Deep Research on GAIA (F1, EM)
25.07F1 ScoreMemPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MemPOTT=0.62, PT=0.122026.02 | 25.07 | 17.48 | |
| DeepResearcherTT=4.94, PT=0.332026.02 | 22.44 | 16.5 | |
| ReSearchTT=0.41, PT=0.172026.02 | 16 | 8.74 | |
| qwen2.5 (ReAct)TT=1.54, PT=0.222026.02 | 14.28 | 8.74 |