Leaderboard PLANTS
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 663.8–1181.7 | Trend | Votes | Status |
|---|---|---|---|---|---|---|
| 1 | Meshy v6 text | 1122.2 | [1057.6, 1181.7] | 85 | firm ► | |
| 1 | Tripo H3.1 text | 1090.8 | [1026.3, 1157.2] | 85 | firm ► | |
| 1 | Tripo P1 text | 1074.2 | [1008.2, 1142.8] | 76 | firm ► | |
| 3 | Hunyuan3D 3.1 text | 950.1 | [868.3, 1010.1] | 81 | firm ► | |
| 4 | Rodin text via fal | 915.6 | [811.9, 986.8] | 73 | firm ► | |
| 4 | Hunyuan3D v3 text | 899.1 | [815.7, 960.4] | 83 | firm ► | |
| 5 | Rodin text via Replicate | 783.5 | [663.8, 852.5] | 49 | 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…