~ same prompt, different LLM — every model gets the same brief in Blender, you judge the render ~
OpenAI / GPT 6 Astra / thinking:max has entered the arena NEW!
LeaderboardGalleryVoteRunsTasks
RankContestantRatingVotesRunsDone %Success %Avg $Avg callsAvg time
no runs on disk — bench idle

Model comparison

each point is a model (3D-only, abandoned-village) — hover for exact values
unrated
14001450150015501600$0.001$0.006$0.032$0.178$1.00Bradley–Terry ratingMean cost per task (USD, log scale)
No rated models yet — cast decisive votes to plot the field.

By dimension

lens rounds and chip verdicts feed these — none cast yet
Lighting
no data yet
Composition
no data yet
Modeling
no data yet
Materials
no data yet
Render
no data yet
Adherence
no data yet

Modes compared

each contestant's ratings across run modes (mixed ladder)
ContestantFullOne-shot3D-only
Anthropic / Claude Fable 5.1 / thinking:medium1196
DeepSeek / Deepseek V4 Flash14731315
DeepSeek / Deepseek V4 Flash 0731 / thinking:max1346
DeepSeek / Deepseek V4 Pro1449
Google / Gemini 3.1 Flash Lite1495
Google / Gemini 3.5 Flash / thinking:medium17501155
Google / Gemini 3.6 Flash / thinking:medium1438
Google / Gemma 4 31b It13461537
Z.AI / GLM 5.21688
OpenAI / GPT 5.6 Luna15991325
OpenAI / GPT 5.6 Luna / thinking:max1781
OpenAI / GPT 5.6 Sol / thinking:max1647
OpenAI / GPT 6 Astra / thinking:medium1613
Anthropic / Haiku 4.5 / thinking:xhigh1489
Anthropic / Opus 5 / thinking:medium1740
Anthropic / Sonnet 5 / thinking:low1616
Vote A/BGalleryRunsratings appear after first votes — BT fit pending
Votes cast on this bench: 000504 · 157 runs · 25 contestants
Best viewed with Netscape Navigator 4.07 at 800×600 · real runs, live ratings