Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
25.07F1 Score
7
Feb 27, 2026
40.41F1 Score
7
Feb 27, 2026
55.09F1 Score
7
Feb 27, 2026
22.5F1 Score
7
Feb 27, 2026
51,066.2Average Token Count
7
Feb 26, 2026
30,205.1Average Token Count
7
Feb 26, 2026
26,442.6Avg Token Count
7
Feb 26, 2026
32,601.3Avg Answer Token Count
7
Feb 26, 2026
1,170Elo Score
7
Feb 26, 2026
59.8Accuracy
7
Feb 26, 2026
0.635Accuracy
7
Feb 26, 2026
58.3EM
7
Feb 26, 2026
86.33QA Accuracy
7
Feb 26, 2026
67.6Fact Retrieval
7
Feb 26, 2026
0.698EM
7
Feb 26, 2026
39.7EM
7
Feb 26, 2026
69.17BERTScore
7
Feb 26, 2026
37.71F1 Score
7
Feb 27, 2026
30,894.5Avg Token Count
7
Feb 26, 2026
5.8EM
7
Feb 26, 2026
81.2Accuracy
7
Feb 26, 2026
27.45ROUGE-L
7
Feb 26, 2026
23.87F1 Score
7
Feb 26, 2026
23.82BLEU-1
7
Feb 26, 2026
0.375BLEU-1
7
Feb 26, 2026