Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
27.87F1 Score
10
Feb 26, 2026
29.13EM
10
Feb 26, 2026
61.61EM
10
Feb 26, 2026
36.73EM
10
Feb 26, 2026
59.22Accuracy
10
Feb 27, 2026
43.8Accuracy
10
Feb 26, 2026
79.6F1 Score
10
Feb 26, 2026
64.83F1 Score
10
Feb 26, 2026
14.73F1
10
Feb 26, 2026
49.5F1 Score
10
Feb 26, 2026
38.4F1 Score
10
Feb 26, 2026
44.42F1 Score
10
Feb 26, 2026
34.8F1 Score
10
Feb 26, 2026
51.51F1 Score
10
Feb 26, 2026
31.6F1
10
Feb 26, 2026
36.45F1 Score
10
Feb 26, 2026
8.56Accuracy
10
Feb 26, 2026
85.6EM Score (TriviaQA)
10
Feb 26, 2026
12.29Accuracy
10
Feb 26, 2026
14.8Accuracy
10
Feb 26, 2026
29.2F2021
10
Feb 26, 2026
27.9F2022 Score
10
Feb 26, 2026
83.8Exact Match
10
Feb 26, 2026
28.8F1
10
Feb 26, 2026
84.6Accuracy
10
Feb 26, 2026