Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
82.5Accuracy
77
Jun 23, 2026
76Exact Match
77
Jun 2, 2026
93.3Accuracy
76
Apr 14, 2026
97.2Accuracy
74
May 19, 2026
96.7Task Accuracy
74
May 15, 2026
91F1
74
Feb 26, 2026
88.7Accuracy
74
Jun 2, 2026
86.64Accuracy
73
Feb 26, 2026
98.32Accuracy
72
Mar 5, 2026
61.65EM
72
Jun 12, 2026
87.2F1
72
Feb 26, 2026
62EM
71
May 11, 2026
22.92EM
71
Jun 1, 2026
0.112ACE (General)
70
Apr 10, 2026
0.496ACE Score
70
Apr 10, 2026
99.65ASR
70
Mar 4, 2026
78.3EM
70
Apr 10, 2026
96.22F1 Score
70
Feb 26, 2026
96.82Accuracy
69
Jun 26, 2026
67EM
69
Jun 11, 2026
79EM
69
Apr 21, 2026
48EM Accuracy (%)
68
May 11, 2026
87.2Accuracy
68
May 15, 2026
91.752Accuracy
68
Jul 8, 2026
86Accuracy (ARC-C)
67
Jul 3, 2026