Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
31.92Accuracy
17
Jun 9, 2026
42.75HS
17
Mar 12, 2026
87.9Normalized Accuracy
17
Jun 8, 2026
84.3Few-Shot Accuracy
17
Mar 10, 2026
75.96F1 Score
17
Feb 26, 2026
56.1F1 Score
17
Feb 26, 2026
0.519EM
17
Feb 26, 2026
67.69F1 Score
17
Feb 26, 2026
47.64F1
17
Feb 26, 2026
45.89F1 Score
17
Feb 26, 2026
53.3F1 Score
17
Feb 26, 2026
399Total Points
17
Feb 26, 2026
67.25Accuracy
17
Jun 23, 2026
18.86Correctness Rec@5
17
Feb 26, 2026
97Equal Accuracy
17
Feb 27, 2026
89.1EM
17
Feb 26, 2026
44.29Accuracy
17
Mar 16, 2026
68.4EM (Total)
17
Feb 26, 2026
86.9EM
17
Feb 26, 2026
46.93Normalized Accuracy
17
Feb 26, 2026
10Accuracy
16
Jul 8, 2026
6.73Accuracy
16
Jul 8, 2026
42.04Accuracy
16
Jul 7, 2026
65.71Accuracy
16
Jul 7, 2026
57Accuracy (Clean)
16
Jul 2, 2026