~ 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
provOpenAI / GPT 6 Astra / thinking:mediumcompare →1623310100$0.57260s
provOpenAI / GPT 5.6 Lunacompare →153441100100$0.0367s
provGoogle / Gemini 3.5 Flash / thinking:mediumcompare →1343110100$0.16145s

Model comparison

each point is a model (One-shot, corgi-beach-ball) — hover for exact values
GoogleOpenAI unrated
13011392148315741665$0.021$0.050$0.123$0.300$0.730Bradley–Terry ratingOpenAI / GPT 6 Astra / thinking:mediumOpenAI / 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 Flash1535
DeepSeek / Deepseek V4 Pro1483
Google / Gemini 3.1 Flash Lite1356
Google / Gemini 3.5 Flash / thinking:medium15241240
Google / Gemma 4 31b It1378
Z.AI / GLM 5.21448
OpenAI / GPT 5.6 Luna17121430
OpenAI / GPT 5.6 Luna / thinking:max1687
OpenAI / GPT 5.6 Sol1769
OpenAI / GPT 6 Astra / thinking:medium1519
Anthropic / Haiku 4.5 / thinking:xhigh1420
Vote A/BGalleryRunsbradley-terry fit over 4 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