Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
95.2GSM8K Accuracy
16
Feb 27, 2026
50.4Accuracy
16
Feb 26, 2026
76.1Exact Match (EM)
16
Feb 26, 2026
90.95Pass@16
16
Feb 26, 2026
100Pass@16
16
Feb 26, 2026
81.5Accuracy
16
Feb 26, 2026
86.67Accuracy
16
Feb 26, 2026
57.7Avg@2
16
Feb 26, 2026
82.1Avg@2
16
Feb 26, 2026
82.2Pass@1 Accuracy
16
Feb 26, 2026
91.4Accuracy
16
Feb 26, 2026
73.6Pass@16
16
Feb 26, 2026
77.9Pass@1
16
Feb 26, 2026
38.2Pass@1
16
Feb 26, 2026
72Accuracy
16
Feb 26, 2026
5.81Delta Accuracy
16
Feb 26, 2026
86.67Pass@5
16
Feb 26, 2026
90Pass@5
16
Feb 26, 2026
99.4Pass@5 Rate
16
Feb 26, 2026
97Pass@5
16
Feb 26, 2026
20.2Accuracy
16
Feb 26, 2026
92.7Accuracy
16
Feb 26, 2026
93.8Accuracy
16
Feb 26, 2026
93.6Success Rate
16
Feb 26, 2026
8,849.7Avg Context Length (tokens)
16
Feb 26, 2026