Preference-driven Tool Calling on MPT Context-Guided Average
67.18OA-F1
PREFINE
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.04 | 67.18 | |
2026.04 | 65.76 | |
2026.04 | 65.35 | |
2026.04 | 63.98 | |
2026.04 | 63.9 | |
2026.04 | 63.58 | |
2026.04 | 61.83 | |
2026.04 | 61.74 | |
2026.04 | 61.42 | |
2026.04 | 60.24 | |
2026.04 | 59.4 | |
2026.04 | 58.9 | |
2026.04 | 56.21 | |
2026.04 | 54.27 | |
2026.04 | 53.27 | |
2026.04 | 47.87 | |
2026.04 | 46.95 | |
2026.04 | 32.63 | |
2026.04 | 25.73 |