Agent Task Completion on tau2-bench airline
60Pass Rate
SkillsInjector
Updated 5d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.05 | 60 | |
2026.05 | 56.1 | |
2026.05 | 54 | |
2026.05 | 49.6 | |
2026.05 | 45.2 | |
2026.05 | 43.6 | |
2026.05 | 42.4 | |
2026.05 | 37.6 | |
2026.05 | 24.4 |
SkillsInjector
| Method | Links | |
|---|---|---|
2026.05 | 60 | |
2026.05 | 56.1 | |
2026.05 | 54 | |
2026.05 | 49.6 | |
2026.05 | 45.2 | |
2026.05 | 43.6 | |
2026.05 | 42.4 | |
2026.05 | 37.6 | |
2026.05 | 24.4 |