Leaderboard PLANTS

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

11 generators
Rank Generator BT score 95% interval BT 24.9–1809.8 Trend Votes Status
1 Pixal3D papercode 1427.0
[1141.9, 1809.8]
8 22 more votes → firm
1 TRELLIS 2 papercode 1369.6
[1086.1, 1653.2]
1 29 more votes → firm
1 Meshy 6 papercode 1369.6
[1032.7, 1748.2]
11 19 more votes → firm
1 TRELLIS via fal papercode 1060.2
[817.1, 1301.6]
2 28 more votes → firm
TRELLIS via Replicate papercode 1060.2
[746.8, 1376.0]
4 26 more votes → firm
1 Hunyuan3D 3.1 papercode 1060.2
[693.8, 1437.0]
9 21 more votes → firm
1 InstantMesh papercode 953.0
[548.5, 1246.0]
2 28 more votes → firm
1 Hunyuan3D v2 papercode 863.2
[328.6, 1147.3]
5 25 more votes → firm
2 SAM 3D papercode 860.0
[424.0, 1105.6]
9 21 more votes → firm
1 TripoSR papercode 769.7
[24.9, 1383.2]
2 28 more votes → firm
2 Hunyuan3D v3 papercode 769.7
[254.6, 1096.4]
10 20 more votes → firm
1 Rodin/Hyper3D papercode 643.6
[260.6, 1170.5]
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…