Workspace
7 cells with a result. Compare the outputs
5 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK4m 38s$0.76Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 33snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK3m 38snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK2m 26snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 20snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)DNF MODEL24 snot recorded: the run's token counts were never reported, so there is no estimate |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL37 snot recorded: the run's token counts were never reported, so there is no estimate |
Isometric Space Station
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK4m 52s$0.85Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 34snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK4m 07snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK2m 21snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK1m 51snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK13 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL40 snot recorded: the run's token counts were never reported, so there is no estimate |
svg_jack_o_lanterns__agent
1 cell with a result. Compare the outputs
0 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | DNF TIMEOUT5m 25s$0 |
Jack-o'-Lanterns
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK4m 32s$0.74Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK40 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 21snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 56snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK48 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL43 snot recorded: the run's token counts were never reported, so there is no estimate |
svg_japanese_pagoda__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK16m 20s$0Details |
Seigaiha Wave Pattern
7 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | high (64k cap)OK1m 03s$0.13Details |
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK57 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 54snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 SolOpenAI | high (64k cap)OK1m 23snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 LunaOpenAI | high (64k cap)OK34 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK26 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL42 snot recorded: the run's token counts were never reported, so there is no estimate |
svg_latte_art__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK6m 16s$0Details |
Temperature Line Chart
4 cells with a result. Compare the outputs
4 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK19 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK33 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK16 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Bakery Badge
4 cells with a result. Compare the outputs
3 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK59 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 05snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.0 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL39 snot recorded: the run's token counts were never reported, so there is no estimate |
Bookshop Logo
4 cells with a result. Compare the outputs
4 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK59 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK3m 22snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK3.8 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK4.4 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Craft Drinks Label Emblem
4 cells with a result. Compare the outputs
4 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 09snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 38snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK4.7 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK22 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
svg_logo_coffee_roaster__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK2m 50s$0Details |
Coffee Roaster Logo
4 cells with a result. Compare the outputs
4 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK49 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK1m 16snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK5.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK32 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Gym Logo
4 cells with a result. Compare the outputs
3 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK56 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 23snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK4.8 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL38 snot recorded: the run's token counts were never reported, so there is no estimate |
Florist Monoline Logo
4 cells with a result. Compare the outputs
3 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK55 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK1m 35snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)DNF MODEL11 snot recorded: the run's token counts were never reported, so there is no estimate |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK15 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Outdoor Gear Emblem
4 cells with a result. Compare the outputs
4 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK52 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 16snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK17 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK23 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Pet Clinic Logo
4 cells with a result. Compare the outputs
3 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK54 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 32snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK8.7 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL38 snot recorded: the run's token counts were never reported, so there is no estimate |
Space Program Patch
4 cells with a result. Compare the outputs
3 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK48 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 10snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK7.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL37 snot recorded: the run's token counts were never reported, so there is no estimate |
svg_logo_sushi_bar__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK37m 57s$0Details |
Sushi Bar Logo
4 cells with a result. Compare the outputs
3 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK57 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 04snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK5.0 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL37 snot recorded: the run's token counts were never reported, so there is no estimate |
Geometric Tech Logo
4 cells with a result. Compare the outputs
