Leaderboard PLANTS
An agent renders, critiques, and revises its own 3D model in a loop.
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.
No ratings yet for this slice. Cast some votes in the Arena.
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…