Tool Use on RoTBench Multi-turn
72.9Tool Selection Accuracy
PA-Tool
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.10 | 72.9 | 64.3 | |
2025.10 | 71.4 | 61.4 | |
2025.10 | 71.4 | 61.4 | |
2025.10 | 70 | 61.4 | |
2025.10 | 65.7 | 58.6 | |
2025.10 | 65.7 | 61.4 | |
2025.10 | 64.3 | 58.6 | |
2025.10 | 64.3 | 58.6 | |
2025.10 | 64.3 | 48.6 | |
2025.10 | 60 | 54.3 | |
2025.10 | 60 | 47.1 | |
2025.10 | 60 | 54.3 | |
2025.10 | 57.1 | 52.9 | |
2025.10 | 51.4 | 38.6 | |
2025.10 | 51.4 | 41.4 | |
2025.10 | 51.4 | 44.3 | |
2025.10 | 48.6 | 35.7 | |
2025.10 | 47.1 | 42.9 | |
2025.10 | 45.7 | 34.3 | |
2025.10 | 45.7 | 38.6 | |
2025.10 | 44.3 | 32.9 | |
2025.10 | 42.8 | 34.3 | |
2025.10 | 38.6 | 38.6 | |
2025.10 | 34.3 | 28.6 | |
2025.10 | 32.9 | 27.1 | |
2025.10 | 32.9 | 25.7 | |
2025.10 | 32.9 | 27.1 | |
2025.10 | 27.1 | 22.9 | |
2025.10 | 24.3 | 20 | |
2025.10 | 21.4 | 21.4 | |
2025.10 | 18.6 | 15.7 | |
2025.10 | 15.7 | 14.3 | |
2025.10 | 12.9 | 8.6 | |
2025.10 | 11.4 | 7.1 | |
2025.10 | 10 | 10 |