4 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK1m 14snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 19snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK3.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK16 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Lunar New Year Lanterns
4 cells with a result. Compare the outputs
3 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK57 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK2m 38snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK8.2 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL37 snot recorded: the run's token counts were never reported, so there is no estimate |
Colourful Mandala
4 cells with a result. Compare the outputs
4 finished cells
| Model | Raw API |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | default (64k cap)OK58 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| DeepSeek V4 ProDeepSeek | default (64k cap)OK1m 55snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK24 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Memphis Pattern
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)DNF MODEL2.6 snot recorded: the run's token counts were never reported, so there is no estimate |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK31 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Cat Seeing a Lion
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK7.8 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK6.6 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Ornate Monogram
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.0 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL37 snot recorded: the run's token counts were never reported, so there is no estimate |
Phases of the Moon
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK16 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL34 snot recorded: the run's token counts were never reported, so there is no estimate |
svg_mountain_lake_dawn__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK12m 49s$0Details |
Hiking Trail Map
2 cells with a result. Compare the outputs
0 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)DNF MODEL4.8 snot recorded: the run's token counts were never reported, so there is no estimate |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL35 snot recorded: the run's token counts were never reported, so there is no estimate |
New Year Fireworks
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK22 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK27 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Op Art Waves
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK14 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK27 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Orchestra Seating Chart
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.6 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL39 snot recorded: the run's token counts were never reported, so there is no estimate |
Organisation Chart
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK4.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK15 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Impossible Triangle
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK14 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL40 snot recorded: the run's token counts were never reported, so there is no estimate |
Periodic Table Excerpt
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK24 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Budget Pie Chart
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK5.8 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK13 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Plant Cell Diagram
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK8.1 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL37 snot recorded: the run's token counts were never reported, so there is no estimate |
Reflection in a Puddle
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK39 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Recycling Process
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK7.4 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK6.9 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
svg_retro_crt_computer__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK6m 47s$0Details |
svg_rice_terraces__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK11m 13s$0Details |
Rock Band on Stage
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK16 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Rock Climber
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.8 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK31 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Saxophone
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK5.2 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK9.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
svg_sewing_machine__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK15m 00s$0Details |
Sheet Music Excerpt
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK13 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL36 snot recorded: the run's token counts were never reported, so there is no estimate |
Downhill Skier
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL36 snot recorded: the run's token counts were never reported, so there is no estimate |
Overhead Kick
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL38 snot recorded: the run's token counts were never reported, so there is no estimate |
Solar System
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK4.1 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK18 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Sports Team Crest
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK8.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL34 snot recorded: the run's token counts were never reported, so there is no estimate |
Cherry Blossom Picnic
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK5.6 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL35 snot recorded: the run's token counts were never reported, so there is no estimate |
Abstract Stained Glass
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK13 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK23 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Stay Wild Circular Badge
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.6 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK17 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Metro Map
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL33 snot recorded: the run's token counts were never reported, so there is no estimate |
Summer Beach Day
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK19 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL35 snot recorded: the run's token counts were never reported, so there is no estimate |
Sunburst Rays
