Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
79.9C
40
Feb 26, 2026
72Accuracy
40
Jun 30, 2026
73.6F1
40
Jun 12, 2026
82.55Accuracy (%)
39
Jun 26, 2026
93.4Accuracy
39
Apr 24, 2026
95.9Accuracy
39
Apr 24, 2026
67.4Accuracy
39
Jul 8, 2026
57.2EM
39
Feb 26, 2026
86.88Accuracy
38
Jun 11, 2026
79.4Accuracy
38
May 25, 2026
24.67EM
38
Apr 28, 2026
15EM
38
Apr 28, 2026
64.5Default Score
38
Apr 14, 2026
44.3Default Accuracy
38
Apr 14, 2026
56.19F1 Score
38
Feb 26, 2026
73Accuracy
38
Jun 5, 2026
0.839Accuracy
38
Feb 26, 2026
58.4TruthfulQA
37
Apr 21, 2026
87.88Accuracy
37
Apr 23, 2026
79.2EM
37
Mar 12, 2026
60.48EM
37
Mar 12, 2026
67.5Ans EM
37
Mar 10, 2026
60EM
36
Jul 2, 2026
38Exact Match (EM)
36
Jul 2, 2026
76Exact Match (EM)
36
Jul 2, 2026