Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
39Accuracy (Avg@16)
15
May 19, 2026
83.1Average Accuracy @16
15
May 19, 2026
81.9Pass@1 Accuracy
15
May 15, 2026
57.2Pass@1
15
May 15, 2026
58.19Accuracy
15
May 13, 2026
72.5Average@12 Accuracy
15
May 13, 2026
80.56Average@12 Accuracy (AIME 2024)
15
May 13, 2026
26.7AIME 2024 Score
15
May 13, 2026
39.18Avg@k
15
May 13, 2026
37.09Avg@k
15
May 13, 2026
74.95Avg@k
15
May 13, 2026
55.31Avg@k
15
May 13, 2026
19.38Avg@k
15
May 13, 2026
15.21Avg@k
15
May 13, 2026
61.46Accuracy (AIME 25)
15
May 12, 2026
95Accuracy
15
May 12, 2026
56.8Accuracy
15
May 12, 2026
10.8Accuracy
15
May 12, 2026
60.42Average Score (32 samples)
15
May 11, 2026
78.1Average Score (@16)
15
May 11, 2026
16.51Mean Score (32 Samples)
15
May 8, 2026
19.9Mean Score (k=32)
15
May 8, 2026
61.19Accuracy@1
15
May 8, 2026
65Pass@1
15
May 7, 2026
26.7Pass@1
15
May 7, 2026