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK17 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK6.1 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Surfer in a Barrel
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK28 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
svg_sushi_platter__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK6m 27s$0Details |
svg_suspension_bridge_fog__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK8m 59s$0Details |
Butterfly Stroke Swimmer
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK37 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
svg_swiss_army_knife__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK11m 54s$0Details |
Modular Synthesizer
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK8.0 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL32 snot recorded: the run's token counts were never reported, so there is no estimate |
Tennis Serve
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK8.2 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK37 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Thank You Script
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK4.8 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL40 snot recorded: the run's token counts were never reported, so there is no estimate |
Harvest Dinner Table
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK7.2 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL42 snot recorded: the run's token counts were never reported, so there is no estimate |
Stacked Animals
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK5.9 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL38 snot recorded: the run's token counts were never reported, so there is no estimate |
History of Flight Timeline
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)DNF MODEL6.8 snot recorded: the run's token counts were never reported, so there is no estimate |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK31 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
svg_treasure_map__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK4m 29s$0Details |
Pirate Treasure Map
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK5.1 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL53 snot recorded: the run's token counts were never reported, so there is no estimate |
Valentine Letter
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK15 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK34 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Three-Circle Venn Diagram
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.3 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK21 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Vintage Travel Poster Type
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK4.4 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL39 snot recorded: the run's token counts were never reported, so there is no estimate |
svg_vinyl_turntable__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK10m 23s$0Details |
Record Turntable
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK4.5 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL43 snot recorded: the run's token counts were never reported, so there is no estimate |
Violin and Bow
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK9.4 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL40 snot recorded: the run's token counts were never reported, so there is no estimate |
Volcano Cross-Section
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK10 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL40 snot recorded: the run's token counts were never reported, so there is no estimate |
svg_voronoi_cells__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK3m 39s$0Details |
Voronoi Pattern
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL31 snot recorded: the run's token counts were never reported, so there is no estimate |
svg_water_cycle_diagram__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK4m 11s$0Details |
Water Cycle Diagram
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK6.9 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL42 snot recorded: the run's token counts were never reported, so there is no estimate |
svg_weather_widget__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK1m 38s$0Details |
Snowy Holiday Cabin
2 cells with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK11 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)DNF MODEL33 snot recorded: the run's token counts were never reported, so there is no estimate |
Cloud Lettering
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK7.9 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Qwen3.8 27BAlibaba Qwen (via Cerebras) | default (64k cap)OK23 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Blizzard Cabin
1 cell with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| gpt-oss-120bOpenAI open-weight (via Cerebras) | high (64k cap)OK12 snot recorded: the run's token counts were never reported, so there is no estimateDetails |
blender_steam_locomotive
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 AstraOpenAI | OK37m 23s$12.73Details |
hyperframes_glass_launch_ui
4 cells with a result. Compare the outputs
1 finished cells
| Model | Claude Code | OpenCode |
|---|---|---|
| Claude Opus 5.5Anthropic | DNF INFRA24m 51s$4.45 | · |
| Claude Sonnet 5.5Anthropic | DNF ERROR38m 03s$8.60 | DNF INFRA23m 14s$4.06 |
| Kimi K3Moonshot | · | OK51m 54s$2.09Details |
quadruped_rig_walk
1 cell with a result. Compare the outputs
0 finished cells
| Model | OpenCode |
|---|---|
| DeepSeek V4.1 FlashDeepSeek | DNF HARNESS58m 15s$0.12 |
svg_soccer_bicycle_kick__agent
1 cell with a result. Compare the outputs
1 finished cells
| Model | OpenCode |
|---|---|
| LongCat 2.5 PreviewMeituan | OK26m 53s$0Details |
remotion_ai_dungeon
3 cells with a result. Compare the outputs
1 finished cells
| Model | Claude Code | OpenCode |
|---|---|---|
| Claude Opus 5.5Anthropic | OK4h 04m$172.93Details | · |
| Claude Sonnet 5.5Anthropic | DNF HARNESS45m 52snot recorded: the run's token counts were never reported, so there is no estimate | DNF TIMEOUT46m 02s$7.10 |
remotion_how_internet_works
3 cells with a result. Compare the outputs
1 finished cells
| Model | Claude Code | OpenCode |
|---|---|---|
| Claude Opus 5.5Anthropic | OK1h 06m$9.54Details | · |
| Claude Sonnet 5.5Anthropic | DNF TIMEOUT45m 56snot recorded: the run's token counts were never reported, so there is no estimate | DNF INFRA25m 23s$3.71 |
coastal_shallows
1 cell with a result. Compare the outputs
0 finished cells
| Model | Claude Code |
|---|---|
| Claude Sonnet 5.5Anthropic | DNF TIMEOUT45m 59snot recorded: the run's token counts were never reported, so there is no estimate |
blender_humanoid_walk_cycle
6 cells with a result. Compare the outputs
