Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
47.66Performance (%)
8
May 26, 2026
9.58AIME 2025 Performance
8
May 26, 2026
12.92Performance (%)
8
May 26, 2026
76.8Exact Match
8
May 26, 2026
26.7Pass@1
8
May 26, 2026
85.1Pass@1
8
May 26, 2026
11.9Pass@1
8
May 26, 2026
8.3Pass@1
8
May 26, 2026
19.6Pass@1
8
May 26, 2026
76.74Accuracy
8
May 21, 2026
26.67Pass@8
8
May 20, 2026
30P@8
8
May 20, 2026
52.5Accuracy
8
May 18, 2026
72.9Accuracy
8
May 18, 2026
96.77Accuracy
8
May 14, 2026
96.02Accuracy
8
May 14, 2026
67.59Accuracy
8
May 13, 2026
65.88Accuracy (GSM8K ID)
8
May 13, 2026
26.84Avg@4 Score
8
May 13, 2026
24.38Avg@32
8
May 13, 2026
2.6Pass@1 Score
8
May 13, 2026
35.3Accuracy
8
May 12, 2026
76.2MATH500 Score
8
May 12, 2026
40Accuracy
8
May 12, 2026
95.6Score
8
May 12, 2026