AI Model Release Tracker
Community preference (Three.js)

threejseval

Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better.

Scores from threejseval, which runs the benchmark and publishes the full field.

Rankings

Higher is better
#1
Claude Fable 5.1
2037
2
GPT-6 Astra
2009
3
Claude Opus 5
1770
4
Gemini 3.8 Flash
1716
5
Claude Fable 5
1552
6
Kimi K3
1549
7
Gemini 3.7 Flash
1526
8
Grok 4.6
1519
9
Muse Spark 1.3
1503
10
GLM-5.3-FlashOW
1502
11
GPT-5.6 Terra
1497
12
GPT-5.6 Sol
1409
13
Gemini 3.6 Flash
1406
14
GPT-5.6 Luna
1317
15
Claude Sonnet 5
1252
16
Composer 2.5
1120

threejseval — frequently asked questions

Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better.