Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
88Accuracy
12
Feb 26, 2026
37.1Accuracy
12
Feb 26, 2026
70.96Accuracy
12
Feb 26, 2026
44.11Average Score
12
Feb 26, 2026
75.16AIME 24 Average Score
12
Feb 26, 2026
96.4MATH500 Average Score
12
Feb 26, 2026
74.8Accuracy
12
Feb 26, 2026
0.848Accuracy
12
Feb 26, 2026
42.38Total Average Score
12
Mar 31, 2026
2.14Accuracy Improvement
12
Feb 27, 2026
2.12Accuracy Improvement
12
Feb 27, 2026
2.05Accuracy Improvement
12
Feb 27, 2026
1.22Accuracy Improvement
12
Feb 27, 2026
76OCR
12
Mar 6, 2026
65.8Biology Accuracy
11
Jun 30, 2026
86.25Accuracy (BBH matched-N)
11
Jun 1, 2026
9.26Brier Score (BBH)
11
Jun 1, 2026
60.2Graphical Puzzles
11
May 21, 2026
85.2Accuracy@1
11
Apr 28, 2026
69Accuracy@1
11
Apr 28, 2026
44Accuracy@1
11
Apr 28, 2026
89.2Easy Score
11
Apr 21, 2026
64.01Character-level Accuracy
11
Mar 18, 2026
73.01Risk Assessment Accuracy
11
Mar 4, 2026
91Accuracy
11
Feb 26, 2026