Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
49.5F1 Score
9
Feb 26, 2026
86.7Win Rate
9
Feb 26, 2026
47.6Accuracy
9
Feb 26, 2026
75Accuracy
9
Feb 26, 2026
1.272PPL
9
Feb 26, 2026
1.408PPL
9
Feb 26, 2026
87Accuracy
9
Feb 26, 2026
71.7Accuracy
9
Feb 26, 2026
91.3Accuracy
9
Feb 26, 2026
50.6Accuracy
9
Feb 26, 2026
37.9Accuracy
9
Feb 26, 2026
44.4Accuracy
9
Feb 26, 2026
46.3Accuracy
9
Feb 26, 2026
78.9Accuracy
9
Feb 26, 2026
69.5Accuracy
9
Feb 26, 2026
81.6Accuracy
9
Feb 26, 2026
59.45F1 (NQ)
9
Feb 26, 2026
58QA1 Accuracy
9
Feb 26, 2026
72.4Accuracy
9
Feb 26, 2026
76.2Accuracy
9
Feb 26, 2026
91.5Accuracy
9
Feb 26, 2026
84Accuracy
9
Feb 26, 2026
76.84Accuracy
9
Feb 26, 2026
59.37Prog Acc
9
Feb 26, 2026
36.9Hit@1
9
Feb 26, 2026