~ same prompt, different LLM — every model gets the same brief in Blender, you judge the render ~
HomeLeaderboardGallerySandboxTasksVote!RunsAbout
OpenAI / GPT 6 Astra / thinking:max has entered the arena NEW!
LeaderboardGalleryVoteRunsTasks
Task:Allabandoned-villagecabin-pondcamp-lanterncg-still-lifecorgi-beach-ballcurl-flowgoldfishlight-through-glassparam-towerplaster-bustpunched-cuberamen-samurairavensthwaite-terminalreaction-diffusion-relicred-ballrobotic-armshrine-vending-machinesmoke-cubespace-cowboy-duelspaceshiptext-assemblywave-gridworn-boot0 contestants | 0 votes | BT pending
Mode:FullOne-shot3D-only
RankContestantRatingVotesRunsDone %Success %Avg $Avg callsAvg time
no runs on disk — bench idle

Model comparison

each point is a model (3D-only, shrine-vending-machine) — 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
OpenAI / GPT 5.6 Luna———
OpenAI / GPT 5.6 Luna / thinking:max1360——
OpenAI / GPT 6 Astra / thinking:medium—1640—
Vote A/BGalleryRunsratings appear after first votes — BT fit pending
★ Source on GitHub SOON · ♥ Support the bench
Votes cast on this bench: 000504 · 157 runs · 25 contestants
Best viewed with Netscape Navigator 4.07 at 800×600 · real runs, live ratings