Extractive Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
92.9F1 Score
34
Feb 26, 2026
80.8F1 Score
22
Feb 27, 2026
83F1 Score
22
Feb 27, 2026
72.6F1
22
Feb 27, 2026
81F1 Score
22
Feb 27, 2026
78.2F1 Score
22
Feb 27, 2026
60.57EM
21
May 29, 2026
73.6NewsQA Score
19
Feb 26, 2026
92.2F1 Score
16
Feb 27, 2026
62.42EM
16
Feb 26, 2026
65.93EM
16
Feb 26, 2026
47.27EM
16
Feb 26, 2026
78.11EM
16
Feb 26, 2026
78.6EM
16
Feb 26, 2026
99.04F1
14
Feb 26, 2026
59.7F1 Score
14
Feb 26, 2026
54.5F1 Score
12
Feb 27, 2026
91F1 Score
12
Feb 27, 2026
0.91Calibration Score (C)
10
Feb 26, 2026
74.94EM
10
Feb 26, 2026
75.981EM
8
Jun 19, 2026
27.368EM
8
Jun 19, 2026
53Jaccard Score (Overall)
8
Feb 26, 2026
55.5QA F1
7
Feb 26, 2026
71.28BERTScore F1
7
Feb 26, 2026