Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
77.7Mean@16
12
Jun 9, 2026
76.7Pass@16
12
Jun 9, 2026
38.8Accuracy
12
Jun 9, 2026
75.13Accuracy
12
Jun 9, 2026
48.3Accuracy (%)
12
Jun 8, 2026
82.8Accuracy (ACC)
12
Jun 5, 2026
75.8Accuracy
12
Jun 5, 2026
49.5Average Score
12
Jun 4, 2026
96.6Average Score
12
Jun 4, 2026
46.4Average Score
12
Jun 4, 2026
71.1Avg Score (AIME 25)
12
Jun 4, 2026
76.9Average Score
12
Jun 4, 2026
31.06Average Score
12
Jun 4, 2026
16.29Avg@16
12
Jun 4, 2026
11.25Avg@16 Score
12
Jun 4, 2026
21.46Avg@16
12
Jun 4, 2026
95Accuracy
12
Jul 2, 2026
85.8Pass@1
12
Jun 4, 2026
66.84Performance Score
12
Jun 2, 2026
90.8Accuracy (%)
12
Jun 2, 2026
20.9Accuracy
12
Jun 2, 2026
76Pass@1 Accuracy
12
Jun 1, 2026
11.08Average Count of Unique Outputs
12
Jun 1, 2026
12Average Unique Outputs Count
12
Jun 1, 2026
79.03GSM8K Accuracy
12
May 29, 2026