Multiple-choice Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
89.45Accuracy
43
May 19, 2026
91.2F1 Score
42
Apr 14, 2026
88.9Accuracy
42
May 12, 2026
87Overall Score
42
Jun 2, 2026
70.4Accuracy (%)
40
May 28, 2026
30.8Accuracy
40
May 28, 2026
72.8Accuracy
40
May 28, 2026
50.98Accuracy
39
Mar 16, 2026
76.2MC1 Accuracy
39
Apr 3, 2026
80Anatomy (EN) Accuracy
35
Apr 10, 2026
92.36Accuracy (College Biology, EN)
35
Apr 10, 2026
76.03Accuracy
34
Jun 2, 2026
57.77MC1 Score
34
Jun 4, 2026
78.2Normalized Accuracy
33
May 29, 2026
56.4Normalized Accuracy
33
May 29, 2026
35Accuracy
33
Feb 26, 2026
93Accuracy
32
Mar 30, 2026
92Accuracy
32
Mar 30, 2026
86Accuracy
32
Mar 30, 2026
89Accuracy
32
Mar 30, 2026
68.31Average Accuracy
31
Feb 26, 2026
70.59Accuracy
31
Feb 26, 2026
38.8HellaSwag Accuracy
30
Jun 5, 2026
44.4Accuracy
30
Jun 29, 2026
93.5Accuracy
29
Jul 7, 2026