Leaderboard ANIMALS

One or more photos reconstructed into a 3D mesh.

Ranked by human votes · 340 cast · see the AI-judge board →

Share Post on X
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.

Image→3D reconstruction

9 generators
Rank Generator BT score 95% interval BT 165.1–1973.4 Trend Votes Status
1 SAM 3D papercode 1269.2
[824.9, 1973.4]
7 23 more votes → firm
1 Hunyuan3D 3.1 papercode 1206.9
[392.6, 1655.8]
6 24 more votes → firm
1 Pixal3D papercode 1157.0
[766.0, 1644.5]
6 24 more votes → firm
1 Meshy 6 papercode 1150.7
[809.9, 1811.3]
8 22 more votes → firm
1 Rodin/Hyper3D papercode 1141.9
[547.5, 1644.3]
6 24 more votes → firm
1 TRELLIS 2 papercode 1141.2
[287.5, 1932.8]
3 27 more votes → firm
1 Hunyuan3D v3 papercode 1095.1
[663.3, 1664.9]
7 23 more votes → firm
1 TRELLIS via Replicate papercode 982.3
[347.6, 1174.9]
9 21 more votes → firm
TRELLIS via fal papercode 631.3
[165.1, 1132.0]
3 27 more votes → firm
1 Hunyuan3D v2 papercode 867.5
[294.9, 1294.8]
5 25 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…