Agentic Search on BrowseComp en
67.6Pass@1Seed1.8
Evaluation Results
| Method | Links | |
|---|---|---|
| Seed1.82026.03 | 67.6 | |
| GPT-5 High2026.03 | 54.9 | |
| Gemini 3-pro2026.03 | 37.8 | |
| Claude Sonnet-4.52026.03 | 24.1 | |
| Gemini 2.5-pro2026.03 | 9.9 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Seed1.82026.03 | 67.6 | |
| GPT-5 High2026.03 | 54.9 | |
| Gemini 3-pro2026.03 | 37.8 | |
| Claude Sonnet-4.52026.03 | 24.1 | |
| Gemini 2.5-pro2026.03 | 9.9 |