Web-retrieval Task Completion on FutureX
49.5Pass@1
Multi agent
Updated 1d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 49.5 | |
2026.06 | 47.5 | |
2026.06 | 47.3 | |
2026.06 | 44.1 | |
2026.06 | 31.8 | |
2026.06 | 31.2 | |
2026.06 | 31 | |
2026.06 | 31 | |
2026.06 | 30.8 | |
2026.06 | 29.8 | |
2026.06 | 29.4 | |
2026.06 | 28.2 | |
2026.06 | 27.8 | |
2026.06 | 25.6 |