Qwen3.8 Max
Alibaba Qwen (via Fireworks). Run in Raw API call.
71 runs on 62 prompts · 83% finished
Results
The best run of each of its 62 tests first, then every other run. Filter them in the explorer
59 finished runs
Live demo
Live demo
Live demo
Live demo
Live scene
Live sceneRetro arcade claw machine with pastel plush prizes (Three.js)
qwen3p8-max
Raw API (one-shot)
raw API baseline
Live sceneFour-stroke engine cutaway: crank, piston and cam-driven valves (Three.js)
qwen3p8-max
Raw API (one-shot)
raw API baseline
Live sceneHot air balloon festival over rolling fields (Three.js)
qwen3p8-max
Raw API (one-shot)
raw API baseline
Live scene
Live sceneOuter-space pinball table with planet bumpers (Three.js)
qwen3p8-max
Raw API (one-shot)
raw API baseline
Live sceneFloating pirate island diorama with a cliff cross-section (Three.js)
qwen3p8-max
Raw API (one-shot)
raw API baseline
Numbers: finish rate, cost, wall time, draft scores
- Runs
- 71
- on 62 prompts
- Finished
- 83%
- 59 of 71
- Median cost, finished run
- not recorded
- n=0
- Median wall time, finished run
- 3m 56s
- n=59
- Recorded spend
- $0
- $0 on unfinished runs; 71 without a recorded cost
From the numbers
Set against the other models with at least 3 runs (top or bottom third), and its draft-score ranks within single prompts. Nothing here is averaged across prompts.
Strengths
- Nothing stands out with enough runs to say so.
Weaknesses
- 12 runs ended as the model's own failure (DNF, class MODEL)
Best and hardest run
Best run
Picked as its fastest finished run (no scored result yet).
-
Qwen3.8 Max, raw API call, Fruit Sales Bar Chart
Raw API call, default effort
raw API baseline
41 s
not recorded: the run's token counts were never reported, so there is no estimate
OK
Unscored: no rubric for this prompt
Hardest run
Picked as its slowest finished run.
-
qwen3p8-max, raw API call, Retro arcade claw machine with pastel plush prizes (Three.js)
Raw API call
raw API baseline
10m 09s
not recorded: the run's token counts were never reported, so there is no estimate
OK
Unscored: no rubric for this prompt
Draft scores by prompt
No scored result yet (only prompts with a published rubric are scored).
By harness
| Raw API call | 71 | 59 | 83% | not recorded: no finished run with a recorded cost | 3m 56s n=59 |
|---|
All 62 tests and experiment collections
- 003 Orbital Coffee Landing (2 runs)
- 004 Brick Breaker Neon (1 run)
- 005 Focus Timer Orbit (1 run)
- 002 Pendulum Wave (2 runs)
- Artwork style pass (1 run)
- Retro arcade claw machine with pastel plush prizes (Three.js) (1 run)
- Four-stroke engine cutaway: crank, piston and cam-driven valves (Three.js) (1 run)
- Hot air balloon festival over rolling fields (Three.js) (1 run)
- Mechanical bee (1 run)
- Outer-space pinball table with planet bumpers (Three.js) (1 run)
- Floating pirate island diorama with a cliff cross-section (Three.js) (1 run)
- Desk Lamp and Books (1 run)
- Desert Dunes at Night (1 run)
- Sales Dashboard Card (1 run)
- Cyberpunk Alley (1 run)
- Corgi Catching a Frisbee (1 run)
- Chalkboard Coffee Lettering (1 run)
- Top-Down City Park (1 run)
- Circuit Board Close-Up (1 run)
- Chessboard Mid-Game (1 run)
- Chat Conversation UI (1 run)
- Chameleon on a Branch (1 run)
- Container Ship (1 run)
- Canyon River (1 run)
- Campus Map (1 run)
- Calendar Month View (1 run)
- Butterfly Life Cycle (1 run)
- Exploded Burger (1 run)
- Bubble Tea (1 run)
- Breakfast Skillet (1 run)
- Boxing Ring (1 run)
- Labelled Bicycle Diagram (1 run)
- Bauhaus Composition (1 run)
- Battery Level Icons (1 run)
- Basketball Slam Dunk (1 run)
- Baseball Stadium (1 run)
- Barn Owl in Flight (1 run)
- Fruit Sales Bar Chart (1 run)
- Ballet Dancer (1 run)
- Autumn Forest Path (1 run)
- Bohr Model of an Atom (1 run)
- Stargazer with Telescope (1 run)
- Floating Astronaut (1 run)
- Art Deco Skyscraper (1 run)
- Flat App Icon Set (1 run)
- Ant Colony Cutaway (1 run)
- Illustrated Alphabet A B C (1 run)
- Alien Planet (1 run)
- Twin-Bell Alarm Clock (1 run)
- Acoustic Guitar (1 run)
- Panda Eating Bamboo (2 runs)
- Swimming Sea Turtle (2 runs)
- Giraffe Side Profile (2 runs)
- Octopus Juggling Teacups (2 runs)
- Elephant Calf Mud Bath (2 runs)
- Sleeping Curled Cat (2 runs)
- Red Fox in Snow (2 runs)
- 001 Ink Bloom Garden (1 run)
- Night Train (1 run)
- Cycling Peloton (1 run)
- Chef Flipping a Pan (1 run)
- Koi Pond Garden (1 run)
Experiment collections: HTML Files (16) · SVG (55) · Three.js (8)