Agentic Search on BrowseComp-zh
81.3Pass@1Seed1.8
Evaluation Results
| Method | Links | |
|---|---|---|
| Seed1.82026.03 | 81.3 | |
| GPT-5 High2026.03 | 63 | |
| Gemini 3-pro2026.03 | 51.6 | |
| Claude Sonnet-4.52026.03 | 42.4 | |
| Gemini 2.5-pro2026.03 | 34.6 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Seed1.82026.03 | 81.3 | |
| GPT-5 High2026.03 | 63 | |
| Gemini 3-pro2026.03 | 51.6 | |
| Claude Sonnet-4.52026.03 | 42.4 | |
| Gemini 2.5-pro2026.03 | 34.6 |