Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.861Score
6
Feb 26, 2026
66.8Score
6
Feb 26, 2026
71.2Accuracy
6
Feb 26, 2026
53.5EM
6
Feb 26, 2026
43.63BLEU-1
6
Feb 26, 2026
97.5Hits@1 (KB)
6
Feb 26, 2026
72.1Accuracy
6
Feb 26, 2026
64.6Exact Match
6
Feb 26, 2026
5Failed Tasks Count
6
Feb 26, 2026
67.25Accuracy
5
Jul 9, 2026
70.9QA Accuracy
5
Jul 8, 2026
62.5QA Accuracy
5
Jul 8, 2026
32.14Relevance
5
Jun 30, 2026
75.1Accuracy
5
Jun 30, 2026
31.1Accuracy (Acc)
5
Jun 30, 2026
63.7Accuracy
5
Jun 30, 2026
27.1Accuracy
5
Jun 30, 2026
95Accuracy
5
Jun 26, 2026
100Accuracy
5
Jun 26, 2026
100Accuracy
5
Jun 26, 2026
100Accuracy
5
Jun 26, 2026
86Accuracy
5
Jun 26, 2026
25.7Law Accuracy
5
Jun 24, 2026
33.8Accuracy
5
Jun 23, 2026
64.5MH
5
Jun 23, 2026