Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
12.2Latency (s)
24
Feb 26, 2026
1.7Latency (s)
24
Feb 26, 2026
1.2Inference Latency (s)
24
Feb 26, 2026
22C_mem Ratio
24
Feb 26, 2026
0.1C_mem (Ratio)
24
Feb 26, 2026
12Memory Usage Ratio
24
Feb 26, 2026
36.67Pass@1
24
Feb 27, 2026
61.2Pass@8
24
Apr 14, 2026
88.1Accuracy
24
Feb 26, 2026
93.33Top-1 Accuracy
24
Feb 26, 2026
15.02Accuracy
24
Feb 26, 2026
0.558Accuracy
24
Feb 26, 2026
89.46Accuracy
24
Feb 26, 2026
85.9Accuracy
24
Feb 26, 2026
36.7Accuracy
24
Feb 26, 2026
83.53Pass@1 Accuracy
24
Apr 9, 2026
39.48Pass@8
24
Mar 25, 2026
46.67Average Score @ 16
24
Mar 4, 2026
96.7Accuracy
24
Feb 26, 2026
0.467Mean@64 Acc
24
Apr 21, 2026
23.33Pass@1
24
Feb 26, 2026
91.88MathQA Accuracy
24
Feb 26, 2026
32Accuracy
24
Feb 26, 2026
81.1Pass@1
24
Feb 26, 2026
66.4m1@t1
24
Feb 26, 2026