4 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK1h 41m$8.85try 2/2Details | · | · |
| Claude Sonnet 5.5Anthropic | DNF TIMEOUT54m 38snot recorded: the run's token counts were never reported, so there is no estimate | · | · |
| GPT-6 AstraOpenAI | · | OK1h 38m$19.54Details | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK1h 20m$0.16Details |
| GLM-5.3Z.ai | · | · | DNF TIMEOUT55m 35snot recorded: the run's usage was never recorded |
| gpt-6.1-solOpenAI | · | OK1h 33mnot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
cine_dolly_zoom
4 cells with a result. Compare the outputs
4 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK24m 11s$1.80Details | · |
| Claude Sonnet 5.5Anthropic | OK19m 02snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
| GPT-6 SolOpenAI | · | OK27m 34s$1.54Details |
| gpt-6.1-solOpenAI | · | OK28m 12snot recorded: the run's token counts were never reported, so there is no estimateDetails |
creature_robot_blueprint
6 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK37m 09s$5.07try 2/2Details | · | · |
| Claude Sonnet 5.5Anthropic | OK34m 51snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| GPT-6 AstraOpenAI | · | OK23m 35s$5.33Details | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK17m 12s$0.17Details |
| GLM-5.3Z.ai | · | · | DNF TIMEOUT42m 28s$2.67 |
| gpt-6.1-solOpenAI | · | OK19m 46snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
html_fox_forest_run
4 cells with a result. Compare the outputs
4 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK30m 07s$3.50Details | · |
| Claude Sonnet 5.5Anthropic | OK18m 40snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
| GPT-6 SolOpenAI | · | OK9m 56s$0.90Details |
| gpt-6.1-solOpenAI | · | OK38m 58snot recorded: the run's token counts were never reported, so there is no estimateDetails |
humanoid_motion_cycle
6 cells with a result. Compare the outputs
4 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK4m 08s$0.64try 2/2Details | · | · |
| Claude Sonnet 5.5Anthropic | OK36m 28snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| GPT-6 AstraOpenAI | · | OK50m 34s$10.77Details | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK16m 43s$0.15Details |
| GLM-5.3Z.ai | · | · | DNF TIMEOUT30m 10snot recorded: the run's usage was never recorded |
| gpt-6.1-solOpenAI | · | DNF TIMEOUT57m 50snot recorded: the run's token counts were never reported, so there is no estimate | · |
threejs_procedural_armor_suit
6 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK4m 03s$0.65try 2/2Details | · | · |
| Claude Sonnet 5.5Anthropic | OK35m 54snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| GPT-6 AstraOpenAI | · | OK25m 49s$5.99Details | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK1h 59m$0.13Details |
| GLM-5.3Z.ai | · | · | DNF TIMEOUT40m 57s$1.64 |
| gpt-6.1-solOpenAI | · | OK42m 02snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
video_printing_press_collage_hyperframes
6 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK1h 16m$2.09Details | · | · |
| Claude Sonnet 5.5Anthropic | OK1h 13mnot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| GPT-6 AstraOpenAI | · | OK1h 56m$44.44Details | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK1h 44m$0.17try 2/2Details |
| GLM-5.3Z.ai | · | · | DNF TIMEOUT3h 22m$7.37 |
| gpt-6.1-solOpenAI | · | OK33m 44snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
video_printing_press_collage_remotion
5 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | DNF MODEL57m 46s$4.95 | · | · |
| Claude Sonnet 5.5Anthropic | DNF TIMEOUT33m 13snot recorded: the run's token counts were never reported, so there is no estimate | · | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | DNF TIMEOUT1h 31m$0.11 |
| GLM-5.3Z.ai | · | · | OK2h 47m$4.76Details |
| gpt-6.1-solOpenAI | · | OK37m 24snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
blender_spongebob
6 cells with a result. Compare the outputs
6 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK15m 58s$0.84Details | · | · |
| Claude Sonnet 5.5Anthropic | OK44m 56snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| GPT-6 AstraOpenAI | · | OK32m 56s$6.79Details | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK1h 14m$0.052Details |
| GLM-5.3Z.ai | · | · | OK1h 06m$1.70Details |
| gpt-6.1-solOpenAI | · | OK14m 40snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
cine_dutch_angle
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK21m 50s$2.93Details | · |
| GPT-6 SolOpenAI | · | OK9m 03s$0.96Details |
cine_noir_low_key
4 cells with a result. Compare the outputs
4 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK40m 17s$4.16Details | · |
| Claude Sonnet 5.5Anthropic | OK25m 13snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
| GPT-6 SolOpenAI | · | OK8m 26s$1.34Details |
| gpt-6.1-solOpenAI | · | OK17m 03snot recorded: the run's token counts were never reported, so there is no estimateDetails |
cine_orbit_360
4 cells with a result. Compare the outputs
4 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK47m 43s$2.91Details | · |
| Claude Sonnet 5.5Anthropic | OK23m 50snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
| GPT-6 SolOpenAI | · | OK17m 28s$1.23Details |
| gpt-6.1-solOpenAI | · | OK1h 13mnot recorded: the run's token counts were never reported, so there is no estimateDetails |
cine_silhouette_backlight
4 cells with a result. Compare the outputs
4 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK37m 02s$4.90Details | · |
| Claude Sonnet 5.5Anthropic | OK26m 49snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
| GPT-6 SolOpenAI | · | OK14m 31s$2.77Details |
| gpt-6.1-solOpenAI | · | OK34m 18snot recorded: the run's token counts were never reported, so there is no estimateDetails |
cine_tracking_shot
3 cells with a result. Compare the outputs
3 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK42m 50s$4.30Details | · |
| Claude Sonnet 5.5Anthropic | OK27m 24snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
| GPT-6 SolOpenAI | · | OK35m 07s$2.62Details |
game_battleship
6 cells with a result. Compare the outputs
6 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK14m 39s$2.46try 2/2Details | · | · |
| Claude Sonnet 5.5Anthropic | OK14m 59snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| Claude Haiku 5.5Anthropic | OK8m 31snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK7m 45s$0.069Details |
| GLM-5.3Z.ai | · | · | OK26m 23s$1.08Details |
| gpt-6.1-solOpenAI | · | OK33m 06snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
threejs_slime_softbody
5 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK55m 03s$4.70try 2/2Details | · | · |
| Claude Sonnet 5.5Anthropic | OK42m 13snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK1h 23m$0.17Details |
| GLM-5.3Z.ai | · | · | OK58m 38s$3.04Details |
| gpt-6.1-solOpenAI | · | OK42m 53snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
