Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
43.33Pass@1 Accuracy
18
Apr 6, 2026
0.656Pass@1
18
Feb 26, 2026
73.47Pass@1
18
Feb 26, 2026
80.63AIME 2024 Score
18
Feb 26, 2026
33.33Pass@1
18
Feb 26, 2026
62Pass@1 Rate
18
Feb 26, 2026
81.35avg@32
18
Feb 26, 2026
74.4Pass@1
18
Feb 26, 2026
39.69Throughput (tokens/s)
18
Feb 26, 2026
53.33Accuracy
18
Feb 26, 2026
90.83Accuracy
18
Feb 26, 2026
93.67Accuracy
18
Feb 26, 2026
93.5Pass@1 Acc
18
Mar 19, 2026
34.1Pass@1
18
Feb 26, 2026
27Pass@1
18
Feb 26, 2026
43.3Pass@1 Success Rate
18
Apr 14, 2026
84.6Accuracy
18
Feb 26, 2026
24.58Acc@16
18
Mar 24, 2026
92.9Score
18
Feb 26, 2026
0.863Score
18
Feb 26, 2026
0.767SC Accuracy
18
Feb 26, 2026
80SC Accuracy
18
Feb 26, 2026
91.9SC Accuracy
18
Feb 26, 2026
90.9SC Accuracy
18
Feb 26, 2026
71.42Pass@1
18
Feb 26, 2026