~ 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
provGoogle / Gemma 4 31b Itcompare →165931100100$0.0071s
provOpenAI / GPT 6 Astra / thinking:mediumcompare →1659110100$0.69290s
provDeepSeek / Deepseek V4 Flashcompare →1468110100$0.00111s
provAnthropic / Sonnet 5 / thinking:lowcompare →1468310100$0.12158s
provOpenAI / GPT 5.6 Lunacompare →1468110100$0.0364s
provGoogle / Gemini 3.5 Flash / thinking:mediumcompare →1277110100$0.22174s

Model comparison

each point is a model (One-shot, plaster-bust) — hover for exact values
AnthropicDeepSeekGoogleOpenAI unrated
12201344146815921716$0.001$0.004$0.026$0.175$1.18Bradley–Terry ratingGoogle / Gemma 4 31b ItOpenAI / GPT 6 Astra / thinking:mediumDeepSeek / Deepseek V4 FlashAnthropic / Sonnet 5 / thinking:lowOpenAI / GPT 5.6 LunaGoogle / Gemini 3.5 Flash / thinking:mediumMean 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
DeepSeek / Deepseek V4 Flash1334
Google / Gemini 3.5 Flash / thinking:medium1143
Google / Gemma 4 31b It1525
OpenAI / GPT 5.6 Luna173913341716
OpenAI / GPT 5.6 Luna / thinking:max1873
OpenAI / GPT 6 Astra / thinking:medium1525
Anthropic / Sonnet 51476
Anthropic / Sonnet 5 / thinking:low1334
Vote A/BGalleryRunsbradley-terry fit over 5 decisive votes
Votes cast on this bench: 000504 · 157 runs · 25 contestants
Best viewed with Netscape Navigator 4.07 at 800×600 · real runs, live ratings