Agentic on τ2-Bench
91.6Score
Claude Opus 4.5
Updated 18d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 91.6 | |
2026.02 | 90.7 | |
2026.02 | 89.7 | |
2026.02 | 87.4 | |
2026.02 | 85.5 | |
2026.02 | 85.3 | |
2026.02 | 80.2 | |
2026.06 | 78.36 | |
2026.06 | 78.12 | |
2026.07 | 78 | |
2026.06 | 76.36 | |
2026.06 | 75.63 | |
2026.06 | 71.21 | |
2026.06 | 69.53 | |
2026.06 | 68.92 | |
2026.07 | 57.2 | |
2026.06 | 46.92 | |
2026.07 | 45.4 | |
2026.07 | 41.7 | |
2026.06 | 23.48 |