SVG
292 tests. Tap a picture to open the demo; the model name opens the full result.
More
One SVG file per run, shown as drawn: controllers, pelicans on bicycles, animals, buildings, icons and UI.
292 tests · 1,614 finished runs (300 agent, 1314 raw one-shot)
SVG by model (the per-model galleries).
1,614 finished runs
Step through all of them in the galleryOne player, arrow keys or swipe.
DualSense controller, max fidelity Test page · 28 finished
SVGClaude Fable 5.1Claude Codeskills off
SVGClaude Fable 5.1Claude Codeskills off
SVGClaude Fable 5.1OpenCodeskills off
SVGClaude Fable 5.1Raw API (one-shot)raw API baseline
SVGClaude Fable 5.1Raw API (one-shot)raw API baseline
SVGClaude Opus 5.5Claude Codeskills off
SVGClaude Opus 5.5OpenCodeskills off
SVGClaude Opus 5.5OpenCodeskills offserved model unverified (proxy log lost)
SVGClaude Opus 5.5Raw API (one-shot)raw API baseline
SVGDeepSeek V4 ProRaw API (one-shot)raw API baseline
SVGDeepSeek V4.1 Flashdshskills off
SVGDeepSeek V4.1 FlashOpenCodeskills off
- Harness config failure (ours)
Claude Fable 5.1Claude Codeskills off
- Infrastructure failure
Claude Fable 5.1Claude Codeskills off
- Stopped by our timeout
Claude Fable 5.1Raw API (one-shot)raw API baseline
- Did not finish
Claude Opus 5.5Raw API (one-shot)raw API baseline
- Did not finish
Claude Opus 5.5Raw API (one-shot)raw API baseline
- Did not finish
Claude Opus 5.5Raw API (one-shot)raw API baseline
- Did not finish
Claude Opus 5.5Raw API (one-shot)raw API baseline
- Did not finish
Claude Opus 5.5Raw API (one-shot)raw API baseline
- Did not finish
Claude Opus 5.5Raw API (one-shot)raw API baseline
- Stopped by our timeout
Claude Sonnet 5.5Claude Codeskills off
- Stopped by our timeout
Claude Sonnet 5.5OpenCodeskills off
- Error
DeepSeek V4.1 FlashCline CLIskills off
- Stopped by our timeout
Gemini 3.8 FlashCline CLIskills off
- Error
Gemini 3.8 FlashCline CLIskills off
- Harness and model mismatch
GLM-5.3Claude Codeskills off
- Stopped by us
MiMo V2.6 FlashCline CLIskills off
See all 28 finished runs of DualSense controller, max fidelity
Animated pelican riding a bicycle (SMIL/CSS) Test page · 25 finished
SVG
Claude Opus 5.5Claude Codeskills off
SVG
Claude Fable 5.1OpenCodeskills off
SVG
Claude Opus 5.5OpenCodeskills off
SVG
GPT-6 AstraOpenCodeskills off
SVG
Kimi K3Kimi Code CLIskills off
SVG
Claude Fable 5.1Claude Codeskills off
SVG
DeepSeek V4.1 Flashdshskills off
SVG
GLM-5.3OpenCodeskills off
SVG
GPT-6 AstraCodex CLIskills off
SVG
Kimi K3OpenCodeskills off
SVG
Grok 4.7OpenCodeskills off
SVG
DeepSeek V4.1 FlashOpenCodeskills off
- Error
Claude Opus 5.5Hermes Agent + Oh-My-Hermesskills off
- Stopped by us
Claude Opus 5.5Hermes Agent + Oh-My-Hermesskills off
- Stopped by us
Claude Opus 5.5Hermes Agent + Oh-My-Hermesskills off
- Error
Claude Opus 5.5Hermes Agentskills off
- Stopped by us
Claude Opus 5.5Hermes Agentskills off
- Stopped by us
Claude Opus 5.5Hermes Agentskills off
- Error
Claude Opus 5.5Oh My Piskills off
- Error
DeepSeek V4.1 FlashCline CLIskills off
- Did not finish
Gemini 3.6 FlashRaw API (one-shot)raw API baseline
- Harness and model mismatch
GLM-5.3Claude Codeskills off
- Infrastructure failure
GLM-5.3Claude Codeskills off
- Stopped by our timeout
MiMo V2.6 FlashCline CLIskills off
- Error
MiMo V2.6 FlashCline CLIskills off
See all 25 finished runs of Animated pelican riding a bicycle (SMIL/CSS)
Pelican riding a bicycle (control) Test page · 30 finished
SVGClaude Fable 5.1OpenCodeskills off
SVGClaude Opus 5.5Claude Codeskills off
SVGGLM-5.3OpenCodeskills off
SVGGPT-6 AstraCodex CLIskills off
SVGGrok 4.7Grok Buildskills off
SVGClaude Opus 5.5OpenCodeskills off
SVGGPT-6 AstraOpenCodeskills off
SVGKimi K3OpenCodeskills off
SVGClaude Fable 5.1Claude Codeskills off
SVGKimi K3Kimi Code CLIskills off
SVGGrok 4.7OpenCodeskills off
SVGDeepSeek V4.1 Flashdshskills off
- Stopped by us
Claude Opus 5.5Hermes Agent + Oh-My-Hermesskills off
- Stopped by us
Claude Opus 5.5Hermes Agentskills off
- Stopped by us
Claude Opus 5.5Hermes Agentskills off
- Error
Gemini 3.6 FlashRaw API (one-shot)raw API baseline
- Error
Gemini 3.7 FlashRaw API (one-shot)raw API baseline
- Harness and model mismatch
GLM-5.3Claude Codeskills off
See all 30 finished runs of Pelican riding a bicycle (control)
Isometric SVG town with sprite sheet Test page · 22 finished
SVGClaude Fable 5.1OpenCodeskills off
SVGClaude Opus 5.5Claude Codeskills off
SVGClaude Fable 5.1Claude Codeskills off
SVGDeepSeek V4.1 Flashdshskills off
SVG
GLM-5.3OpenCodeskills off
SVGGPT-6 AstraCodex CLIskills off
SVGGPT-6 AstraOpenCodeskills off
SVGGrok 4.7Grok Buildskills off
SVGDeepSeek V4.1 FlashOpenCodeskills off
SVGGrok 4.7OpenCodeskills off
SVGKimi K3Kimi Code CLIskills off
SVG
Kimi K3OpenCodeskills off
- Did not finish
Claude Opus 5.5OpenCodeskills off
- Error
Claude Sonnet 5.5Claude Codeskills off
- Stopped by our timeout
Claude Sonnet 5.5OpenCodeskills off
- Error
DeepSeek V4.1 FlashCline CLIskills off
- Did not finish
Gemini 3.6 FlashRaw API (one-shot)raw API baseline
- Harness and model mismatch
GLM-5.3Claude Codeskills off
- Did not finish
GLM-5.3Claude Codeskills off
- Stopped by our timeout
MiMo V2.6 FlashCline CLIskills off
- Error
MiMo V2.6 FlashCline CLIskills off
See all 22 finished runs of Isometric SVG town with sprite sheet
MacBook Pro 16" realistic 3D render (Playcode benchmark) Test page · 21 finished
