Multiple-choice Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
55.12Accuracy
15
Apr 24, 2026
80.38Accuracy
15
Apr 24, 2026
58.54Accuracy
15
Apr 24, 2026
37.8Overall Accuracy
15
Apr 15, 2026
63.62Accuracy
15
Mar 16, 2026
58.34Accuracy (%)
15
Mar 16, 2026
0.073Mean Per-Step Regret
15
Feb 26, 2026
0.137Mean Per-Step Regret
15
Feb 26, 2026
59.7EN Accuracy
14
Jun 11, 2026
67.1EN Accuracy
14
Jun 11, 2026
89.7EN Accuracy
14
Jun 11, 2026
81.5Accuracy (MMLU-Pro)
14
Jun 12, 2026
82.6Average Accuracy
14
Apr 23, 2026
90.5Accuracy (ZH)
14
Apr 21, 2026
88.8Wealth Acc
14
Feb 26, 2026
40.43Accuracy
14
Feb 26, 2026
65.6Accuracy (ACC)
13
Jun 2, 2026
79.12Accuracy
13
Jun 2, 2026
62.47Accuracy (Humanities)
13
Jun 2, 2026
76.9Accuracy
13
Mar 30, 2026
82.7Accuracy
13
Mar 30, 2026
63.8Accuracy
13
Jun 11, 2026
80.1Accuracy
13
Jun 11, 2026
84.54Accuracy
13
Mar 16, 2026
57.5Average Score
13
Feb 26, 2026