Chain-of-Thought Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
86.9Accuracy (Acc)
21
Mar 10, 2026
73.7Composite Score
20
Feb 26, 2026
74.32Accuracy
12
Jun 2, 2026
67.93Accuracy
12
Jun 2, 2026
81.46Accuracy
12
Jun 2, 2026
81.04Accuracy
12
Jun 2, 2026
15.1Accuracy
11
Mar 19, 2026
64.22S_FC Score
11
Mar 9, 2026
21.6Best@3
8
May 22, 2026
0.88GPT Score
5
Feb 26, 2026
54.42Accuracy (BBH CoT)
3
May 29, 2026