SVGClaude Opus 5.5Claude Codeskills off
SVGClaude Opus 5.5OpenCodeskills off
SVGClaude Fable 5.1Claude Codeskills off
SVGClaude Fable 5.1OpenCodeskills off
SVGGLM-5.3OpenCodeskills off
SVGGPT-6 AstraOpenCodeskills off
SVGGPT-6 AstraCodex CLIskills off
SVGGrok 4.7Grok Buildskills off
SVGKimi K3OpenCodeskills off
SVGKimi K3Kimi Code CLIskills off
SVGDeepSeek V4.1 Flashdshskills off
SVGDeepSeek V4.1 FlashOpenCodeskills off
- Stopped by us
Claude Opus 5.5OpenCodeskills off
- Stopped by our timeout
Claude Sonnet 5.5OpenCodeskills off
- Error
DeepSeek V4.1 FlashCline CLIskills off
- Did not finish
Gemini 3.6 FlashRaw API (one-shot)raw API baseline
- Did not finish
Gemini 3.8 FlashCline CLIskills off
- Error
Gemini 3.8 FlashCline CLIskills off
- Harness and model mismatch
GLM-5.3Claude Codeskills off
- Error
MiMo V2.6 FlashCline CLIskills off
- Error
MiMo V2.6 FlashCline CLIskills off
See all 21 finished runs of MacBook Pro 16" realistic 3D render (Playcode benchmark)
California brown pelican riding a bicycle (detailed spec) Test page · 24 finished
SVGClaude Fable 5.1Claude Codeskills off
SVGClaude Fable 5.1OpenCodeskills off
SVGClaude Opus 5.5Claude Codeskills off
SVGClaude Opus 5.5Hermes Agentskills off
SVGClaude Opus 5.5Kilo Code CLIskills off
SVG
Claude Opus 5.5Oh My Piskills off
SVGClaude Opus 5.5OpenCodeskills off
SVGClaude Opus 5.5Pi + skills kitskills off
SVGClaude Opus 5.5Piskills off
SVGDeepSeek V4.1 Flashdshskills off
SVGDeepSeek V4.1 FlashOpenCodeskills off
SVGGemini 3.8 FlashCline CLIskills off
- Stopped by us
Claude Opus 5.5Hermes Agent + Oh-My-Hermesskills off
- Stopped by our timeout
Claude Sonnet 5.5OpenCodeskills off
- Error
DeepSeek V4.1 FlashCline CLIskills off
- Did not finish
Gemini 3.6 FlashRaw API (one-shot)raw API baseline
- Harness and model mismatch
GLM-5.3Claude Codeskills off
- Error
MiMo V2.6 FlashCline CLIskills off
See all 24 finished runs of California brown pelican riding a bicycle (detailed spec)
Lighthouse on a headland at night Test page · 21 finished
SVGClaude Fable 5.1OpenCodeskills off
SVGClaude Fable 5.1Claude Codeskills off
SVGClaude Opus 5.5Claude Codeskills off
SVGClaude Opus 5.5OpenCodeskills off
SVG
Grok 4.7Grok Buildskills off
SVGKimi K3OpenCodeskills off
SVGDeepSeek V4.1 Flashdshskills off
SVGGPT-6 AstraCodex CLIskills off
SVGGPT-6 AstraOpenCodeskills off
SVGGrok 4.7OpenCodeskills off
SVGKimi K3Kimi Code CLIskills off
SVGDeepSeek V4.1 FlashOpenCodeskills off
- Stopped by our timeout
Claude Sonnet 5.5Claude Codeskills off
- Stopped by our timeout
Claude Sonnet 5.5OpenCodeskills off
- Stopped by us
DeepSeek V4.1 FlashCline CLIskills off
- Did not finish
Gemini 3.6 FlashRaw API (one-shot)raw API baseline
- Did not finish
Gemini 3.7 FlashRaw API (one-shot)raw API baseline
- Harness and model mismatch
GLM-5.3Claude Codeskills off
- Stopped by us
MiMo V2.6 FlashCline CLIskills off
See all 21 finished runs of Lighthouse on a headland at night
Xbox 360 controller Test page · 21 finished
SVGClaude Fable 5.1Claude Codeskills off
SVGClaude Fable 5.1OpenCodeskills off
SVGClaude Opus 5.5Claude Codeskills off
SVGClaude Opus 5.5OpenCodeskills off
SVGClaude Sonnet 5.5Claude Codeskills off
SVGClaude Sonnet 5.5OpenCodeskills off
SVGDeepSeek V4.1 Flashdshskills off
SVGDeepSeek V4.1 FlashOpenCodeskills off
SVGGemini 3.8 FlashCline CLIskills off
SVGGLM-5.3Claude Codeskills off
SVGGLM-5.3OpenCodeskills off
SVGGPT-6 AstraCodex CLIskills off
- Error
DeepSeek V4.1 FlashCline CLIskills off
- Did not finish
Gemini 3.6 FlashRaw API (one-shot)raw API baseline
- Error
GLM-5.3Claude Codeskills off
- Stopped by us
GLM-5.3Claude Codeskills off
- Harness and model mismatch
GLM-5.3Claude Codeskills off
- Error
GLM-5.3Claude Codeskills off
- Stopped by us
MiMo V2.6 FlashCline CLIskills off
BMW M4 Competition, side view (flat vector) Test page · 22 finished
SVGClaude Fable 5.1Claude Codeskills off
SVGClaude Fable 5.1OpenCodeskills off
SVGClaude Opus 5.5Claude Codeskills off
SVGClaude Opus 5.5Claude Codeskills off
SVGClaude Opus 5.5OpenCodeskills off
SVGClaude Sonnet 5.5Claude Codeskills off
SVGClaude Sonnet 5.5OpenCodeskills off
SVGDeepSeek V4.1 FlashCline CLIskills off
SVGDeepSeek V4.1 Flashdshskills off
SVGDeepSeek V4.1 FlashOpenCodeskills off
SVGGLM-5.3Claude Codeskills off
SVGGLM-5.3OpenCodeskills off
- Did not finish
Gemini 3.6 FlashRaw API (one-shot)raw API baseline
- Did not finish
Gemini 3.8 FlashCline CLIskills off
- Did not finish
Gemini 3.8 FlashCline CLIskills off
- Error
Gemini 3.8 FlashOpenCodeskills off
- Harness and model mismatch
GLM-5.3Claude Codeskills off
See all 22 finished runs of BMW M4 Competition, side view (flat vector)
Pelican car france Test page · 22 finished
SVGClaude Fable 5.1Claude Codeskills off
SVGClaude Fable 5.1OpenCodeskills off
SVGClaude Opus 5.5Claude Codeskills off
SVGClaude Opus 5.5Kilo Code CLIskills off
SVGClaude Opus 5.5Oh My Piskills off
SVGClaude Opus 5.5OpenCodeskills off
SVGClaude Opus 5.5Pi + skills kitskills off
SVGClaude Opus 5.5Piskills off
SVGDeepSeek V4.1 Flashdshskills off
SVGDeepSeek V4.1 FlashOpenCodeskills off
SVGGemini 3.8 FlashCline CLIskills off
SVGGLM-5.3Claude Codeskills off
- Stopped by us
Claude Opus 5.5Hermes Agent + Oh-My-Hermesskills off
- Stopped by us
Claude Opus 5.5Hermes Agentskills off
- Error
DeepSeek V4.1 FlashCline CLIskills off
- Error
MiMo V2.6 FlashCline CLIskills off
Dolphin vlog bicycle Test page · 18 finished
