Deep Research on MuSiQue (MUS) (test)
81Mean Correct Answer RateOur best agent
Evaluation Results
| Method | Links | |
|---|---|---|
| Our best agentType=Live web2025.10 | 81 | |
| WebSailorType=Live web2025.10 | 69 | |
| Our base agentType=Live web2025.10 | 67 | |
| ASearcherType=Live web2025.10 | 64.9 | |
| DeepResearcherType=Live web2025.10 | 62.78 | |
| Search-R1Type=Static & simulated web2025.10 | 61 | |
| R1-SearcherType=Static & simulated web2025.10 | 51.5 | |
| ZeroSearchType=Static & simulated web2025.10 | 11.4 |