List your company

Reasoning

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated
95.4Accuracy
Reasoning on Big-Bench Hard performance trend
770
Jun 29, 2026
96.3Accuracy (ARC-c)
Reasoning on ARC-c performance trend
113
Jul 2, 2026
1Accuracy
Reasoning on GSM8K performance trend
111
Jun 30, 2026
97.2Accuracy
Accuracy Evaluation on ARC Challenge (Reasoning) performance trend
100
May 26, 2026
73.9Accuracy
Reasoning on Big-Bench Hard (test) performance trend
94
May 19, 2026
86.3Accuracy on AIME 24
Accuracy on AIME 24 (Reasoning) performance trend
65
May 8, 2026