Agent Task Completion on tau2-bench telecom
67Pass Rate
SkillsInjector
Updated 5d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.05 | 67 | |
2026.05 | 62.8 | |
2026.05 | 60.4 | |
2026.05 | 55.8 | |
2026.05 | 54.7 | |
2026.05 | 51.2 | |
2026.05 | 41.9 | |
2026.05 | 40 | |
2026.05 | 24.6 |
SkillsInjector
| Method | Links | |
|---|---|---|
2026.05 | 67 | |
2026.05 | 62.8 | |
2026.05 | 60.4 | |
2026.05 | 55.8 | |
2026.05 | 54.7 | |
2026.05 | 51.2 | |
2026.05 | 41.9 | |
2026.05 | 40 | |
2026.05 | 24.6 |