Leaderboard ALL KINGDOMS

Each generation method is ranked on its own board — scores aren't comparable across methods (they come from separate match pools). Pick a method to compare the models within it. 1614 votes cast.

Share Post on X

Image→3D reconstruction

One or more photos reconstructed into a 3D mesh.

no votes yet — evaluation in progress

unrated

View board →

LLM procedural (code-gen)

An LLM writes code (e.g. Blender) that builds the 3D model.

no votes yet — evaluation in progress

unrated

View board →

Text→3D (native)

A text prompt turned directly into 3D.

no votes yet — evaluation in progress

unrated

View board →

Agentic 3D

An agent renders, critiques, and revises its own 3D model in a loop.

no votes yet — evaluation in progress

unrated

View board →
Filters & bias audit
Scope Bradley–Terry over votes from signed-in (Hugging Face) users only.

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…