Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
49.7Exact Match
5
Feb 26, 2026
74.64Accuracy
5
Feb 26, 2026
89.16Accuracy
5
Feb 26, 2026
89.6Accuracy
5
Feb 26, 2026
70.2Accuracy
5
Feb 26, 2026
24.07Strict Accuracy
5
Feb 26, 2026
69.8EM
5
Feb 26, 2026
0.911EM
5
Feb 26, 2026
30.2EM
5
Feb 26, 2026
79.08Lenient Accuracy
5
Feb 26, 2026
88.28Lenient Accuracy
5
Feb 26, 2026
0.883Lenient Accuracy
5
Feb 26, 2026
55.2EM
5
Feb 26, 2026
66.3RA
5
Feb 26, 2026
79.6RA
5
Feb 26, 2026
0.873RA
5
Feb 26, 2026
78.5F1 Score
5
Feb 26, 2026
96.75Accuracy
5
Feb 27, 2026
36.2Aggregate Precision
5
Feb 26, 2026
0.752Accuracy
5
Feb 26, 2026
89.5Accuracy
5
Feb 26, 2026
75.5EM
5
Feb 26, 2026
66.37Exact Match
5
Feb 26, 2026
40Accuracy
5
Feb 26, 2026
44Accuracy
5
Feb 26, 2026