SVGClaude Fable 5.1Claude Codeskills off
SVGClaude Fable 5.1OpenCodeskills off
SVGClaude Opus 5.5Claude Codeskills off
SVGClaude Opus 5.5Oh My Piskills off
SVGClaude Opus 5.5OpenCodeskills off
SVGClaude Opus 5.5Pi + skills kitskills off
SVGClaude Opus 5.5Piskills off
SVGDeepSeek V4.1 FlashOpenCodeskills off
SVGGLM-5.3Claude Codeskills off
SVGGLM-5.3OpenCodeskills off
SVGGPT-6 AstraCodex CLIskills off
SVGGPT-6 AstraOpenCodeskills off
- Stopped by us
Claude Opus 5.5Hermes Agentskills off
- Error
DeepSeek V4.1 FlashCline CLIskills off
- Error
DeepSeek V4.1 FlashCline CLIskills off
- Infrastructure failure
DeepSeek V4.1 Flashdshskills off
- Did not finish
Gemini 3.8 FlashCline CLIskills off
- Error
MiMo V2.6 FlashCline CLIskills off
- Error
Muse Spark 1.3OpenCodeskills off
Whale clouds Test page · 18 finished
SVGClaude Fable 5.1Claude Codeskills off
SVGClaude Fable 5.1OpenCodeskills off
SVG
Claude Opus 5.5Claude Codeskills off
SVGClaude Opus 5.5OpenCodeskills off
SVGDeepSeek V4.1 Flashdshskills off
SVGDeepSeek V4.1 FlashOpenCodeskills off
SVGGemini 3.8 FlashCline CLIskills off
SVGGLM-5.3Claude Codeskills off
SVGGLM-5.3OpenCodeskills off
SVGGPT-6 AstraCodex CLIskills off
SVGGPT-6 AstraOpenCodeskills off
SVGGPT-6 SolCodex CLIskills off
- Error
DeepSeek V4.1 FlashCline CLIskills off
- Infrastructure failure
DeepSeek V4.1 Flashdshskills off
- Error
MiMo V2.6 FlashCline CLIskills off
- Error
MiMo V2.6 FlashCline CLIskills off
Sleeping Curled Cat Test page · 14 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GLM-5.3Raw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
MiniMax M3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 MaxRaw API (one-shot)raw API baseline
Red Fox in Snow Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
MiniMax M3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 MaxRaw API (one-shot)raw API baseline
Barn Owl in Flight Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Elephant Calf Mud Bath Test page · 11 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 MaxRaw API (one-shot)raw API baseline
Octopus Juggling Teacups Test page · 11 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
MiniMax M3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 MaxRaw API (one-shot)raw API baseline
Twin-Bell Alarm Clock Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
MiniMax M3Raw API (one-shot)raw API baseline
Alien Planet Test page · 14 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GLM-5.3Raw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
Ant Colony Cutaway Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Flat App Icon Set Test page · 14 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GLM-5.3Raw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
Art Deco Skyscraper Test page · 13 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
Floating Astronaut Test page · 13 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
Stargazer with Telescope Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Autumn Forest Path Test page · 13 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
Ballet Dancer Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Battery Level Icons Test page · 14 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GLM-5.3Raw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
Breakfast Skillet Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
gpt-oss-120bRaw API (one-shot)raw API baseline
Bubble Tea Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
Claude Opus 5.5Raw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
Exploded Burger Test page · 14 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GLM-5.3Raw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
Calendar Month View Test page · 14 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GLM-5.3Raw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
Canyon River Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Container Ship Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Chameleon on a Branch Test page · 11 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
MiniMax M3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Chat Conversation UI Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
MiniMax M3Raw API (one-shot)raw API baseline
Chef Flipping a Pan Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
Kimi K3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 MaxRaw API (one-shot)raw API baseline
Circuit Board Close-Up Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Corgi Catching a Frisbee Test page · 13 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
Cyberpunk Alley Test page · 11 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Sales Dashboard Card Test page · 14 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GLM-5.3Raw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
Giraffe Side Profile Test page · 11 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 MaxRaw API (one-shot)raw API baseline
Swimming Sea Turtle Test page · 11 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
MiniMax M3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 MaxRaw API (one-shot)raw API baseline
Acoustic Guitar Test page · 11 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
GLM-5.3Raw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
- Did not finish
