Insight Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
4.15Set-level Score (Gemini-2.5-Flash)
10
Apr 23, 2026
4.77Set-level Score (Gemini-2.5-Flash Judge)
10
Apr 23, 2026
4.76Set-level Score (Gemini-2.5-Flash Judge)
10
Apr 23, 2026
4.65Set-level Score (Gemini-2.5-Flash Judge)
10
Apr 23, 2026
69.3Recall
4
Apr 9, 2026