Tool-use Reasoning on BFCL V4
18Average Performance
Llama-3.1-8B-Instruct + RODS (ours)
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| 18 | 15.5 | 20.5 | ||
| 16.53 | 15 | 18.06 | ||
2026.06 | 15.75 | 8.9 | 22.6 | |
2026.06 | 9.17 | 5 | 13.33 | |
2026.06 | 7.41 | 4.5 | 10.32 | |
2026.06 | 7.05 | 2.5 | 11.6 |