Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
51.72F1 Score
93
Jun 12, 2026
75.9Accuracy
91
Apr 28, 2026
76.6AUROC
90
Mar 23, 2026
90.2AUROC
90
Mar 23, 2026
83AUROC
90
Mar 23, 2026
0.039Absolute Execution Time Overhead (s)
90
Mar 23, 2026
0.173Absolute Execution Time Overhead (s)
90
Mar 23, 2026
0.064Absolute Execution Time Overhead (s)
90
Mar 23, 2026
62.8PRR
90
Mar 23, 2026
86.1PRR
90
Mar 23, 2026
0.65PRR
90
Mar 23, 2026
92.7Accuracy
90
Jun 30, 2026
76.2ROUGE-L
88
May 29, 2026
71.72Accuracy
86
Apr 30, 2026
52.7Score
86
Jun 9, 2026
48EM
85
Jun 30, 2026
94.7F1
85
May 8, 2026
39.6EM
84
Feb 26, 2026
93.4Accuracy
84
Jul 3, 2026
93.33Exact Match
83
Mar 27, 2026
50F1 Score
80
May 27, 2026
92.1EM
80
May 19, 2026
92.3Accuracy
80
Jun 1, 2026
52.27F1 Score
79
May 8, 2026
54.02Accuracy
78
Feb 26, 2026