Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
51Average Score
177
Jun 30, 2026
77.2EM
173
Jun 16, 2026
89.3Accuracy
172
Jun 24, 2026
82.4Accuracy
170
Apr 21, 2026
86.6Accuracy
164
May 29, 2026
91.2F1
163
Apr 6, 2026
89.8F1
162
May 12, 2026
87.12Accuracy
158
Jul 8, 2026
84.4Accuracy
157
Jul 9, 2026
91.2F1
156
Jul 8, 2026
90.5Accuracy
153
May 12, 2026
83.6Accuracy
145
Feb 26, 2026
66.4EM Accuracy
143
Jun 30, 2026
74.1Accuracy
138
Apr 21, 2026
64.2Exact Match
133
May 22, 2026
84.98F1
132
May 8, 2026
61.5F1 Score (Match)
132
May 19, 2026
88.2ASR
130
May 25, 2026
92.4OBQA Accuracy
130
Feb 26, 2026
80Accuracy
125
Jul 3, 2026
38.12F1 Score
124
Jun 2, 2026
91.2Accuracy
124
Feb 26, 2026
70Accuracy
123
Mar 5, 2026
94.4Accuracy
123
Apr 23, 2026
77.2Accuracy
122
Jun 30, 2026