~ same prompt, different LLM — every model gets the same brief in Blender, you judge the render ~
Google / Gemini 3.8 Flash / thinking:medium has entered the arena NEW!
LeaderboardGalleryVoteRunsTasks
RankContestantRatingVotesRunsDone %Success %Avg $Avg callsAvg time
1OpenAI / GPT 5.6 Solcompare →1807181100100$0.4510196s
2OpenAI / GPT 5.6 Lunacompare →1744422100100$0.045106s
3OpenAI / GPT 5.6 Luna / thinking:maxcompare →1690211100100$0.2816350s
4Google / Gemini 3.5 Flash / thinking:mediumcompare →1553121100100$2.0252709s
5DeepSeek / Deepseek V4 Flashcompare →1478131100100$0.20741175s
6DeepSeek / Deepseek V4 Procompare →1451151100100$0.20581488s
7Z.AI / GLM 5.2compare →13671510100$1.00911836s
8Google / Gemma 4 31b Itcompare →1340151100100$0.036377s
9Anthropic / Haiku 4.5 / thinking:xhighcompare →1319161100100$0.77971114s
10Google / Gemini 3.1 Flash Litecompare →1250151100100$0.011086s

Model comparison

each point is a model (Full, corgi-beach-ball) — hover for exact values
AnthropicDeepSeekGoogleOpenAIZ.AI unrated
11661347152917101891$0.008$0.035$0.154$0.685$3.05Bradley–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
DeepSeek / Deepseek V4 Flash1502——
DeepSeek / Deepseek V4 Pro1486——
Google / Gemini 3.1 Flash Lite1273——
Google / Gemini 3.5 Flash / thinking:medium15791191—
Google / Gemma 4 31b It1356——
Z.AI / GLM 5.21394——
OpenAI / GPT 5.6 Luna17711382—
OpenAI / GPT 5.6 Luna / thinking:max1716——
OpenAI / GPT 5.6 Sol1834——
OpenAI / GPT 6 Astra / thinking:medium—1668—
Anthropic / Haiku 4.5 / thinking:xhigh1348——
Vote A/BGalleryRunsbradley-terry fit over 91 decisive votes
Votes cast on this bench: 001671 · 163 runs · 26 contestants
Best viewed with Netscape Navigator 4.07 at 800×600 · real runs, live ratings