General Reasoning and Coding
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
24.15Delta
28
Jun 8, 2026
4Speed
26
May 26, 2026
96.6ARC-c (pass@1)
16
Apr 10, 2026
31.9GSM8K Score
6
Jun 29, 2026
51.4GSM8K Accuracy
6
Jun 29, 2026
64.1GSM8K Accuracy
6
Jun 29, 2026
74.7Average Accuracy
4
Jun 23, 2026