Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
67.65Accuracy
9
Jun 2, 2026
16.7Accuracy
9
Jun 2, 2026
44Accuracy
9
Jun 2, 2026
12Greedy Success Rate
9
May 29, 2026
48.8Greedy
9
May 29, 2026
96.4Accuracy
9
May 29, 2026
100Accuracy
9
May 29, 2026
96.3Accuracy
9
May 29, 2026
89.2Accuracy
9
May 26, 2026
94.1Accuracy
9
May 26, 2026
94.1Accuracy
9
May 26, 2026
87.87Math 500 Accuracy
9
May 26, 2026
2.15Accuracy Deg %
9
May 25, 2026
57.8SAT Math Score
9
May 21, 2026
51.4Score
9
May 21, 2026
94.39Task Accuracy
9
Jun 30, 2026
38.7nR2
9
May 20, 2026
90.7Accuracy
9
May 19, 2026
78.1Accuracy
9
May 19, 2026
70Accuracy
9
May 19, 2026
60Accuracy
9
May 19, 2026
90.9Accuracy
9
May 19, 2026
97.8Accuracy
9
May 19, 2026
97.4Accuracy
9
May 19, 2026
0.3Accuracy Degradation (Δ)
9
May 19, 2026