Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
43.33Pass@128
30
Apr 21, 2026
36.67Pass@128
30
Apr 21, 2026
66.67Pass@128
30
Apr 21, 2026
56.67Pass@128
30
Apr 21, 2026
73.33Pass@128
30
Apr 21, 2026
42.2Accuracy
30
Apr 20, 2026
66.7Pass@k
30
Apr 14, 2026
63.3Pass@k
30
Apr 14, 2026
91.4Pass@k
30
Apr 14, 2026
66.6GSM8K Accuracy
30
Apr 14, 2026
73.3Accuracy (%)
30
Apr 10, 2026
92.87Pass@1
30
Jun 16, 2026
1.67Average Inference Time (s)
30
Mar 25, 2026
68.2Intelligence Per Token (IPT)
30
May 11, 2026
28Pass@1
30
Jun 1, 2026
68.3Accuracy
30
Mar 4, 2026
48.5Pass@8
30
May 13, 2026
26.2Accuracy
30
Feb 26, 2026
65.9Accuracy
30
Feb 26, 2026
77Accuracy (pass@1)
30
Jun 11, 2026
81.3Accuracy
30
Feb 26, 2026
103.69Tokens
30
Mar 4, 2026
83.1Avg@4
30
Feb 26, 2026
27.92Avg@32
30
Feb 26, 2026
75.83AIME'25 Accuracy
30
Jun 26, 2026