MiniMax M3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Illustrated Alphabet A B C Test page · 11 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
MiniMax M3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Bohr Model of an Atom Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GLM-5.3Raw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
MiniMax M3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Fruit Sales Bar Chart Test page · 14 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GLM-5.3Raw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
Baseball Stadium Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Basketball Slam Dunk Test page · 13 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GLM-5.3Raw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Bauhaus Composition Test page · 14 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GLM-5.3Raw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
Labelled Bicycle Diagram Test page · 11 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
Claude Sonnet 5Raw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Boxing Ring Test page · 13 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
Butterfly Life Cycle Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
gpt-oss-120bRaw API (one-shot)raw API baseline
Campus Map Test page · 11 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
MiniMax M3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Chessboard Mid-Game Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
Kimi K3Raw API (one-shot)raw API baseline
- Did not finish
MiniMax M3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Top-Down City Park Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Chalkboard Coffee Lettering Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
SVG
MiniMax M3Raw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Cycling Peloton Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Kimi K3Raw API (one-shot)raw API baseline
- Did not finish
GLM-5.3Raw API (one-shot)raw API baseline
- Did not finish
MiniMax M3Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 MaxRaw API (one-shot)raw API baseline
Desert Dunes at Night Test page · 12 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GLM-5.3Raw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
Panda Eating Bamboo Test page · 11 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 MaxRaw API (one-shot)raw API baseline
Desk Lamp and Books Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
SVG
Qwen3.8 MaxRaw API (one-shot)raw API baseline
- Did not finish
DeepSeek V4 ProRaw API (one-shot)raw API baseline
Windmill by a Canal Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
gpt-oss-120bRaw API (one-shot)raw API baseline
Noir Detective Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Group Selfie Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Dragon Coiled on a Tower Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Dragonfly Over Pond Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Quadcopter Drone Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Pyramids at Sunset Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
File Upload Dropzone Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
35mm Film Camera Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Flamingo on One Leg Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Floating Islands Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Fountain Pen and Ink Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Fruit Bowl Still Life Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Retro Handheld Console Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Gardener Watering Plants Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Victorian Glasshouse Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Good Vibes Retro Type Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Gothic Cathedral Facade Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Festival Oil Lamps Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
DNA Double Helix Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Energy Mix Donut Chart Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
3D Block Letters Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Drum Kit Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Basket of Painted Eggs Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Fantasy World Map Test page · 8 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Claude Opus 5.5Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Coffee Decision Flowchart Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Food Pyramid Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Fractal Tree Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Straw in a Glass Test page · 9 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Glitch Text Test page · 10 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Greek Temple Test page · 8 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Wolf Howling at Moon Test page · 8 finished
SVG
Claude Fable 5.1Raw API (one-shot)raw API baseline
SVG
Claude Opus 5.5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
gpt-oss-120bRaw API (one-shot)raw API baseline
Grand Piano Test page · 7 finished
SVG
Claude Sonnet 5Raw API (one-shot)raw API baseline
