Multiple-choice Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
85Accuracy
6
Apr 21, 2026
62.9Accuracy
6
Apr 10, 2026
74.7Accuracy
6
Apr 10, 2026
75.63Accuracy
6
Apr 3, 2026
62Accuracy (General)
6
Mar 27, 2026
72.5Accuracy
6
Mar 4, 2026
77.4Accuracy
6
Mar 4, 2026
86.9Accuracy
6
Mar 4, 2026
71.7Accuracy
6
Mar 4, 2026
75.8Accuracy
6
Mar 4, 2026
89.2Accuracy
6
Mar 4, 2026
40.91Top-1 Accuracy
6
Feb 26, 2026
71.45Accuracy
6
Feb 26, 2026
86.31Accuracy
6
Feb 26, 2026
86Accuracy (%)
6
Feb 26, 2026
81.41Accuracy
6
Feb 26, 2026
83Accuracy
6
Feb 26, 2026
82.21Accuracy
6
Feb 26, 2026
56.85Accuracy
6
Feb 26, 2026
81.71Accuracy
6
Feb 26, 2026
93.46Accuracy
6
Feb 26, 2026
77.54Accuracy
6
Feb 26, 2026
0.3Delta Accuracy
6
Feb 26, 2026
0.5ΔAcc
6
Feb 26, 2026
0Delta Acc
6
Feb 26, 2026