Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
47.7EM
6
Apr 9, 2026
31Accuracy
6
Apr 8, 2026
95.4Accuracy
6
Apr 8, 2026
20.7Genuine Followup Rate
6
Apr 3, 2026
81.75Accuracy (Set 1)
6
Apr 2, 2026
46.42Accuracy (MMLU Psychology)
6
Apr 2, 2026
36.87Accuracy
6
Apr 2, 2026
20.77Accuracy
6
Apr 2, 2026
10.63Accuracy
6
Apr 2, 2026
9.78Accuracy
6
Apr 2, 2026
25.04Accuracy
6
Apr 2, 2026
19.71Accuracy
6
Apr 2, 2026
38.84ROUGE-1
6
Mar 31, 2026
15.22ROUGE-1
6
Mar 31, 2026
79.3Rubrics Score
6
Mar 31, 2026
33.46F1 Score
6
Mar 27, 2026
1Answerability Rate
6
May 27, 2026
80.6F1 Score
6
Mar 25, 2026
80.7Accuracy
6
Mar 24, 2026
74.7F1 Score
6
Mar 20, 2026
96Accuracy
6
Mar 19, 2026
95Accuracy
6
Mar 19, 2026
66.9Normalized Log Accuracy
6
Mar 18, 2026
29.54ROUGE
6
Mar 13, 2026
5.59ROUGE
6
Mar 13, 2026