General Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
67.5Exact Match Accuracy
15
Jun 9, 2026
50.1Exact Match (EM)
15
Feb 26, 2026
61.2Average F1
14
Jun 30, 2026
27.7OSR Score
13
Apr 21, 2026
12.2OSR (%)
13
Apr 21, 2026
25.2OSR (%)
13
Apr 21, 2026
71.4Pass@1
12
Mar 5, 2026
66.1F1
11
Feb 26, 2026
47.87EM
10
Apr 21, 2026
66.3EM
10
Apr 21, 2026
46.08EM
10
Apr 21, 2026
81.26Accuracy
8
Jun 9, 2026
0.239Reward
8
Mar 24, 2026
76.1Accuracy
4
Apr 14, 2026
52.1Exact Match (EM)
4
Feb 26, 2026
79.55Mean Accuracy
4
Feb 26, 2026
595Optimization Token Usage
3
Feb 26, 2026
0.17Reward
2
Mar 24, 2026