algoviz_pathfinding_race
8 cells with a result. Compare the outputs
8 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK14m 02s$2.45Details | · | · |
| Claude Sonnet 5.5Anthropic | OK8m 06snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| Claude Fable 5.1Anthropic | OK27m 35s$10.20Details | · | · |
| Claude Haiku 5.5Anthropic | OK7m 51snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| GPT-6 AstraOpenAI | · | OK13m 28s$4.30Details | OK8m 39s$2.55Details |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK5m 38s$0.049Details |
| GPT-6 SolOpenAI | · | OK7m 10s$1.00Details | · |
algoviz_sorting_race
7 cells with a result. Compare the outputs
7 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK15m 08s$2.62Details | · | · |
| Claude Sonnet 5.5Anthropic | OK8m 30snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| Claude Haiku 5.5Anthropic | OK7m 56snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| GPT-6 AstraOpenAI | · | OK15m 17s$4.34Details | OK11m 49s$3.22Details |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK10m 01s$0.057Details |
| GPT-6 SolOpenAI | · | OK6m 20s$0.90Details | · |
appclone_retro_desktop
8 cells with a result. Compare the outputs
8 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK11m 52s$2.37Details | · | · |
| Claude Sonnet 5.5Anthropic | OK8m 15snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| Claude Fable 5.1Anthropic | OK34m 06s$12.03Details | · | · |
| GPT-6 AstraOpenAI | · | OK11m 27s$3.61Details | OK16m 38s$4.36Details |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK7m 14s$0.069Details |
| GPT-6 SolOpenAI | · | OK6m 25s$0.91Details | · |
| gpt-6.1-solOpenAI | · | OK33m 18snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
appclone_spreadsheet
7 cells with a result. Compare the outputs
7 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK12m 42s$2.62Details | · | · |
| Claude Sonnet 5.5Anthropic | OK9m 15snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| Claude Fable 5.1Anthropic | OK33m 50s$11.65Details | · | · |
| GPT-6 AstraOpenAI | · | OK13m 58s$4.13Details | OK13m 03s$4.13Details |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK11m 47s$0.077Details |
| GPT-6 SolOpenAI | · | OK6m 50s$1.07Details | · |
dash_coffee_chain_sales
5 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK9m 26s$2.02Details | · | · |
| Claude Sonnet 5.5Anthropic | OK6m 09snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| GPT-6 AstraOpenAI | · | OK25m 57s$4.21Details | OK21m 11s$4.58Details |
| GPT-6 SolOpenAI | · | OK6m 16s$0.93Details | · |
threejs_artwork_style_pass
11 cells with a result. Compare the outputs
4 finished cells
threejs_mechanical_bee
11 cells with a result. Compare the outputs
7 finished cells
threejs_stillwater_pond
7 cells with a result. Compare the outputs
4 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK40m 18s$7.27Details | · | · |
| Claude Sonnet 5.5Anthropic | OK25m 27snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| Claude Fable 5.1Anthropic | DNF TIMEOUT43m 02s$15.37 | · | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK31m 19s$0.22Details |
| GLM-5.3Z.ai | · | · | DNF TIMEOUT42m 56s$0.46 |
| GPT-6 SolOpenAI | · | OK14m 02s$1.69Details | · |
| gpt-6.1-solOpenAI | · | DNF TIMEOUT43m 00snot recorded: the run's token counts were never reported, so there is no estimate | · |
hyperframes_brutalist_event_promo
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK20m 37s$4.46Details | · |
| GPT-6 SolOpenAI | · | OK16m 29s$4.44Details |
hyperframes_css_3d_cube_gallery
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK17m 59s$3.83Details |
hyperframes_glass_dashboard_launch
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK25m 23s$4.92Details | · |
| GPT-6 SolOpenAI | · | OK23m 33s$3.23Details |
hyperframes_ink_brush_dragon
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK42m 32s$8.54Details | · |
| GPT-6 SolOpenAI | · | OK15m 39s$3.36Details |
hyperframes_isometric_server_room
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK24m 53s$6.29Details | · |
| GPT-6 SolOpenAI | · | OK15m 43s$2.86Details |
hyperframes_lighthouse_storm
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK26m 23s$4.56Details | · |
| GPT-6 SolOpenAI | · | OK21m 08s$3.76Details |
hyperframes_product_reveal_watch
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK17m 09s$2.82Details |
hyperframes_terminal_hacker_boot
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK33m 38s$5.09Details | · |
| GPT-6 SolOpenAI | · | OK15m 29s$2.63Details |
hyperframes_tokyo_neon_title
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK24m 23s$4.12Details |
remotion_chess_famous_game
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK11m 38s$1.40Details |
remotion_chip_fabrication_journey
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK11m 32s$1.77Details |
remotion_energy_mix_sankey
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK23m 58s$3.24Details | · |
| GPT-6 SolOpenAI | · | OK13m 35s$1.80Details |
remotion_f1_lap_telemetry
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK26m 08s$4.76Details | · |
| GPT-6 SolOpenAI | · | OK12m 44s$1.62Details |
remotion_galaxy_collision
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK28m 51s$4.07Details | · |
| GPT-6 SolOpenAI | · | OK14m 13s$1.84Details |
remotion_github_contrib_wrapped
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK11m 27s$1.71Details |
remotion_music_visualizer_synthwave
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK30m 38s$3.91Details | · |
| GPT-6 SolOpenAI | · | OK12m 22s$1.42Details |
remotion_orbital_launch_sequence
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK13m 16s$1.71Details |
remotion_satellite_constellation
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK28m 20s$5.19Details | · |
| GPT-6 SolOpenAI | · | OK11m 28s$1.63Details |
remotion_sorting_algorithms_race
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK14m 28s$2.10Details |
threelab_breed_generative_art
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK11m 57s$1.99Details | · |
| GPT-6 SolOpenAI | · | OK7m 16s$1.16Details |
webgpu_deferred_sponza_playground
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK9m 44s$1.64Details |
webgpu_fishing_game
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK13m 53s$1.96Details |
webgpu_ocean_wave_physics
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK36m 39s$2.94Details | · |
| GPT-6 SolOpenAI | · | OK7m 35s$1.25Details |
webgpu_sailing_storm
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK16m 28s$2.70Details |
one_prompt_3d_kart_racer
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK21m 46s$3.98Details | · |
| GPT-6 SolOpenAI | · | OK6m 34s$0.86Details |
webgpu_particle_life_audio
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK10m 53s$1.72Details |
webgpu_snow_physics
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK16m 06s$2.82Details |
