Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.115Brier Score
6
Mar 5, 2026
0Average Latency
6
Mar 5, 2026
1,407.4Tokens to Target Accuracy (MATH Streaming)
6
Mar 5, 2026
54.92Accuracy
6
Mar 4, 2026
77.6GSM8K Accuracy
6
Mar 4, 2026
79.17Mean@16 Accuracy
6
Mar 4, 2026
37.1Accuracy
6
Mar 4, 2026
36.67Accuracy
6
Mar 4, 2026
18.1Acc@16
6
Feb 27, 2026
19.4Acc@16
6
Feb 27, 2026
39.8Acc@16
6
Feb 27, 2026
65.3Accuracy@16
6
Feb 27, 2026
31.4Accuracy
6
Feb 26, 2026
71.9Accuracy
6
Feb 26, 2026
27.93Accuracy
6
Feb 26, 2026
51.35Accuracy
6
Feb 26, 2026
20.4Accuracy
6
Feb 26, 2026
0.231Dist-3 Score
6
Feb 26, 2026
88.86Pass@32
6
Feb 26, 2026
41.25Pass@32
6
Feb 26, 2026
47.19Pass@32
6
Feb 26, 2026
60.29Pass@32
6
Feb 26, 2026
69.04Pass@32
6
Feb 26, 2026
94.2Pass@32
6
Feb 26, 2026
91.8Accuracy
6
Feb 26, 2026