Multimodal Tool Use on LLaVA-Bench Tool Use
89.3GroundingLLaVA-Plus
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| LLaVA-Plustool_configuration=All Tools2023.11 | 89.3 | 94.4 | 96.7 | 48.8 | 82.3 | |
| LLaVA-Plustool_configuration=Fly2023.11 | 88.6 | 88.9 | 90.2 | 38.4 | 76.5 | |
| All Tools + GPT4planner_configuration=GPT-4, tool_configuration=All Tools2023.11 | 77.5 | 95.6 | 95.2 | 39.3 | 76.9 | |
| Bing Chatevaluation_date=07302023.11 | 56 | 84 | 96 | 44.8 | 70.2 | |
| LLaVA2023.11 | 47.1 | 87.1 | 77 | 23.6 | 58.7 | |
| LLaVAtool_configuration=Tools in Test2023.11 | 41.7 | 48.5 | 72 | 31.9 | 48.5 | |
| Bardevaluation_date=07302023.11 | 36.5 | 105.3 | 103.3 | 60 | 76.3 | |
| MM-REACT2023.11 | 30.2 | 94.7 | 103.8 | 77.3 | 76.5 |