Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
47.72F1 Score
12
Mar 12, 2026
63.63F1 Score
12
Mar 12, 2026
48.3Average Accuracy
12
Mar 11, 2026
65.6Accuracy
12
Mar 10, 2026
59.6Accuracy
12
Mar 10, 2026
100Accuracy
12
Feb 27, 2026
71.4Accuracy
12
Feb 27, 2026
46.2Accuracy
12
Feb 27, 2026
95.4Accuracy
12
Feb 27, 2026
100Accuracy
12
Feb 27, 2026
88Open Accuracy
12
Feb 26, 2026
90.1Accuracy
12
Apr 28, 2026
93Pass@1
12
Feb 26, 2026
0.923F1 Score
12
Feb 26, 2026
28.8Accuracy
12
Feb 26, 2026
7.7Exact Match
12
Feb 26, 2026
63.58F1 Score
12
May 29, 2026
0.824Acc
12
Feb 26, 2026
91.4Accuracy
12
Feb 26, 2026
0.896Accuracy
12
Feb 26, 2026
95.59Acc
12
Feb 26, 2026
83.93Disambiguation TOP-1
12
Feb 26, 2026
60.94EM (LQ)
12
Feb 26, 2026
45.36EM (Long Question)
12
Feb 26, 2026
39Accuracy
12
Feb 26, 2026