Deep Search on BrowseComp-ZH (test)
58.1Accuracy
OpenAI-o3
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.01 | 58.1 | |
2026.01 | 49.5 | |
2026.01 | 49.2 | |
2026.01 | 46.7 | |
2026.01 | 37.5 | |
2026.01 | 33.3 | |
2026.01 | 32 | |
2026.01 | 29.7 | |
2026.01 | 26.1 | |
2026.01 | 26 | |
2026.01 | 25.5 | |
2026.01 | 24.7 | |
2026.01 | 24.7 | |
2026.01 | 24.1 | |
2026.01 | 24 | |
2026.01 | 20.2 | |
2026.01 | 18.2 | |
2026.01 | 17.5 | |
2026.01 | 17.1 | |
2026.01 | 16.6 | |
2026.01 | 16.6 | |
2026.01 | 16.5 | |
2026.01 | 15.8 | |
2026.01 | 15.6 | |
2026.01 | 15.1 | |
2026.01 | 14.2 | |
2026.01 | 10.1 |