Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
59.2F1
15
Feb 26, 2026
91.27Accuracy
15
May 12, 2026
69.1F1 Score
15
Feb 26, 2026
2.16Delta Accuracy
15
Feb 27, 2026
40.2Accuracy
15
Feb 26, 2026
73.95Fact Retrieval (FR)
15
Feb 26, 2026
48.2Accuracy (Arabic)
15
Mar 10, 2026
77.1Accuracy
15
Feb 26, 2026
72.3Acc
15
Feb 26, 2026
85.3Accuracy
15
Feb 26, 2026
82.2Accuracy
15
Apr 8, 2026
93.1Accuracy
15
Mar 4, 2026
59.93F1 Score
15
Feb 26, 2026
66.4Score (History)
15
Feb 26, 2026
20.1EM
15
Feb 26, 2026
77.6EM
15
Feb 26, 2026
71.4Accuracy
15
Feb 26, 2026
67.3Recall
15
Feb 26, 2026
85.84F1 Score
15
Feb 26, 2026
85.54F1
15
Feb 26, 2026
85.84F1 Score
15
Feb 26, 2026
60.3EM
15
Feb 26, 2026
53.9ROUGE-L
15
Feb 26, 2026
79.9Accuracy
15
Feb 26, 2026
80.61EM
15
Feb 26, 2026