Multiple-choice Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
51.5ARC-C Accuracy
12
Jul 2, 2026
71.5Accuracy
12
Mar 30, 2026
52.2Accuracy
12
Mar 30, 2026
63.3Accuracy
12
Mar 30, 2026
73.5Accuracy
12
Mar 30, 2026
84Accuracy
12
Mar 30, 2026
34.64Accuracy (MC1 Delta)
12
Jun 9, 2026
43.6ARC-Challenge Accuracy
12
Mar 12, 2026
39.65Accuracy
12
Feb 26, 2026
86Accuracy
12
Feb 26, 2026
69.36MC9 Accuracy
12
Feb 26, 2026
84.4Accuracy
12
Feb 26, 2026
99.5Blood Safety & STIs/HIV Accuracy
11
Jul 9, 2026
60.46MCQ Accuracy
11
May 12, 2026
77.6Dynasty Accuracy
11
Mar 31, 2026
62.5MMLU
11
Mar 26, 2026
0Cost (cents)
11
Mar 24, 2026
94.2Choice-V & T Accuracy (Single)
11
Feb 26, 2026
79.86Accuracy
11
Jul 7, 2026
68.3Accuracy
11
Feb 26, 2026
99.82Accuracy
11
Feb 26, 2026
84.91Score
10
Jul 7, 2026
19.6NComm
10
May 25, 2026
22.8NComm
10
May 25, 2026
99.54Accuracy
10
May 25, 2026