threejs_domino_chain_physics
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK23m 31s$3.35Details |
threejs_evolving_art_garden
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK27m 14s$4.01Details | · |
| GPT-6 SolOpenAI | · | OK9m 42s$1.22Details |
threejs_ps1_horror_kitchen
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK22m 32s$4.23Details | · |
| GPT-6 SolOpenAI | · | OK9m 31s$1.15Details |
webgpu_ink_marbling
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK17m 10s$3.16Details |
shader_hero_background_studio
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK11m 38s$2.24Details | · |
| GPT-6 SolOpenAI | · | OK14m 39s$2.04Details |
threejs_tiny_anime_world
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK31m 18s$4.67Details | · |
| GPT-6 SolOpenAI | · | OK8m 59s$1.16Details |
threejs_torchlit_dungeon_dragon
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK13m 54s$1.51Details |
webgpu_ascii_shader_scene
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK15m 30s$2.96Details | · |
| GPT-6 SolOpenAI | · | OK9m 39s$1.66Details |
one_key_rhythm_runner
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK19m 32s$3.07Details | · |
| GPT-6 SolOpenAI | · | OK9m 02s$1.25Details |
threejs_marble_run_machine
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK13m 26s$1.71Details |
threejs_solar_sail_orrery
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK12m 32s$1.44Details | · |
| GPT-6 SolOpenAI | · | OK9m 01s$1.30Details |
webgl_reaction_diffusion_coral
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK16m 10s$1.91Details | · |
| GPT-6 SolOpenAI | · | OK12m 25s$1.80Details |
image_to_procedural_threejs_scene
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK37m 48s$6.03Details | · |
| GPT-6 SolOpenAI | · | OK7m 17s$1.04Details |
js13k_style_shader_game
3 cells with a result. Compare the outputs
3 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK15m 29s$2.90Details | · |
| Claude Haiku 5.5Anthropic | OK8m 07snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
| GPT-6 SolOpenAI | · | OK6m 41s$0.95Details |
procedural_lego_builder
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK10m 27s$1.59Details |
threejs_boids_dragon
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 SolOpenAI | OK17m 07s$2.34Details |
threejs_pathtraced_product_shot
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK37m 55s$5.45Details | · |
| GPT-6 SolOpenAI | · | OK13m 27s$1.78Details |
threejs_rocket_car_arena
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK22m 04s$2.93Details | · |
| GPT-6 SolOpenAI | · | OK7m 10s$1.03Details |
volumetric_raymarched_sun
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK18m 35s$2.88Details | · |
| GPT-6 SolOpenAI | · | OK9m 18s$1.42Details |
webgl_particle_life_sim
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK18m 13s$2.50Details | · |
| GPT-6 SolOpenAI | · | OK10m 34s$1.52Details |
algoviz_balanced_trees
3 cells with a result. Compare the outputs
3 finished cells
| Model | Codex CLI | OpenCode |
|---|---|---|
| GPT-6 AstraOpenAI | OK20m 54s$5.24Details | · |
| DeepSeek V4.1 FlashDeepSeek | · | OK18m 51s$0.16Details |
| GPT-6 SolOpenAI | OK10m 33s$1.44Details | · |
algoviz_convex_hull_race
4 cells with a result. Compare the outputs
4 finished cells
| Model | Claude Code | Codex CLI |
|---|---|---|
| Claude Opus 5.5Anthropic | OK20m 08s$3.10Details | · |
| Claude Sonnet 5.5Anthropic | OK27m 48snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
| GPT-6 SolOpenAI | · | OK6m 05s$0.88Details |
| gpt-6.1-solOpenAI | · | OK31m 21snot recorded: the run's token counts were never reported, so there is no estimateDetails |
algoviz_fourier_epicycles
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 AstraOpenAI | OK16m 24s$4.12Details |
algoviz_hash_table_showdown
5 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Fable 5.1Anthropic | OK41m 11s$16.72Details | · | · |
| GPT-6 AstraOpenAI | · | OK24m 53s$5.22Details | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK27m 53s$0.21Details |
| GPT-6 SolOpenAI | · | OK10m 12s$1.66Details | · |
| gpt-6.1-solOpenAI | · | OK22m 44snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
algoviz_maze_generate_and_solve
7 cells with a result. Compare the outputs
7 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK18m 51s$2.65Details | · | · |
| Claude Sonnet 5.5Anthropic | OK11m 13snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| Claude Fable 5.1Anthropic | OK25m 17s$9.88Details | · | · |
| GPT-6 AstraOpenAI | · | OK16m 34s$3.95Details | OK17m 14s$3.12Details |
| GPT-6 SolOpenAI | · | OK7m 20s$1.09Details | · |
| gpt-6.1-solOpenAI | · | OK19m 36snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
algoviz_edit_distance_dp
3 cells with a result. Compare the outputs
3 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Sonnet 5.5Anthropic | OK17m 45snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| GPT-6 AstraOpenAI | · | OK18m 40s$5.26Details | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK19m 21s$0.12Details |
algoviz_raft_consensus
2 cells with a result. Compare the outputs
2 finished cells
| Model | OpenCode |
|---|---|
| GPT-6 AstraOpenAI | OK17m 30s$4.71Details |
| DeepSeek V4.1 FlashDeepSeek | OK17m 28s$0.077Details |
appclone_calendar_planner
5 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK31m 40s$6.49Details | · | · |
| Claude Sonnet 5.5Anthropic | OK26m 38snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| GPT-6 AstraOpenAI | · | OK31m 52s$9.96Details | OK19m 49s$5.75Details |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK17m 43s$0.13Details |
appclone_code_editor
6 cells with a result. Compare the outputs
6 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK41m 30s$7.57Details | · | · |
| Claude Sonnet 5.5Anthropic | OK27m 23snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| GPT-6 AstraOpenAI | · | OK25m 22s$6.88Details | OK21m 41s$5.48Details |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK23m 24s$0.14Details |
| GPT-6 SolOpenAI | · | OK11m 52s$2.11Details | · |
appclone_drum_machine_daw
7 cells with a result. Compare the outputs
7 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Sonnet 5.5Anthropic | OK28m 20snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| Claude Fable 5.1Anthropic | OK34m 02s$14.04Details | · | · |
| GPT-6 AstraOpenAI | · | OK31m 32s$8.56Details | OK13m 46s$3.84Details |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK8m 13s$0.079Details |
| GPT-6 SolOpenAI | · | OK8m 46s$1.41Details | · |
| gpt-6.1-solOpenAI | · | OK40m 15snot recorded: the run's token counts were never reported, so there is no estimateDetails | · |
appclone_kanban_board
4 cells with a result. Compare the outputs
