Reading Comprehension
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
66.2Accuracy
6
Feb 26, 2026
34.11Accuracy (Estonian)
6
Mar 6, 2026
53.6Accuracy
6
Feb 26, 2026
74Exact Match (EM)
6
Feb 26, 2026
10.3Accuracy (0-shot)
6
Feb 26, 2026
71.4Acc (0-shot)
6
Feb 26, 2026
90.6Accuracy
6
Feb 26, 2026
44.3F1 Score
6
Feb 26, 2026
85F1 Score
6
Feb 26, 2026
82.1Accuracy
6
Feb 26, 2026
90.6Accuracy
6
Feb 26, 2026
38.6EM
6
Feb 26, 2026
52.78BLEU-1
6
Feb 26, 2026
61.4Follow
6
Feb 26, 2026
41.6F1 Score
5
Jun 4, 2026
34.9Belebele RC Score (CA)
5
May 29, 2026
29.9Likelihood Accuracy
5
May 28, 2026
82.4Pass@1
5
May 7, 2026
33.1Accuracy
5
Apr 21, 2026
25.7Accuracy
5
Apr 21, 2026
29.9Accuracy
5
Apr 21, 2026
34.1Accuracy
5
Apr 21, 2026
90.3Accuracy (ZH)
5
Apr 21, 2026
83.08Accuracy
5
Mar 10, 2026
83.7F1 Score
5
Feb 26, 2026