Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
49.86EM (%)
27
May 8, 2026
56.17Accuracy
27
Apr 30, 2026
75.99Accuracy
27
Apr 30, 2026
36.8EM
27
May 22, 2026
32EM
27
Apr 14, 2026
0.079ECE
27
Apr 8, 2026
90.8Accuracy
27
Jun 4, 2026
46.1EM
27
May 7, 2026
10.2F1
27
Feb 26, 2026
44.44Solve Rate
27
Feb 26, 2026
80.6F1 Score
27
Mar 25, 2026
85.2Hits@1
27
Jul 2, 2026
0.383fEM
27
Feb 26, 2026
47.6fEM
27
Feb 26, 2026
87.4Accuracy
27
May 12, 2026
75.7P@1
27
Feb 26, 2026
99.2Info Accuracy
27
Feb 26, 2026
86.3Accuracy (ACC)
27
Feb 26, 2026
86.7Accuracy
27
Feb 26, 2026
81.7Accuracy
27
Feb 26, 2026
43Acc_norm
26
Jun 8, 2026
1,853Correlation
26
May 20, 2026
52.76Gen-F1
26
Jun 11, 2026
83NQ Score
26
Apr 23, 2026
88.04Accuracy
26
Jun 30, 2026