Leaderboard FUNGI

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

10 generators
Rank Generator BT score 95% interval BT -267.2–2003.5 Trend Votes Status
1 Pixal3D papercode 1291.9
[604.5, 1883.2]
4 26 more votes → firm
1 Hunyuan3D v3 papercode 1285.0
[297.2, 2003.5]
4 26 more votes → firm
1 SAM 3D papercode 1268.0
[794.3, 1888.6]
8 22 more votes → firm
1 Rodin/Hyper3D papercode 1099.7
[-87.2, 1788.9]
3 27 more votes → firm
1 TRELLIS 2 papercode 1078.3
[216.9, 1965.0]
4 26 more votes → firm
1 Meshy 6 papercode 1057.0
[293.4, 1413.9]
6 24 more votes → firm
1 Hunyuan3D 3.1 papercode 967.3
[33.9, 1414.1]
2 28 more votes → firm
1 TRELLIS via Replicate papercode 655.8
[1.3, 1202.1]
4 26 more votes → firm
1 Hunyuan3D v2 papercode 649.6
[-150.0, 1168.6]
3 27 more votes → firm
1 TripoSR papercode 549.4
[-267.2, 1418.2]
2 28 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…