Leaderboard ALL KINGDOMS
A text prompt turned directly into 3D.
Ranked by human votes · 1614 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.
Text→3D (native)
7 generators| Rank | Generator | BT score | 95% interval BT 860.9–1125.1 | Trend | Votes | Status |
|---|---|---|---|---|---|---|
| 1 | Meshy v6 text | 1086.4 | [1043.8, 1125.1] | 205 | firm ► | |
| 1 | Tripo H3.1 text | 1064.3 | [1024.3, 1094.6] | 230 | firm ► | |
| 1 | Tripo P1 text | 1038.3 | [1009.5, 1081.6] | 205 | firm ► | |
| 3 | Rodin text via fal | 976.7 | [929.8, 1018.9] | 183 | firm ► | |
| 4 | Rodin text via Replicate | 958.7 | [860.9, 1009.1] | 112 | firm ► | |
| 4 | Hunyuan3D 3.1 text | 951.2 | [905.7, 993.6] | 177 | firm ► | |
| 4 | Hunyuan3D v3 text | 930.4 | [885.9, 976.0] | 222 | 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 0.5 (≈0.50 = unbiased) · tie 0.07 · bad 0.162
VLM judge (Sonnet 4.6, multi-view) — automated LLM-judge rankings by paradigm
Loading automated rankings…