4 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Sonnet 5.5Anthropic | OK30m 53snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| GPT-6 AstraOpenAI | · | OK40m 27s$9.99Details | · |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK18m 52s$0.14Details |
| GPT-6 SolOpenAI | · | OK13m 44s$2.52Details | · |
appclone_team_chat
5 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK24m 48s$3.95Details | · | · |
| Claude Sonnet 5.5Anthropic | OK23m 02snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| Claude Fable 5.1Anthropic | OK39m 00s$12.85Details | · | · |
| GPT-6 AstraOpenAI | · | · | OK22m 00s$4.88Details |
| GPT-6 SolOpenAI | · | OK8m 21s$1.30Details | · |
algoviz_mst_kruskal_prim
2 cells with a result. Compare the outputs
2 finished cells
| Model | Claude Code | OpenCode |
|---|---|---|
| Claude Opus 5.5Anthropic | OK17m 55s$3.53Details | · |
| GPT-6 AstraOpenAI | · | OK14m 11s$4.29Details |
appclone_paint_studio
5 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK38m 14s$6.82Details | · | · |
| GPT-6 AstraOpenAI | · | OK30m 57s$8.64Details | OK20m 13s$6.31Details |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK35m 54s$0.21Details |
| GPT-6 SolOpenAI | · | OK8m 36s$1.28Details | · |
appclone_photo_editor
6 cells with a result. Compare the outputs
6 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK25m 48s$4.74Details | · | · |
| Claude Sonnet 5.5Anthropic | OK29m 12snot recorded: the run's token counts were never reported, so there is no estimateDetails | · | · |
| Claude Fable 5.1Anthropic | OK36m 51s$12.88Details | · | · |
| GPT-6 AstraOpenAI | · | · | OK21m 15s$5.40Details |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK28m 54s$0.14Details |
| GPT-6 SolOpenAI | · | OK10m 37s$1.73Details | · |
algoviz_gpu_boids_50k
5 cells with a result. Compare the outputs
5 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK34m 57s$4.09Details | · | · |
| GPT-6 AstraOpenAI | · | OK27m 56s$6.20Details | OK14m 45s$3.61Details |
| DeepSeek V4.1 FlashDeepSeek | · | · | OK29m 56s$0.12Details |
| GPT-6 SolOpenAI | · | OK10m 31s$1.36Details | · |
Codrops-style scroll story: the life of a raindrop
5 cells with a result. Compare the outputs
5 finished cells
| Model | Raw API |
|---|---|
| Claude Fable 5.1Anthropic | call (64k cap)OK9m 28s$2.46Details |
| GPT-6 AstraOpenAI | callOK4m 43s$0.75Details |
| DeepSeek V4 ProDeepSeek | call (64k cap)OK3m 30snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| gpt-6.1-solOpenAI | callOK2m 40snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| minimax-m3unknown | call (64k cap)OK2m 35snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Victorian optical toys in 3D: zoetrope, phenakistiscope, praxinoscope (Three.js)
2 cells with a result. Compare the outputs
2 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | callOK4m 50s$0.80Details |
| gpt-6.1-solOpenAI | callOK3m 47snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Vintage biplane aerobatics over a grass airfield (Three.js)
4 cells with a result. Compare the outputs
4 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | call (64k cap)OK7m 52s$1.00Details |
| GPT-6 AstraOpenAI | callOK4m 44s$0.58Details |
| DeepSeek V4 ProDeepSeek | call (64k cap)OK2m 50snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Grok 4.7xAI | No result QUOTA ×1 |
| Gemini 3.8 FlashGoogle | No result QUOTA ×1 |
| Kimi K3Moonshot | No result QUOTA ×1 |
| gemini-3.1-pro-preview | No result QUOTA ×1 |
| gemini-3.5-flash | No result QUOTA ×1 |
| gpt-6.1-solOpenAI | callOK2m 37snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Retro arcade claw machine with pastel plush prizes (Three.js)
6 cells with a result. Compare the outputs
6 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | call (64k cap)OK5m 00s$0.65Details |
| Claude Fable 5.1Anthropic | call (64k cap)OK9m 11s$2.37Details |
| GPT-6 AstraOpenAI | callOK4m 43s$0.76Details |
| DeepSeek V4 ProDeepSeek | call (64k cap)OK2m 10snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Grok 4.7xAI | No result QUOTA ×1 |
| Gemini 3.8 FlashGoogle | No result QUOTA ×1 |
| Kimi K3Moonshot | No result QUOTA ×1 |
| gemini-3.1-pro-preview | No result QUOTA ×1 |
| gemini-3.5-flash | No result QUOTA ×1 |
| gpt-6.1-solOpenAI | callOK3m 44snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| qwen3p8-maxAlibaba | call (64k cap)OK10m 09snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Four-stroke engine cutaway: crank, piston and cam-driven valves (Three.js)
8 cells with a result. Compare the outputs
8 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | call (64k cap)OK5m 13s$0.68Details |
| Claude Fable 5.1Anthropic | call (64k cap)OK8m 12s$2.08Details |
| Claude Haiku 5.5Anthropic | call (64k cap)OK3m 36snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| GPT-6 AstraOpenAI | callOK3m 08s$0.52Details |
| DeepSeek V4 ProDeepSeek | call (64k cap)OK8m 21snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Grok 4.7xAI | No result QUOTA ×1 |
| Kimi K3Moonshot | No result QUOTA ×1 |
| gemini-3.1-pro-preview | No result QUOTA ×1 |
| gemini-3.5-flash | No result QUOTA ×1 |
| gpt-6.1-solOpenAI | callOK2m 45snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| minimax-m3unknown | call (64k cap)OK3m 35snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| qwen3p8-maxAlibaba | call (64k cap)OK5m 17snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Hot air balloon festival over rolling fields (Three.js)
9 cells with a result. Compare the outputs
9 finished cells
Synthwave hover-bike racer on a neon grid highway (Three.js)
7 cells with a result. Compare the outputs
7 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | call (64k cap)OK3m 45s$0.48Details |
| Claude Sonnet 5.5Anthropic | call (64k cap)OK5m 02snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Claude Fable 5.1Anthropic | call (64k cap)OK7m 05s$1.76Details |
| GPT-6 AstraOpenAI | callOK2m 22s$0.44Details |
| DeepSeek V4 ProDeepSeek | call (64k cap)OK6m 28snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Grok 4.7xAI | No result QUOTA ×1 |
| Gemini 3.8 FlashGoogle | No result QUOTA ×1 |
| Kimi K3Moonshot | No result QUOTA ×1 |
| gemini-3.1-pro-preview | No result QUOTA ×1 |
| gemini-3.5-flash | No result QUOTA ×1 |
| gpt-6.1-solOpenAI | callOK1m 55snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| minimax-m3unknown | call (64k cap)OK3m 27snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Outer-space pinball table with planet bumpers (Three.js)
5 cells with a result. Compare the outputs
5 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | callOK4m 58s$0.69Details |
| DeepSeek V4 ProDeepSeek | call (64k cap)OK3m 50snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Grok 4.7xAI | No result QUOTA ×1 |
| Gemini 3.8 FlashGoogle | No result QUOTA ×1 |
| Kimi K3Moonshot | No result QUOTA ×1 |
| gemini-3.1-pro-preview | No result QUOTA ×1 |
| gemini-3.5-flash | No result QUOTA ×1 |
