Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
62.01Pass@1
9
Feb 26, 2026
1,550Pass@1
9
Feb 26, 2026
67.75Pass@8
9
Feb 26, 2026
43.81Mean@8
9
Feb 26, 2026
43.62mean@8
9
Feb 26, 2026
70.94Mean@8 Score
9
Feb 26, 2026
77.88Mean@8
9
Feb 26, 2026
0Cost ($)
9
Feb 26, 2026
0Cost ($)
9
Feb 26, 2026
186.5OTPS
9
Feb 26, 2026
61.03Pass@1
9
Feb 26, 2026
3.98Tokens Per Frame (TPF)
9
Feb 26, 2026
1TPF (Time Per First Token)
9
Feb 26, 2026
63.7Pass@1 Accuracy
9
Feb 27, 2026
80.4Avg@32
9
Feb 26, 2026
12Average Score @256
9
Feb 26, 2026
18.1Average Score (avg@256)
9
Feb 26, 2026
0.893Accuracy (Context Size 128)
9
Feb 26, 2026
29.2Accuracy (128 tokens)
9
Feb 26, 2026
74.3Acc (128)
9
Feb 26, 2026
82.34Accuracy
9
Feb 26, 2026
91.2Avg@3 Accuracy
9
Feb 26, 2026
95.9avg@3 Accuracy
9
Feb 26, 2026
84.6Accuracy
9
Feb 26, 2026
90Accuracy
9
Feb 26, 2026