~ 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!
ARCHIVEDRetired from the leaderboard and voting — smoke-test scene — capability sanity check, not part of the benchmark · 2026-07-20. Preserved here for reference only.
Task: red-ball·compare this model on this scene →
Render Window — hero
hero render
camera + framing set up by the AI contestant
3D Viewport — red-ball User Persp
LOADING 3D VIEW
$0.09Cost
51sDuration
7Tool calls
8Turns
Blender 5.1.0MCP 1.22026-07-15
Tokens: 42664/3049Vision: ✓Votes W-L-T: 0-0-0DONE ✓
B-BENCH — TRANSCRIPT OpenAI / GPT 5.6 Terra · r1 · 2026-07-15
RUN LOG — red-ball · OpenAI / GPT 5.6 Terra · r1 · ok
SYSTEM PROMPTthe control — every model on this task got these instructions
PROMPTblender-bench v6HARNESSraw-v1

WITHHELD · The prompt text is unavailable: the publish security scan withheld this run's transcript, which carried it. The prompt versions above still identify exactly which prompt this run was given.

--TASK red-ball
>
F1 RANKSF2 GALLERYF3 RUNSF9 VOTEESC QUIT
FULL CALL INSPECTOR
OPEN RAW JSONL ↗
0 SHOWN
LOADING COMPLETE TRANSCRIPT…
★ Source on GitHub SOON · ♥ Support the bench
Votes cast on this bench: 000482 · 157 runs · 25 contestants
Best viewed with Netscape Navigator 4.07 at 800×600 · real runs, live ratings