Agentic Task on τ2-Bench Telecom (avg@2, pass@2)
45Avg@2 Score
PPO-EWMA
Updated 21d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 45 | 57.5 | |
2026.05 | 45 | 57.5 | |
2026.05 | 44.75 | 55 | |
2026.05 | 44 | 55 | |
2026.05 | 42.5 | 52.5 | |
2026.05 | 42.5 | 52.5 | |
2026.05 | 40 | 50 | |
2026.05 | 37.5 | 50 |
PPO-EWMA
| Method | Links | ||
|---|---|---|---|
2026.05 | 45 | 57.5 | |
2026.05 | 45 | 57.5 | |
2026.05 | 44.75 | 55 | |
2026.05 | 44 | 55 | |
2026.05 | 42.5 | 52.5 | |
2026.05 | 42.5 | 52.5 | |
2026.05 | 40 | 50 | |
2026.05 | 37.5 | 50 |