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Claude Opus 5.5Raw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Honeybee on Honeycomb Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Over-Ear Headphones Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
gpt-oss-120bRaw API (one-shot)raw API baseline
Hedgehog Under Mushroom Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Rescue Helicopter Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Hello Neon Sign Test page · 5 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
GPT-6 AstraRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Hot Air Balloons Test page · 7 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Hourglass Test page · 7 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Hummingbird at Flower Test page · 7 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Melting Ice Cream Cone Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Five-Storey Pagoda Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Ring of Keys Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Kids Building a Snowman Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Kingfisher Diving Test page · 7 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Knight in Armour Test page · 7 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Ladybug on a Leaf Test page · 5 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
- Did not finish
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Latte Art Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Polar Bear on Ice Floe Test page · 7 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Drippy BOO Lettering Test page · 7 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Hand Holding Five Fruits Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Human Eye Diagram Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Human Heart Anatomy Test page · 5 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Human Skeleton Test page · 7 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Geometric Star Tiling Test page · 5 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
GPT-6 AstraRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Isometric Coffee Shop Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Isometric Cube Illusion Test page · 7 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Isometric Farm Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Isometric Harbour Test page · 5 finished
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
DeepSeek V4 ProRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Isometric Workspace Test page · 5 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
- Did not finish
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Isometric Space Station Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Jack-o'-Lanterns Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Seigaiha Wave Pattern Test page · 6 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 AstraRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
GPT-6 SolRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Lavender Fields Test page · 5 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
GPT-6 LunaRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Layer Cake Slice Test page · 4 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Line Icon Set Test page · 4 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Login Screen Test page · 4 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Monarch Butterfly Test page · 3 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Peacock Tail Display Test page · 3 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Temperature Line Chart Test page · 4 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Bakery Badge Test page · 3 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Bookshop Logo Test page · 4 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Craft Drinks Label Emblem Test page · 4 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Coffee Roaster Logo Test page · 4 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Gym Logo Test page · 3 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Florist Monoline Logo Test page · 3 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
gpt-oss-120bRaw API (one-shot)raw API baseline
Outdoor Gear Emblem Test page · 4 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Pet Clinic Logo Test page · 3 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Space Program Patch Test page · 3 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Sushi Bar Logo Test page · 3 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Geometric Tech Logo Test page · 4 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Lunar New Year Lanterns Test page · 3 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Colourful Mandala Test page · 4 finished
SVG
DeepSeek V4 ProRaw API (one-shot)raw API baseline
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Giant Mech Test page · 2 finished
SVG
DeepSeek V4.1 FlashRaw API (one-shot)raw API baseline
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
DualSense controller, quick Test page · 2 finished
SVGClaude Opus 5.5Raw API (one-shot)raw API baseline
SVGGPT-6 SolRaw API (one-shot)raw API baseline
PS5 Pro console scene Test page · 2 finished
SVGClaude Opus 5.5Raw API (one-shot)raw API baseline
SVGGPT-6 SolRaw API (one-shot)raw API baseline
