Deep Research on BAM (test)
92.8Mean Correct RateOur best agent
Evaluation results
| Method | Links | |
|---|---|---|
| Our best agentType=Live web2025.10 | 92.8 | |
| WebSailorType=Live web2025.10 | 86.8 | |
| Our base agentType=Live web2025.10 | 84.3 | |
| DeepResearcherType=Live web2025.10 | 78.31 | |
| Search-R1Type=Static & simulated web2025.10 | 75.3 | |
| ASearcherType=Live web2025.10 | 74.4 | |
| R1-SearcherType=Static & simulated web2025.10 | 62.4 | |
| ZeroSearchType=Static & simulated web2025.10 | 53.9 |