BlenderWorld
Visual agents turn a text, image or video brief into an editable Blender scene with rendered media. Hidden binary rubrics and eight visual quality dimensions score each project.
223 tasks in nine creative domains with 2,651 rubric criteria. Score is half rubric and half dimension quality, out of 100. GPT-6 Astra led 13 models at 79.9.
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
GPT-6 Astra leads with 79.9 among models released by Sep 2026
Best score per model from the benchmark's own leaderboard, read on 2 Nov 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in Sep 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- Claude Sonnet 5.5
- and 11 more
- 1 GPT-6 Astra 79.9
- 2 Claude Opus 5 73.0
- 3 GPT-5.6 Sol 67.7
- 4
DeepSeek V4.1 Flash 65.7 - 5
Qwen 3.8 Max 60.6 - 6 GLM-5.3-Flash 59.7
- 7 Claude Opus 4.8 57.0
- 8 Grok 4.6 57.0
- 9
Seed2.1 Pro 51.3 - 10 Qwen 3.8 27B 47.7
- 11 Kimi K3 46.5
- 12
Gemini 3.8 Flash 34.2 - 13
MiniMax-M3 31.8
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 79.9 | Sep 2026 | Official leaderboard | |
| 2 | Claude Opus 5 | 73.0 | Jul 2026 | Official leaderboard | |
| 3 | GPT-5.6 Sol | 67.7 | Jul 2026 | Official leaderboard | |
| 4 | DeepSeek V4.1 Flash | 65.7 | Sep 2026 | Official leaderboard | |
| 5 | Qwen 3.8 Max | 60.6 | Aug 2026 | Official leaderboard | |
| 6 | GLM-5.3-Flash | 59.7 | Aug 2026 | Official leaderboard | |
| 7 | Claude Opus 4.8 | 57.0 | May 2026 | Official leaderboard | |
| 8 | Grok 4.6 | 57.0 | Aug 2026 | Official leaderboard | |
| 9 | Seed2.1 Pro | 51.3 | Jun 2026 | Official leaderboard | |
| 10 | Qwen 3.8 27B | 47.7 | Aug 2026 | Official leaderboard | |
| 11 | Kimi K3 | 46.5 | Jul 2026 | Official leaderboard | |
| 12 | Gemini 3.8 Flash | 34.2 | Sep 2026 | Official leaderboard | |
| 13 | MiniMax-M3 | 31.8 | Jun 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No lab model card reports it yet
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.
More in Engineering and CAD
- BenchCAD In use Programmatic CAD: 17,900 execution-verified CadQuery programs over 106 industrial part families. Four matched tasks scored on geometry. GPT-6 Astra 95.9%
- EEBench In use 13 electrical-engineering circuit and PCB design tasks graded by deterministic build checks, simulation and BOM constraints. No LLM judge. Claude Opus 5.5 75%
- Parametric CAD Bench In use Agents author editable parametric FreeCAD part designs, graded against held-back references for geometry and spec consistency. Claude Opus 5.5 61%
- CADGenBench Only in system cards Agents construct CAD models from design prompts. The generation split is graded for executability and geometric correctness. Claude Fable 5 45.1%
- 3DCodeBench Only in system cards Agentic procedural 3D modeling via code: author engine-ready 3D assets through software APIs. Graded for executability and shape fidelity. Grok 4.6 54%
- PartBench Only in system cards Parametric mechanical part design and CAD-style generation, graded for geometric and manufacturing fidelity. Grok 4.6 58.5%