Leaderboard FUNGI
An agent renders, critiques, and revises its own 3D model in a loop.
Human voting is currently focused on the commercial image→3D and text→3D models, so these scores are paused where the votes so far left them. The AI-judge board still ranks this modality.
Ranked by human votes · 340 cast · see the AI-judge board →
How ranking works
Rank groups models whose 95% bootstrap CIs overlap into the same rank (they are not statistically separable). BT = Bradley–Terry score (Elo-scaled); the bar shows the 95% CI with the point estimate marked. Every board ranks a SINGLE method — scores from different methods come from disconnected match pools and aren't comparable, so there is no cross-method ranking. Elo updates live per vote. Recompute in Admin.
Agentic 3D
13 generators| Rank | Generator | BT score | 95% interval BT 121.5–1977.6 | Trend | Votes | Status |
|---|---|---|---|---|---|---|
| 1 | minimax/minimax-m3 (agentic) | 1718.2 | [1102.7, 1977.6] | 1 | 29 more votes → firm ► | |
| 1 | openai/gpt-5.6-sol-pro (agentic) | 1400.7 | [1099.9, 1700.2] | 2 | 28 more votes → firm ► | |
| 1 | x-ai/grok-4.5 (agentic) | 1301.7 | [1052.5, 1502.7] | 3 | 27 more votes → firm ► | |
| 1 | anthropic/claude-sonnet-5 (agentic) | 1301.6 | [808.8, 1519.3] | 4 | 26 more votes → firm ► | |
| 1 | openai/gpt-5.6-sol (agentic) | 1003.5 | [417.9, 1362.5] | 4 | 26 more votes → firm ► | |
| 1 | anthropic/claude-opus-4.8 (agentic) | 984.2 | [619.6, 1296.2] | 5 | 25 more votes → firm ► | |
| 1 | x-ai/grok-4.20 (agentic) | 984.2 | [603.7, 1211.5] | 1 | 29 more votes → firm ► | |
| 1 | google/gemini-3.1-pro-preview (agentic) | 885.2 | [626.9, 1184.3] | 1 | 29 more votes → firm ► | |
| 1 | qwen/qwen3.7-plus (agentic) | 885.2 | [639.5, 1290.0] | 2 | 28 more votes → firm ► | |
| 1 | openai/gpt-5.1 (agentic) | 885.1 | [538.8, 1158.1] | 2 | 28 more votes → firm ► | |
| 1 | z-ai/glm-4.6v (agentic) | 686.1 | [174.9, 1172.6] | 2 | 28 more votes → firm ► | |
| 1 | meta-llama/llama-4-maverick (agentic) | 577.1 | [121.5, 1164.8] | 2 | 28 more votes → firm ► | |
| 1 | moonshotai/kimi-k2.7-code (agentic) | 468.6 | [197.1, 1179.3] | 1 | 29 more votes → firm ► |
95% credible interval · point estimate · trend · firm a rank backed by 30+ votes; below that, Status counts the votes still needed · click a row for detail
Filters & bias audit
Bias audit — left(A) win rate 0.569 (≈0.50 = unbiased) · tie 0.059 · bad 0.191
VLM judge (Sonnet 4.6, multi-view) — automated LLM-judge rankings by paradigm
Loading automated rankings…