Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
61.8Accuracy
19
Feb 27, 2026
73.7Accuracy
19
Feb 27, 2026
72.2Accuracy
19
Feb 27, 2026
84.8Accuracy
19
Feb 27, 2026
57.3F1 Score
19
May 27, 2026
72.6EM
19
Feb 26, 2026
50EM
19
Feb 26, 2026
57.72EM
19
Feb 26, 2026
73.3Accuracy
19
Feb 26, 2026
93.66Accuracy
19
Feb 26, 2026
38.5EM
19
Feb 26, 2026
61.3F1
19
Feb 26, 2026
83.59ARC-e Accuracy
18
Jul 7, 2026
98.26BBQ Accuracy
18
Jul 1, 2026
57.89Factuality
18
Jun 23, 2026
46.9Exact Match
18
Jun 4, 2026
81.2F1 Score
18
Jun 2, 2026
77.4F1 Score
18
Jun 2, 2026
71Accuracy (BBH Disambiguation QA)
18
Jun 2, 2026
18.5ΔLL (%)
18
May 29, 2026
68.2Accuracy
18
May 26, 2026
45.53Token F1
18
May 26, 2026
75.6Accuracy
18
May 22, 2026
76.4Accuracy
18
May 22, 2026
66.2Accuracy
18
May 22, 2026