Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
97Pass@1
31
Jun 8, 2026
84.8DM-1 Score
31
Jun 8, 2026
97.17Accuracy
31
Apr 21, 2026
43.3AIME24 Score
31
Apr 23, 2026
89.4Pass@k (PK)
31
Jun 16, 2026
79.3Avg@32
31
Apr 29, 2026
86.4Accuracy
31
May 1, 2026
68.6Accuracy
31
May 18, 2026
93.3Accuracy
31
May 12, 2026
94.61Avg@16
31
May 29, 2026
75.07Accuracy
31
Feb 26, 2026
72.3Accuracy
31
Feb 26, 2026
91.7Pass@1
31
May 27, 2026
60.5Avg@16
30
Jul 9, 2026
84.1Avg@16
30
Jul 9, 2026
87Accuracy
30
Jun 11, 2026
9,043Throughput (tokens/s)
30
May 29, 2026
54.53Accuracy
30
May 26, 2026
87.6Ac (alpha=0.10)
30
May 15, 2026
97.7Ac (alpha=0.10)
30
May 15, 2026
75.81Average Accuracy
30
May 19, 2026
71.7Pass@16
30
May 22, 2026
78.4AIME24 Score
30
Jun 23, 2026
86Accuracy (avg@16)
30
May 11, 2026
72.7GSM8K Accuracy
30
Apr 23, 2026