Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
80.5F1
67
Jun 12, 2026
52.9ARC-C
67
Feb 26, 2026
89.55Accuracy
67
Apr 29, 2026
63.5Accuracy
67
Feb 26, 2026
38Accuracy
66
Jun 11, 2026
37Accuracy
66
Jun 11, 2026
60PRR
66
Apr 29, 2026
58.3PRR
66
Apr 29, 2026
74.9F1
66
Jun 4, 2026
84Accuracy
65
Jun 5, 2026
92.42BS (%)
65
Jun 1, 2026
70.4Accuracy
65
May 14, 2026
78.8F1 Score (NQ)
64
May 12, 2026
76.31CACC
64
May 27, 2026
99.02ASR
64
May 27, 2026
99.9ASR
64
May 27, 2026
50.83StrEM
63
Jun 30, 2026
94.7F1 Score
63
May 6, 2026
90.2ASR
62
May 25, 2026
0.446F1
62
May 22, 2026
75ACC
62
Feb 26, 2026
26EM
62
Apr 21, 2026
64.1EM
61
May 29, 2026
94.4Overall Accuracy
61
Mar 9, 2026
36.9F1 Score
61
Feb 27, 2026