Embodied3DBench - 2D Average: leaderboard
Embodied3DBench (2026) low-level embodied spatial intelligence in the image plane: a vision-language model grounds parts and objects, matches points across views, and predicts affordances, manipulation trajectories and grasp points on simulated robotic tabletop scenes. Mean of five normalized 0-100 task scores derived from box IoU and point distance; higher is better.
Metric: Mean of the five 2D task scores, each a 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: Not forecast. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Qwen 3 VL 4B Instruct | 56.5 | #1332 | |
| 2 | Qwen 2.5 VL 72B Instruct | 55.5 | #841 | |
| 3 | GPT-5 | 54.4 | #178 | |
| 4 | Qwen 2.5 VL 7B Instruct | 43 | #1902 | |
| 5 | Claude Sonnet 4 | 41.2 | #410 | |
| 6 | GPT-4o | 36.6 | #751 | |
| 7 | Gemini 2.5 Flash | 31.8 | #463 | |
| 8 | Gemini 2.5 Pro | 31.4 | #276 | |
| 9 | InternVL3.5-8B | 28.9 | #1604 | |
| 10 | InternVL3-38B | 27.4 | #939 | |
| 11 | Doubao-1.5-thinking-vision-pro | 27.4 | #344 | |
| 12 | Doubao-Seed-1.6 | Thinking | 27.2 | |
| 13 | Seed-1.6 | Non-reasoning | 25.8 | #469 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=embodied3dbench-2d-average · How It Works · Data refreshed daily, snapshot 2026-11-21.