Planning on NuInteract (test)
82.64AccuracyDriveMonkey
Evaluation Results
| Method | Links | |
|---|---|---|
| DriveMonkeyYears=2025, LLM=InternLM2.5-7B2025.12 | 82.64 | |
| GaussianDWMYears=2025, LLM=Qwen3-8B2025.12 | 66.27 | |
| InternVL1.5-2BYears=2024, LLM=InternLM2-7B2025.12 | 53.96 | |
| Qwen2VLYears=2024, LLM=QWen2-7B2025.12 | 49.33 | |
| InternVL2-8BYears=2024, LLM=InternLM2.5-7B2025.12 | 46.93 | |
| QWen2VLYears=2024, LLM=Qwen2-2B2025.12 | 45.59 | |
| InternVL2-2BYears=2024, LLM=InternLM2-2B2025.12 | 44.61 | |
| InternVL2-1BYears=2024, LLM=Qwen2-0.5B2025.12 | 44.08 | |
| InternVL2-4BYears=2024, LLM=Phi3-4B2025.12 | 40.43 | |
| InternVL1.5-4BYears=2024, LLM=Phi3-4B2025.12 | 40.25 | |
| MiniCPM-V 2Years=2024, LLM=MiniCPM-2B2025.12 | 36.69 | |
| MiniCPM-V 2.6Years=2024, LLM=QWen2-7B2025.12 | 36.42 | |
| LLaVA1.5Years=2024, LLM=Vicuna-7B2025.12 | 36.2 |