Agent Task Completion on τ-bench airline
19Success Rate
Qwen3-30B
Updated 1mo ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.06 | 19 | - | - | - | - | - | |
2026.06 | 19 | - | - | - | - | - | |
2026.06 | 17.3 | - | - | - | - | - | |
2026.06 | 17 | - | - | - | - | - | |
2026.06 | 16 | - | - | - | - | - | |
2026.06 | 16 | - | - | - | - | - | |
2026.06 | 14.3 | - | - | - | - | - | |
2026.06 | 8 | - | - | - | - | - | |
2026.04 | - | 18.4 | 12 | 9.4 | 8.4 | 8 | |
2026.04 | - | 36.8 | 23.79 | 18.2 | 16.6 | 16 | |
2026.04 | - | 21.2 | 15.2 | 13.3 | 12.4 | 12 |