Deep Research Report Generation on QRC-Eval
75.42RelevanceMind2Report
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Mind2ReportReport Length (Len.)=21.93k, Time=385s2026.01 | 75.42 | 85.24 | 6.12 | 90.53 | 75.82 | 16.17 | 3.37 | 1 | |
| Gemini Deep ResearchReport Length (Len.)=46.91k, Time=498s2026.01 | 64.87 | 78.54 | 11.25 | 81.23 | 63.58 | 13.27 | 3.35 | 2.71 | |
| o3 Deep ResearchReport Length (Len.)=38.34k, Time=516s2026.01 | 63.52 | 79.18 | 10.48 | 79.85 | 64.13 | 14.16 | 3.27 | 2.43 | |
| Grok Deep SearchReport Length (Len.)=13.15k, Time=127s2026.01 | 59.54 | 75.39 | 13.76 | 76.52 | 55.45 | 13.37 | 2.3 | 4.86 | |
| Perplexity Deep ResearchReport Length (Len.)=18.43k, Time=229s2026.01 | 58.17 | 71.53 | 15.22 | 78.41 | 52.86 | 6.57 | 2.11 | 7 | |
| Tongyi-DeepResearchReport Length (Len.)=9.84k, Time=624s2026.01 | 55.46 | 70.25 | 17.58 | 72.43 | 49.87 | 8.9 | 3.18 | 6.14 | |
| o4-mini Deep ResearchReport Length (Len.)=12.62k, Time=364s2026.01 | 54.23 | 72.09 | 16.54 | 70.47 | 48.21 | 8.07 | 2.73 | 6.43 | |
| MiroThinkerReport Length (Len.)=6.58k, Time=315s2026.01 | 52.84 | 68.52 | 18.23 | 69.48 | 45.19 | 7.89 | 2.14 | 8.57 | |
| WebThinkerReport Length (Len.)=5.34k, Time=263s2026.01 | 49.53 | 66.18 | 19.47 | 66.85 | 42.54 | 10.59 | 2.44 | 8.43 | |
| OpenManusReport Length (Len.)=5.86k, Time=146s2026.01 | 48.25 | 65.14 | 21.82 | 65.23 | 39.38 | 9.79 | 2.6 | 8.86 | |
| MiroFlowReport Length (Len.)=3.58k, Time=262s2026.01 | 46.52 | 62.84 | 23.47 | 63.45 | 36.53 | 7.7 | 2.51 | 10.29 | |
| OWLReport Length (Len.)=9.58k, Time=287s2026.01 | 44.56 | 60.52 | 24.58 | 61.54 | 33.25 | 6.86 | 2.54 | 11.14 |