Visual Question Answering on CA-VQA
81.2Binary AccGround3D-LMM
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Ground3D-LMMInput Mode=3D+2D2026.07 | 81.2 | 82.8 | 41.2 | 11.5 | 85.7 | 37.8 | 14.2 | 30 | 48.1 | |
| MM1.5-3B2026.07 | 59.1 | 9.1 | 32.6 | 0 | 38.6 | 0.6 | 2.2 | 3.4 | 18.2 | |
| SpatialRGPT-8B2026.07 | 53.6 | 68.8 | 5.5 | 0 | 37.2 | 10.5 | 8.7 | 7 | 23.9 | |
| GPT-4o2026.07 | 44.2 | 69 | 0 | 0 | 36.6 | 11.7 | 10 | 11 | 22.8 |