Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
81.3F1 Score
54
May 29, 2026
88.8MC1 Accuracy
54
Mar 16, 2026
0.032Mean Error
54
Feb 26, 2026
82.7Accuracy
53
Feb 26, 2026
81.1Performance Score
52
Apr 10, 2026
0.141Test Error Probability
52
Feb 26, 2026
57.2F1 Score
52
Feb 26, 2026
87.6Exact Match (EM)
52
Mar 17, 2026
70.58EM
52
Feb 27, 2026
74.48AUC
51
Apr 20, 2026
64.07AUC
51
Apr 20, 2026
83.48AUC
51
Apr 20, 2026
90.79AUC
51
Apr 20, 2026
75.95AUC
51
Apr 20, 2026
87.79AUC
51
Apr 20, 2026
84F1 Score
50
Jun 2, 2026
72F1 Score (%)
50
Jun 2, 2026
64.47F1 Score
50
Jun 2, 2026
43Exact Match
50
Jun 1, 2026
90.38Accuracy
50
Jun 29, 2026
93.7Accuracy
50
Apr 28, 2026
92.94Correctness EM Recall
50
Apr 10, 2026
51.3Overall Average Score
49
Feb 26, 2026
75.7Pass@1
49
Feb 26, 2026
37.8EM
48
Jun 11, 2026