Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
42.12EM
14
May 12, 2026
45.68EM
14
May 12, 2026
98.7Accuracy
14
May 26, 2026
53.8STEM Accuracy
14
May 7, 2026
45.8EM
14
May 1, 2026
88T Score
14
Apr 28, 2026
66T Score
14
Apr 28, 2026
76.8T Score
14
Apr 28, 2026
56.3T Metric
14
Apr 28, 2026
77.5Accuracy
14
Apr 23, 2026
73.2Accuracy
14
Apr 21, 2026
49.17Accuracy
14
Apr 21, 2026
7.2Accuracy Improvement Delta
14
May 18, 2026
55Accuracy
14
Apr 20, 2026
44Accuracy
14
Apr 20, 2026
77Accuracy
14
Apr 20, 2026
73.21Accuracy
14
Apr 15, 2026
31.9Accuracy
14
Apr 7, 2026
30ASR Score
14
Apr 2, 2026
34ASR
14
Apr 2, 2026
0.871AUROC
14
May 20, 2026
45.9EM
14
Mar 24, 2026
38.3Exact Match (EM)
14
Mar 24, 2026
55.4Exact Match (EM)
14
Mar 24, 2026
88.8Accuracy
14
Apr 13, 2026