Embodied3DBench - Affordance (2D): leaderboard
Metric: Affordance (2D) task (functional contact point and interaction vector projected to the image), 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.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 66.1 |
| 2 | Qwen 2.5 VL 72B Instruct | 66.1 |
| 3 | Qwen 2.5 VL 7B Instruct | 55 |
| 4 | Claude Sonnet 4 | 54.6 |
| 5 | GPT-4o | 53 |
| 6 | Qwen 3 VL 4B Instruct | 51.9 |
| 7 | Gemini 2.5 Pro | 50.6 |
| 8 | Gemini 2.5 Flash | 50.3 |
| 9 | Doubao-Seed-1.6 (Thinking) | 44 |
| 10 | InternVL3-38B | 41.2 |
Interactive version: theaggregate.ai/benchmark?slug=embodied3dbench-affordance-2d · How It Works · Data refreshed daily, snapshot 2026-10-07.