Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
78Accuracy
10
Mar 18, 2026
50.4ROUGE-L
10
Mar 18, 2026
33.33F1
10
Mar 4, 2026
56.64F1 Score
10
Mar 4, 2026
97.92F1 Score
10
Mar 4, 2026
61.99F1 Score
10
Mar 4, 2026
67.25F1 Score
10
Mar 4, 2026
23.6F1 Score (Month 9)
10
Feb 27, 2026
3.184LIS
10
Feb 26, 2026
41Knowledge
10
Feb 26, 2026
60.7EM
10
Feb 26, 2026
43.2EM
10
Feb 26, 2026
50.94EM
10
Feb 26, 2026
51.3EM
10
Feb 26, 2026
60Exact Match
10
Feb 26, 2026
79.8EM
10
Feb 26, 2026
76.2Normalized Accuracy
10
Feb 26, 2026
40.1Avg@16
10
Feb 26, 2026
19.4Average @16
10
Feb 26, 2026
44Avg@16
10
Feb 26, 2026
47.2Avg@16
10
Feb 26, 2026
63.9Average Rate @16
10
Feb 26, 2026
58.3EM
10
Feb 26, 2026
51.51Accuracy
10
Feb 26, 2026
76.71Accuracy
10
Feb 26, 2026