Web Search Research on WideSearch
76.2ScoreClaude Opus 4.5
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude Opus 4.52026.05 | 76.2 | |
| Quest-35B2026.05 | 60.6 | |
| Gemini 3 Pro2026.05 | 57 | |
| Quest-30B2026.05 | 54.2 | |
| GPT-52026.05 | 54 | |
| Tongyi-DREvaluation Implementation=Authors' implementation2026.05 | 37.3 | |
| OpenResearcherEvaluation Implementation=Authors' implementation2026.05 | 19.2 |