Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
65.9Precision
9
Feb 26, 2026
80.08EM Score
9
Feb 26, 2026
83.13Unhelpful
9
Feb 26, 2026
14.32Misleading Rate
9
Feb 26, 2026
33.91Accuracy
9
Feb 26, 2026
21.34Average Score
9
Feb 26, 2026
86.83Accuracy
9
Feb 26, 2026
87.05Accuracy
9
Feb 26, 2026
79.02EM
9
Feb 26, 2026
56.8EM
9
Feb 26, 2026
0Balanced Acc (Old N/O)
9
Feb 26, 2026
0Balanced Accuracy (Old N/O)
9
Feb 26, 2026
69.51Accuracy
9
Feb 26, 2026
79.16Accuracy
9
Feb 26, 2026
64.31Accuracy
9
Feb 26, 2026
49.7F1 Score
9
Feb 27, 2026
79.8Exact Match (EM)
9
Feb 26, 2026
89.5Accuracy
9
Feb 26, 2026
82.4F1 Score
9
Feb 26, 2026
84.5F1
9
Feb 26, 2026
84.2F1 Score
9
Feb 26, 2026
68Accuracy
8
Jun 19, 2026
46.9Accuracy
8
Jun 16, 2026
83.5Accuracy
8
Jun 15, 2026
54.7Exact Match (EM)
8
Jun 12, 2026