Agentic Task Completion on τ2-bench Airline
97Success Rate
SagaLLM
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 97 | - | 76 | 80,000 | |
2026.05 | 97 | 81 | 50 | 77,000 | |
2026.05 | 82 | - | 52 | 48,000 | |
2026.05 | 82 | - | 69 | 62,000 | |
2026.06 | 46 | - | - | - | |
2026.06 | 42 | - | - | - | |
2026.06 | 42 | - | - | - | |
2026.06 | 40 | - | - | - | |
2026.06 | 40 | - | - | - | |
2026.06 | 30 | - | - | - | |
2026.06 | 29.9 | - | - | - | |
2026.06 | 26 | - | - | - | |
2026.06 | 24.5 | - | - | - | |
2026.06 | 24 | - | - | - | |
2026.06 | 24 | - | - | - | |
2026.06 | 20 | - | - | - | |
2026.06 | 18 | - | - | - | |
2026.06 | 17.3 | - | - | - | |
2026.06 | 14.3 | - | - | - | |
2026.06 | 14 | - | - | - | |
2026.06 | 10 | - | - | - | |
2026.06 | 8 | - | - | - |