Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
33Accuracy
16
Apr 20, 2026
59.29Overall Accuracy
16
Jun 23, 2026
74Accuracy
16
Mar 4, 2026
37.1Accuracy
16
Feb 26, 2026
48.75Accuracy
16
Feb 26, 2026
93.9ARC-C Score
16
Feb 27, 2026
100Accuracy
16
Feb 26, 2026
90Accuracy
16
Feb 26, 2026
95.8Accuracy
16
Feb 26, 2026
99Accuracy
16
Feb 26, 2026
90.7Accuracy
16
Feb 26, 2026
58.3Accuracy
16
Feb 26, 2026
100Accuracy
16
Feb 26, 2026
86.67Pass@8
16
Apr 23, 2026
10,572Thinking Tokens Count
15
Jun 17, 2026
72.93MMLU Accuracy
15
May 13, 2026
24.1Score
15
May 13, 2026
51.2Score
15
May 13, 2026
0.48Score
15
May 13, 2026
24.1Score
15
May 13, 2026
51.2Score
15
May 13, 2026
48Reasoning Score (SynthWorlds)
15
May 13, 2026
38.72Accuracy
15
Jun 2, 2026
66.8Pass@1 Accuracy
15
Apr 6, 2026
93.7pass@1 Accuracy
15
May 13, 2026