Mechanical Keyboard Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Medieval Castle Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Mermaid on a Rock Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Monster Truck Jump Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Domed Mosque Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Mountain Lake at Dawn Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Music Player UI Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Northern Lights Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Old Fisherman Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Painter at an Easel Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Emperor Penguin Huddle Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Phoenix Rising Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Pizza Slice Cheese Pull Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Potted Succulents Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Fitness Activity Rings Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Bowl of Ramen Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Double-Decker Bus Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Retro Desktop Computer Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Rice Terraces Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Robot Vacuum Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Colourful Row Houses Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Sailboat Regatta Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Server Rack Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Vintage Sewing Machine Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Skateboarder Ollie Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Exploded Smartphone Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Smartwatch Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Running Shoe Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Rocket Launch Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Starfighter in a Hangar Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Stack of Pancakes Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Steam Locomotive Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Steampunk Airship Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Deep-Sea Submarine Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Sushi Platter Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Suspension Bridge in Fog Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Multi-Tool Pocket Knife Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Trio of Tacos Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Prairie Thunderstorm Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Settings Toggles Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Open Toolbox Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Toucan on a Branch Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Cable Car on a Hill Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Treehouse Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Tropical Beach Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Open Umbrella in Rain Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Kelp Forest Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Vintage Biplane Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Vintage Scooter Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Vintage Typewriter Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Erupting Volcano Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
VR Headset Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Jungle Waterfall Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Weather Widget Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Wizard Casting a Spell Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Memphis Pattern Test page · 1 finished
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
gpt-oss-120bRaw API (one-shot)raw API baseline
Cat Seeing a Lion Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Ornate Monogram Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Phases of the Moon Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
New Year Fireworks Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Op Art Waves Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Orchestra Seating Chart Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Organisation Chart Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Impossible Triangle Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Periodic Table Excerpt Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Budget Pie Chart Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Plant Cell Diagram Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Reflection in a Puddle Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Recycling Process Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Rock Band on Stage Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Rock Climber Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Saxophone Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Sheet Music Excerpt Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Downhill Skier Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Overhead Kick Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Solar System Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Sports Team Crest Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Cherry Blossom