SceneActBench - Articulated: leaderboard
Articulated task of SceneActBench (2026): 100 S2O articulated objects: rig a closed, unlabelled mesh to reproduce 32 ordered frames of its motion, scored by mean part error against a 1 m reference. The agent acts through a shared Blender tool interface; task score from 0 to 100, higher is better.
Metric: Task score (0-100): 100 S2O articulated objects: rig a closed, unlabelled mesh to reproduce 32 ordered frames of its motion, scored by mean part error against a 1 m reference; every configuration drives one headless Blender through the same MCP tool interface (scene and object inspection, Python execution, rendering) with task step budgets; each native geometric error or F-score is mapped to a 0 to 100 case score against a fixed reference, invalid outputs score 0, cases are averaged per task. Source: arxiv.org. Saturation forecast: Around February 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 (High) | 73.8 | #123 (GPT-5.4) |
| 2 | Claude Opus 4.6 (High) | 63.7 | #102 (Claude Opus 4.6) |
| 3 | GPT-5.4 (Medium) | 62.3 | #123 (GPT-5.4) |
| 4 | Seed 2.0 Pro (High) | 59.6 | #211 (Seed 2.0 Pro) |
| 5 | MiniMax-M3 (High) | 58.4 | #269 (MiniMax-M3) |
| 6 | Claude Sonnet 5 (High) | 57.8 | #111 (Claude Sonnet 5) |
| 7 | Kimi K2.6 (Thinking) | 57.3 | #178 (Kimi K2.6) |
| 8 | Gemini 3.1 Pro (Preview) (High) | 56.5 | #94 (Gemini 3.1 Pro (Preview)) |
| 9 | Step 3.7 Flash (High) | 48.3 | #465 (Step 3.7 Flash) |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=sceneactbench-articulated · How It Works · Data refreshed daily, snapshot 2026-11-13.