Grade School Math Reasoning
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
98Accuracy (GSM8K)
186
Jun 23, 2026
94.53Accuracy
42
May 29, 2026
61.33GSM8K Accuracy
20
Apr 10, 2026
94.9Accuracy
12
Jun 11, 2026
28.2GSM8K Accuracy
11
Jul 9, 2026
94.84Accuracy
10
Jun 4, 2026
0.248Accuracy
6
Feb 26, 2026