| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| DeepResearch Bench Open-Ended | AUQ | Overall Score52.09 | 11 | 4mo ago | |
| ScholarQA, HealthBench, ResearchQA, DeepResearchBench 200-question v2 | SearchSwarm | ResearchQA Accuracy80.2 | 9 | 1mo ago | |
| DeepConsult | DualGraph | Win Rate64.42 | 9 | 4mo ago | |
| DeepResearchGym | Gemini-2.5-Pro-DeepResearch | Clarity90.71 | 9 | 4mo ago |