Deep Research Report Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
52.84Comprehensiveness
89
Jun 9, 2026
50.7Overall Score
24
Jun 16, 2026
7.21P-Score
22
Feb 26, 2026
0.626Quality
22
Feb 26, 2026
75.42Relevance
12
Feb 26, 2026
4.15Informativeness
9
May 14, 2026
80.55KPR
9
Feb 26, 2026
66.3Numeric Grounding
3
Apr 1, 2026