~ 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!
ARCHIVEDRetired from the leaderboard and voting — aborted mid-run (v2 wave, no metrics) · 2026-07-20. Preserved here for reference only.
Render Window — hero
NO CAPTURE
3D Viewport — robotic-arm User Persp
3D Viewport — Z.AI / GLM 5.2
no GLB — pre-capture run
Cost
Duration
Tool calls
Turns
Blender MCP 2026-07-15
Tokens: /Vision: Votes W-L-T: 0-0-0NO DONE
B-BENCH — TRANSCRIPT Z.AI / GLM 5.2 · r1 · 2026-07-15
RUN LOG — robotic-arm · Z.AI / GLM 5.2 · r1 · aborted
SYSTEM PROMPTthe control — every model on this task got these instructions
SHOW FULL PROMPT · 2016 chars
You are participating in Blender-Bench, a public benchmark where AI models complete the same Blender task.

Your result will be compared head-to-head with another model. Anyone on the internet can vote, based only on the published visual outputs they can inspect: the interactive 3D scene and rendered presentation.

Complete the request as well as you can. The benchmark does not prescribe a workflow or visual style; use whichever Blender techniques you consider appropriate. Make the important requirements evident in the published result, save a complete scene, and present the work clearly in every requested output.

The final published capture is rendered by the benchmark from your saved scene using Cycles at 1536 x 1536, 64 samples, denoising enabled, and GPU acceleration when available with a CPU fallback. The saved scene is also exported to GLB with geometry, materials, the contestant camera, and supported lights for interactive inspection. Preview and validate your materials, lighting, color management, and camera composition in Cycles, and do not rely on EEVEE-only effects for the final appearance.

## Harness Instructions

You are operating Blender through the provided tools. The scene starts empty. Build what the user's prompt asks for in the current scene. Work step by step and verify your own work. Before you finish, set up a camera and lighting to frame a single, well-composed presentation image of your result — position and aim the camera, and add or adjust lights so the subject reads clearly. The final benchmark capture overrides the scene render settings and renders in Cycles at 1536x1536, 64 samples, with denoising and GPU acceleration (CPU fallback). Preview and validate materials, lighting, color management, and composition in Cycles; do not rely on EEVEE-only effects. The saved scene is also exported to GLB with geometry, materials, your camera, and supported lights for interactive inspection. When you are finished, reply with the single word DONE and no tool calls.
--TASK robotic-arm: ## Task Complete the following Blender task: <task> A desk-mounted robotic arm with at least four articulated joints, posed mid-reach toward a small object on the desk — but not an industrial catalog part. This arm is generatively designed: its metal frame has the parametric, "AI-optimized" look of topology-optimized engineering — organic load-bearing branches, smooth bone-like transitions, lat…
>
FULL CALL INSPECTOR
OPEN RAW JSONL ↗
0 SHOWN
LOADING COMPLETE TRANSCRIPT…
Votes cast on this bench: 000482 · 157 runs · 25 contestants
Best viewed with Netscape Navigator 4.07 at 800×600 · real runs, live ratings