Textual long-horizon complex reasoning on BrowseComp
85.9Score
Gemini-3.1-Pro-Preview
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 85.9 | |
2026.06 | 78.6 | |
2026.06 | 77.3 | |
2026.06 | 76.1 | |
2026.06 | 75.9 | |
2026.06 | 74.9 | |
2026.06 | 74.7 | |
2026.06 | 74 | |
2026.06 | 67.9 | |
2026.06 | 65.8 | |
2026.06 | 51.4 | |
2026.06 | 43.4 | |
2026.06 | 42.1 | |
2026.06 | 36.7 | |
2026.06 | 29.5 | |
2026.06 | 26.3 | |
2026.06 | 11.5 | |
2026.06 | 3.2 |