Embodied3DBench - Grounding (2D): leaderboard
Embodied3DBench (2026) Grounding (2D) task on simulated robotic tabletop scenes: object and part pointing and bounding boxes in the image plane, predicted zero-shot by a vision-language model. Normalized 0-100 score derived from box IoU or point distance; higher is better.
Metric: Grounding (2D) task (object and part pointing and bounding boxes in the image plane), 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 2.5 VL 72B Instruct | 62.8 | #841 | |
| 2 | GPT-5 | 53.7 | #178 | |
| 3 | Qwen 3 VL 4B Instruct | 49.6 | #1332 | |
| 4 | Qwen 2.5 VL 7B Instruct | 48.5 | #1902 | |
| 5 | Claude Sonnet 4 | 36.8 | #410 | |
| 6 | GPT-4o | 28.7 | #751 | |
| 7 | Gemini 2.5 Flash | 21.8 | #463 | |
| 8 | Gemini 2.5 Pro | 20.5 | #276 | |
| 9 | InternVL3.5-8B | 19.9 | #1604 | |
| 10 | InternVL3-38B | 17.8 | #939 | |
| 11 | Doubao-Seed-1.6 | Thinking | 17.6 | |
| 12 | Doubao-1.5-thinking-vision-pro | 16.9 | #344 | |
| 13 | Seed-1.6 | Non-reasoning | 15.8 | #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-grounding-2d · How It Works · Data refreshed daily, snapshot 2026-11-21.