Leaderboard ALL KINGDOMS

One or more photos reconstructed into a 3D mesh.

Ranked by human votes · 1614 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.

Show all 53 · 31 unrated

Image→3D reconstruction

11 generators
Rank Generator BT score 95% interval BT 524.9–1216.5 Trend Votes Status
1 Meshy 6 papercode 1145.7
[1092.3, 1216.5]
117 firm
1 TRELLIS 2 papercode 1067.1
[995.3, 1136.6]
51 firm
2 Hunyuan3D v3 papercode 1044.0
[1001.3, 1088.8]
112 firm
2 Rodin/Hyper3D papercode 1014.7
[932.9, 1074.2]
78 firm
2 Pixal3D papercode 1011.1
[951.7, 1077.7]
114 firm
2 Hunyuan3D 3.1 papercode 986.8
[890.8, 1041.5]
101 firm
2 Hunyuan3D v2 papercode 982.9
[916.1, 1045.4]
81 firm
4 SAM 3D papercode 941.1
[872.0, 991.3]
126 firm
4 TRELLIS via Replicate papercode 907.6
[830.2, 958.0]
67 firm
TRELLIS via fal papercode 878.4
[732.2, 973.1]
48 firm
4 TripoSR papercode 834.0
[582.2, 955.8]
28 2 more votes → firm
2 InstantMesh papercode 729.1
[524.9, 1013.6]
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 0.5 (≈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…