Tool-use evaluation on MCPToolBench++
81.8Precision
Llama-3.3-70B
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2025.04 | 81.8 | 82.7 | 82.1 | 81 | |
2025.04 | 77.5 | 80 | 78.3 | 75.3 | |
2025.04 | 77.3 | 80.7 | 78.4 | 74 | |
2025.04 | 75 | 76.3 | 75.3 | 74.3 | |
2025.04 | 72.5 | 75.3 | 73.4 | 69.7 | |
2025.04 | 67 | 68.3 | 67.4 | 65.7 | |
2025.04 | 62 | 65.3 | 63.1 | 58.7 |