Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
75F1 Score
4
Feb 26, 2026
0.796MRR
4
Feb 26, 2026
80.93Flans Score
4
Feb 26, 2026
79.32Flans Score
4
Feb 26, 2026
73.15Flans
4
Feb 26, 2026
0.426EM
4
Feb 26, 2026
75.3F1 Score
4
Feb 26, 2026
59.6Success Rate
4
Feb 26, 2026
81.4Accuracy - English
4
Feb 26, 2026
40.1Accuracy
4
Feb 26, 2026
72.8Accuracy
4
Feb 26, 2026
97.75Q1 Score
4
Feb 26, 2026
61.67QA-avg Score
4
Feb 26, 2026
76.2Accuracy
4
Feb 26, 2026
88.2Accuracy
4
Feb 26, 2026
87.6Accuracy
4
Feb 26, 2026
83.72EM
4
Feb 26, 2026
90.2Accuracy
4
Feb 26, 2026
42.6F1 (Arabic)
4
Feb 26, 2026
73.8Arabic F1
4
Feb 26, 2026
92.66Accuracy
4
Feb 26, 2026
72.4Average Score
4
Feb 26, 2026
68.67Accuracy
4
Feb 26, 2026
59.1EM
4
Feb 27, 2026
31.6ROUGE-L
4
Feb 26, 2026