BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References
Paper · https://arxiv.org/abs/2610.23986
Recent advances in multimodal large language models (MLLMs) have enabled them to act as autonomous agents, creating and editing 3D models via code or direct software manipulation. In practical workflows, these models must infer object shapes, materials, spatial layouts, and lighting from diverse references while strictly following instructions to reconstruct, modify, or design 3D content. However, existing benchmarks provide limited coverage of such open-ended requests across real-world scenarios. To bridge this gap, we introduce BlenderWorld, the first comprehensive benchmark dedicated to evaluating frontier models on realistic 3D creation tasks. BlenderWorld comprises 223 tasks spanning architecture, products, natural environments, and scientific visualization, driven by text, image, video, and structured specification inputs. To rigorously assess these complex deliverables, we establish a unified evaluation protocol: we render the submitted Blender projects from multiple viewpoints and evaluate them against 2,651 task-specific binary rubrics alongside holistic visual quality scores. Benchmarking thirteen frontier models reveals that GPT-6-Astra achieves the highest overall fused score of 79.9, followed by Opus-5 (73.0) and GPT-5.6-Sol (67.7). Ultimately, our findings reveal a critical bottleneck: while current models can parse broad instructions, they still profoundly struggle with fine-grained 3D spatial coherence and accurate structural reproduction in Blender, leaving substantial headroom for future 3D-native agentics.
First seen by Oriel on .
AI summary
BlenderWorld is a benchmark for evaluating frontier models on realistic 3D creation tasks using multimodal references and rendered Blender project assessments.
- The benchmark contains 223 tasks covering architecture, products, natural environments, and scientific visualization.
- Tasks use text, image, video, and structured specification inputs to drive 3D reconstruction, modification, and design.
- Submitted Blender projects are rendered from multiple viewpoints and assessed with 2,651 binary rubrics plus holistic visual quality scores.
- Among thirteen evaluated models, GPT-6-Astra scored highest at 79.9, followed by Opus-5 at 73.0 and GPT-5.6-Sol at 67.7.
- Results show that models struggle with fine-grained 3D spatial coherence and accurate structural reproduction in Blender.
#3d creation #blender #multimodal agents #benchmarks
Generated by gpt-5.6-sol. Check the original for details.
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained
Points
Score reported by the source.
- Hugging Face Papers: 22, latest observation ; +1 over observed period since
Comments
Comment count reported by the source.
- Hugging Face Papers: 2, latest observation ; +1 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hugging Face Papers | 2610.23986 | https://arxiv.org/abs/2610.23986 Read discussion |