Picnic Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Abstract Stained Glass Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Stay Wild Circular Badge Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Metro Map Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Summer Beach Day Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Sunburst Rays Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Surfer in a Barrel Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Butterfly Stroke Swimmer Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Modular Synthesizer Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Tennis Serve Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Thank You Script Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Harvest Dinner Table Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Stacked Animals Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
History of Flight Timeline Test page · 1 finished
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
- Did not finish
gpt-oss-120bRaw API (one-shot)raw API baseline
Pirate Treasure Map Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Valentine Letter Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Three-Circle Venn Diagram Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Vintage Travel Poster Type Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Record Turntable Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Violin and Bow Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Volcano Cross-Section Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Voronoi Pattern Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Water Cycle Diagram Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Snowy Holiday Cabin Test page · 1 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Cloud Lettering Test page · 2 finished
SVG
gpt-oss-120bRaw API (one-shot)raw API baseline
SVG
Qwen3.8 27BRaw API (one-shot)raw API baseline
Cargo ship containers (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Hummingbird flower (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Ladybug leaf (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Panda bamboo (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Red fox snow (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Steam locomotive (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Astronaut floating (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Boxing ring (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Chat interface (agent version) Test page · 1 finished
SVG
LongCat 2.5 PreviewOpenCodeskills off
Detective noir (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Dragon sleeping castle (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Film camera (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Food pyramid (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Grand piano (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Halloween drippy boo (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Hand five fruits (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Hello neon sign (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Human heart anatomy (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Human skeleton front (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Japanese pagoda (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Latte art (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Logo coffee roaster (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Logo sushi bar (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Mountain lake dawn (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Retro crt computer (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Rice terraces (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Sewing machine (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Sushi platter (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Suspension bridge fog (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Swiss army knife (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Treasure map (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Vinyl turntable (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Voronoi cells (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Water cycle diagram (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Weather widget (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Soccer bicycle kick (agent version) Test page · 1 finished
SVGLongCat 2.5 PreviewOpenCodeskills off
Robot Tending a Flower Test page · 0 finished
- Did not finish
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Unicorn in a Meadow Test page · 0 finished
- Did not finish
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
Hiking Trail Map Test page · 0 finished
- Did not finish
gpt-oss-120bRaw API (one-shot)raw API baseline
- Did not finish
Qwen3.8 27BRaw API (one-shot)raw API baseline
City park top down (agent version) Test page · 0 finished
- Stopped by us
LongCat 2.5 PreviewOpenCodeskills off
Cyberpunk alley (agent version) Test page · 0 finished
- Stopped by us
LongCat 2.5 PreviewOpenCodeskills off
Islamic star tiling (agent version) Test page · 0 finished
- Stopped by us
LongCat 2.5 PreviewOpenCodeskills off
Jack o lanterns (agent version) Test page · 0 finished
- Stopped by us
LongCat 2.5 PreviewOpenCodeskills off