Web Agent Task Success on τ-bench
76.52Retail Success Rate
Asym-AC-SFT
Updated 17d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.03 | 76.52 | - | - | 54.4 | 65.46 | |
2026.03 | 73.56 | - | - | 52.8 | 63.18 | |
2026.03 | 71.3 | - | - | 50.4 | 60.85 | |
2026.03 | 70.61 | - | - | 52 | 61.31 | |
2026.03 | 67.1 | - | - | 45.2 | 56.2 | |
2026.03 | 58.3 | - | - | 47.2 | 52.75 | |
2025.10 | - | 22.61 | - | - | - | |
| - | 39.13 | 100 | - | - | ||
| - | 41.16 | 100 | - | - | ||
| - | 37.68 | 100 | - | - |