~ 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
1OpenAI / GPT 5.6 Luna / thinking:maxcompare →171791100100$0.0215299s
2Google / Gemini 3.5 Flash / thinking:mediumcompare →168871100100$2.0831562s
3Z.AI / GLM 5.2compare →162571100100$0.1829703s
4OpenAI / GPT 5.6 Lunacompare →153581100100$0.055103s
5Google / Gemini 3.1 Flash Litecompare →142651100100$0.021291s
6Anthropic / Haiku 4.5 / thinking:xhighcompare →142251100100$0.2034352s
provDeepSeek / Deepseek V4 Flashcompare →141831100100$0.0329521s
provDeepSeek / Deepseek V4 Procompare →138641100100$0.1540790s
provGoogle / Gemma 4 31b Itcompare →128241100100$0.049148s

Model comparison

each point is a model (Full, abandoned-village) — hover for exact values
AnthropicDeepSeekGoogleOpenAIZ.AI unrated
12171358150016411782$0.010$0.043$0.179$0.742$3.07Bradley–Terry ratingMean cost per task (USD, log scale)

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:medium1231
DeepSeek / Deepseek V4 Flash14711313
DeepSeek / Deepseek V4 Flash 0731 / thinking:max1344
DeepSeek / Deepseek V4 Pro1447
Google / Gemini 3.1 Flash Lite1493
Google / Gemini 3.5 Flash / thinking:medium17481153
Google / Gemini 3.6 Flash / thinking:medium1437
Google / Gemma 4 31b It13441535
Z.AI / GLM 5.21686
OpenAI / GPT 5.6 Luna15971323
OpenAI / GPT 5.6 Luna / thinking:max1779
OpenAI / GPT 5.6 Sol / thinking:max1645
OpenAI / GPT 6 Astra / thinking:medium1613
Anthropic / Haiku 4.5 / thinking:xhigh1487
Anthropic / Opus 5 / thinking:medium1738
Anthropic / Sonnet 5 / thinking:low1614
Vote A/BGalleryRunsbradley-terry fit over 26 decisive votes
Votes cast on this bench: 000482 · 157 runs · 25 contestants
Best viewed with Netscape Navigator 4.07 at 800×600 · real runs, live ratings