Reading Comprehension
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
75.21Personalized Accuracy (Acc_p)
5
Feb 26, 2026
0.623Hard Score
5
Feb 26, 2026
91.8Accuracy
5
Feb 26, 2026
72.6Accuracy
5
Feb 26, 2026
71.7Accuracy
5
Feb 26, 2026
52.17Clean Accuracy
4
Jun 16, 2026
40.9Accuracy
4
Mar 18, 2026
69.98Accuracy
4
Feb 27, 2026
79.24Accuracy
4
Feb 27, 2026
0.821Accuracy (PIQA)
4
Feb 26, 2026
71.88Average Score
4
Feb 26, 2026
94.8Accuracy (English)
4
Feb 26, 2026
60.5Accuracy
4
Feb 26, 2026
59.4Accuracy
4
Feb 26, 2026
44.2Accuracy
4
Feb 26, 2026
29.03BLEU
4
Feb 26, 2026
29.34BLEU
4
Feb 26, 2026
29.31BLEU
4
Feb 26, 2026
29.44BLEU
4
Feb 26, 2026
29.03BLEU
4
Feb 26, 2026
73.2EM
4
Feb 26, 2026
90.7F1 Score
4
Feb 26, 2026
91.4Accuracy
4
Feb 26, 2026
56.8EM
4
Feb 26, 2026
42BLEU-1
4
Feb 26, 2026