Embodied3DBench - Manipulation Trajectory (3D): leaderboard
Metric: Manipulation Trajectory (3D) task (end-effector key trajectory points in metric 3D), normalized score (0-100): IoU of predicted boxes or the L2 error of predicted points (pixels in 2D, metres in 3D) mapped to 0-100, on the simulated robotic tabletop scenes of Embodied3DBench (21K QA pairs over 4.8K object instances), zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 VL 4B Instruct | 44.5 |
| 2 | Gemini 2.5 Pro | 43.4 |
| 3 | GPT-5 | 38 |
| 4 | Gemini 2.5 Flash | 36.9 |
| 5 | Doubao-Seed-1.6 (Thinking) | 33.8 |
| 6 | Claude Sonnet 4 | 32 |
| 7 | InternVL3-38B | 13.2 |
| 8 | GPT-4o | 11.8 |
| 9 | Qwen 2.5 VL 7B Instruct | 5 |
| 10 | Qwen 2.5 VL 72B Instruct | 3.8 |
Interactive version: theaggregate.ai/benchmark?slug=embodied3dbench-manipulation-trajectory-3d · How It Works · Data refreshed daily, snapshot 2026-10-07.