Visual Question Answering on NuscenesQA
61.3AccuracyHERMES++
Evaluation Results
| Method | Links | |
|---|---|---|
| HERMES++Modality=Camera2026.04 | 61.3 | |
| HERMES++Modality=Camera2026.04 | 61.3 | |
| CenterPoint+MCANModality=LiDAR2026.04 | 59.5 | |
| CenterPoint+MCANModality=LiDAR2026.04 | 59.5 | |
| Omni-QModality=Camera2026.04 | 59.2 | |
| Omni-QModality=Camera2026.04 | 59.2 | |
| ACE-Brain-0-8BModel Type=Embodied Brain MLLM2026.03 | 58.8 | |
| OpenDriveVLA-7BModality=Camera2026.04 | 58.2 | |
| OpenDriveVLA-7BModality=Camera2026.04 | 58.2 | |
| CenterPoint+BUTDModality=LiDAR2026.04 | 58.1 | |
| CenterPoint+BUTDModality=LiDAR2026.04 | 58.1 | |
| BEVDet+MCANModality=Camera2026.04 | 57.9 | |
| BEVDet+MCANModality=Camera2026.04 | 57.9 | |
| BEVDet+BUTDModality=Camera2026.04 | 57 | |
| BEVDet+BUTDModality=Camera2026.04 | 57 | |
| MiMo-Embodied-7BModel Type=Embodied Brain MLLM2026.03 | 56.7 | |
| LiDAR-LLMModality=LiDAR2026.04 | 48.6 | |
| LiDAR-LLMModality=LiDAR2026.04 | 48.6 | |
| LLaVAModality=Camera2026.04 | 47.4 | |
| LLaVAModality=Camera2026.04 | 47.4 | |
| GPT-4oModel Type=Closed-source MLLM2026.03 | 34.3 | |
| MiMo-VL-7BModel Type=Open-source general-purpose MLLM2026.03 | 33.9 | |
| RoboBrain2.5-8BModel Type=Embodied Brain MLLM2026.03 | 33.2 | |
| Vlaser-8BModel Type=Embodied Brain MLLM2026.03 | 33.1 | |
| RoboBrain2.0-7BModel Type=Embodied Brain MLLM2026.03 | 32.3 | |
| VeBrain-7BModel Type=Embodied Brain MLLM2026.03 | 29.3 | |
| InternVL3-8BModel Type=Open-source general-purpose MLLM2026.03 | 26.6 | |
| Qwen2.5-VL-7B-Inst.Model Type=Open-source general-purpose MLLM2026.03 | 25.8 | |
| Qwen3-VL-8B-Inst.Model Type=Open-source general-purpose MLLM2026.03 | 22.8 | |
| InternVL3.5-8BModel Type=Open-source general-purpose MLLM2026.03 | 17.2 | |
| Gemini2.5-proModel Type=Closed-source MLLM2026.03 | 16.1 | |
| Pelican-VL-7BModel Type=Embodied Brain MLLM2026.03 | 14.8 | |
| Qwen-VL-MaxModel Type=Closed-source MLLM2026.03 | 6.7 |