| gpt-6.1-solOpenAI | callOK3m 05snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| minimax-m3unknown | call (64k cap)OK4m 28snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| qwen3p8-maxAlibaba | call (64k cap)OK9m 03snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Floating pirate island diorama with a cliff cross-section (Three.js)
7 cells with a result. Compare the outputs
7 finished cells
| Model | Raw API |
|---|---|
| Claude Opus 5.5Anthropic | call (64k cap)OK7m 28s$0.97Details |
| Claude Fable 5.1Anthropic | call (64k cap)OK8m 02s$1.94Details |
| GPT-6 AstraOpenAI | callOK3m 58s$0.71Details |
| DeepSeek V4 ProDeepSeek | call (64k cap)OK2m 47snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| Grok 4.7xAI | No result QUOTA ×1 |
| Gemini 3.8 FlashGoogle | No result QUOTA ×1 |
| Kimi K3Moonshot | No result QUOTA ×1 |
| gemini-3.1-pro-preview | No result QUOTA ×1 |
| gemini-3.5-flash | No result QUOTA ×1 |
| gpt-6.1-solOpenAI | callOK5m 50snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| minimax-m3unknown | call (64k cap)OK3m 29snot recorded: the run's token counts were never reported, so there is no estimateDetails |
| qwen3p8-maxAlibaba | call (64k cap)OK9m 48snot recorded: the run's token counts were never reported, so there is no estimateDetails |
Rube Goldberg breakfast machine on a kitchen countertop (Three.js)
1 cell with a result. Compare the outputs
1 finished cells
| Model | Raw API |
|---|---|
| GPT-6 AstraOpenAI | callOK5m 39s$0.65Details |
| Grok 4.7xAI | No result QUOTA ×1 |
| Gemini 3.8 FlashGoogle | No result QUOTA ×1 |
| Kimi K3Moonshot | No result QUOTA ×1 |
| gemini-3.1-pro-preview | No result QUOTA ×1 |
| gemini-3.5-flash | No result QUOTA ×1 |
dash_ecommerce_funnel
2 cells with a result. Compare the outputs
2 finished cells
| Model | Codex CLI | OpenCode |
|---|---|---|
| GPT-6 AstraOpenAI | OK31m 55s$6.88Details | OK23m 52s$4.30Details |
dash_power_grid_day
3 cells with a result. Compare the outputs
3 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK19m 13s$2.69Details | · | · |
| GPT-6 AstraOpenAI | · | OK22m 56s$5.01Details | OK28m 28s$6.12Details |
dash_saas_growth_metrics
3 cells with a result. Compare the outputs
3 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK21m 25s$3.76Details | · | · |
| GPT-6 AstraOpenAI | · | OK34m 04s$6.41Details | OK17m 58s$4.09Details |
dash_world_weather_stations
3 cells with a result. Compare the outputs
3 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK20m 14s$2.99Details | · | · |
| GPT-6 AstraOpenAI | · | OK31m 34s$4.18Details | OK37m 21s$4.73Details |
cine_crane_rise
1 cell with a result. Compare the outputs
1 finished cells
| Model | Claude Code |
|---|---|
| Claude Sonnet 5.5Anthropic | OK30m 11snot recorded: the run's token counts were never reported, so there is no estimateDetails |
cine_low_angle_hero
1 cell with a result. Compare the outputs
1 finished cells
| Model | Claude Code |
|---|---|
| Claude Sonnet 5.5Anthropic | OK19m 54snot recorded: the run's token counts were never reported, so there is no estimateDetails |
cine_rack_focus
1 cell with a result. Compare the outputs
1 finished cells
| Model | Claude Code |
|---|---|
| Claude Sonnet 5.5Anthropic | OK33m 22snot recorded: the run's token counts were never reported, so there is no estimateDetails |
cine_whip_pan
1 cell with a result. Compare the outputs
1 finished cells
| Model | Claude Code |
|---|---|
| Claude Sonnet 5.5Anthropic | OK24m 52snot recorded: the run's token counts were never reported, so there is no estimateDetails |
firstprinciples_mascot_multimedia
1 cell with a result. Compare the outputs
1 finished cells
| Model | Claude Code |
|---|---|
| Claude Sonnet 5.5Anthropic | OK22m 48snot recorded: the run's token counts were never reported, so there is no estimateDetails |
threejs_gerstner_ocean_storm
1 cell with a result. Compare the outputs
1 finished cells
| Model | Claude Code |
|---|---|
| Claude Sonnet 5.5Anthropic | OK14m 17snot recorded: the run's token counts were never reported, so there is no estimateDetails |
threejs_gpgpu_galaxy_collision
1 cell with a result. Compare the outputs
1 finished cells
| Model | Claude Code |
|---|---|
| Claude Sonnet 5.5Anthropic | OK5m 08snot recorded: the run's token counts were never reported, so there is no estimateDetails |
threejs_infinite_terrain_flyover
1 cell with a result. Compare the outputs
1 finished cells
| Model | Claude Code |
|---|---|
| Claude Sonnet 5.5Anthropic | OK15m 44snot recorded: the run's token counts were never reported, so there is no estimateDetails |
threejs_jetski_ocean_physics
1 cell with a result. Compare the outputs
1 finished cells
| Model | Claude Code |
|---|---|
| Claude Sonnet 5.5Anthropic | OK17m 19snot recorded: the run's token counts were never reported, so there is no estimateDetails |
threejs_soap_bubble_shader_playground
1 cell with a result. Compare the outputs
1 finished cells
| Model | Claude Code |
|---|---|
| Claude Sonnet 5.5Anthropic | OK8m 50s$0.84Details |
threejs_toy_pool_water
1 cell with a result. Compare the outputs
1 finished cells
| Model | Claude Code |
|---|---|
| Claude Sonnet 5.5Anthropic | OK31m 12snot recorded: the run's token counts were never reported, so there is no estimateDetails |
video_style_morph_character_hyperframes
1 cell with a result. Compare the outputs
1 finished cells
| Model | Claude Code |
|---|---|
| Claude Sonnet 5.5Anthropic | OK37m 40snot recorded: the run's token counts were never reported, so there is no estimateDetails |
video_style_morph_character_remotion
1 cell with a result. Compare the outputs
1 finished cells
| Model | Claude Code |
|---|---|
| Claude Sonnet 5.5Anthropic | OK24m 05snot recorded: the run's token counts were never reported, so there is no estimateDetails |
dash_football_league_season
2 cells with a result. Compare the outputs
2 finished cells
| Model | Codex CLI | OpenCode |
|---|---|---|
| GPT-6 AstraOpenAI | OK36m 11s$4.80Details | OK20m 47s$4.48Details |
dash_marathon_results
2 cells with a result. Compare the outputs
2 finished cells
| Model | Codex CLI | OpenCode |
|---|---|---|
| GPT-6 AstraOpenAI | OK38m 43s$6.39Details | OK31m 49s$5.60Details |
threejs_mobile_touch_arcade_game
4 cells with a result. Compare the outputs
4 finished cells
| Model | Claude Code | Codex CLI | OpenCode |
|---|---|---|---|
| Claude Opus 5.5Anthropic | OK32m 05s$3.78Details | · | · |
| GPT-6 AstraOpenAI | · | OK41m 21s$6.65Details | OK42m 01s$6.15Details |
| Kimi K3Moonshot | · | · | OK29m 55s$2.02Details |
threejs_octopus_reef
1 cell with a result. Compare the outputs
1 finished cells
| Model | Claude Code |
|---|---|
| Claude Haiku 5.5Anthropic | OK17m 49snot recorded: the run's token counts were never reported, so there is no estimateDetails |
threejs_impressionist_world
1 cell with a result. Compare the outputs
1 finished cells
| Model | Codex CLI |
|---|---|
| GPT-6 AstraOpenAI | OK23m 50s$3.37Details |