Reading Comprehension
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
94.5Accuracy
295
Feb 27, 2026
94.47Accuracy
279
Mar 12, 2026
88.47Accuracy (BoolQ)
258
Jun 24, 2026
89.9Accuracy
196
Feb 26, 2026
89.95Accuracy
151
Feb 26, 2026
92.28DROP Accuracy
138
Jun 30, 2026
92.2F1 Score
96
May 21, 2026
93.5Accuracy
89
May 26, 2026
68.3Accuracy
86
Jun 18, 2026
96.42F1 Score
76
May 14, 2026
74.93Accuracy
75
May 26, 2026
88.1F1 Score
63
Feb 27, 2026
99.87Accuracy
43
May 12, 2026
75.91Attack Accuracy
40
Apr 28, 2026
84.7Accuracy
39
Mar 10, 2026
93F1 Score
38
Jul 8, 2026
85.66Accuracy (%)
37
Jun 18, 2026
86.2F1 Score
35
Jul 1, 2026
85.91Overall Score
34
Apr 14, 2026
97.7Accuracy
34
Feb 26, 2026
37.11Accuracy (Normalized)
32
Apr 23, 2026
93.7Accuracy
32
Apr 10, 2026
72.9MultiRC Accuracy
32
Jun 18, 2026
69.42F1 Score
32
Apr 10, 2026
80Average RC Score (BELEBELE)
31
Feb 26, 2026