Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
76.28Accuracy
6
Jun 9, 2026
95.53Accuracy
6
Jun 9, 2026
78.1Accuracy (Avg@8)
6
Jun 5, 2026
87Accuracy (Avg@8)
6
Jun 5, 2026
75.7Accuracy (Avg@8)
6
Jun 5, 2026
88.7Accuracy
6
Jun 4, 2026
47.64Average Score @16
6
Jun 4, 2026
49.95MATH500 Score
6
Jun 4, 2026
73.7Accuracy
6
Jun 4, 2026
78.9Strict-match Accuracy
6
Jun 2, 2026
49.8CD4 Score
6
Jun 2, 2026
89.93Pass@1
6
Jun 2, 2026
31.25Pass@1
6
Jun 2, 2026
44.27Pass@1
6
Jun 2, 2026
76.23Score
6
Jun 2, 2026
73.65Score
6
Jun 2, 2026
82.19Score
6
Jun 2, 2026
68.86Score
6
Jun 2, 2026
64.92Client 1 Accuracy
6
May 28, 2026
74.3Accuracy
6
May 28, 2026
0.61Accuracy
6
May 28, 2026
73Accuracy (Raw Consensus)
6
May 27, 2026
94.81Accuracy (Raw consensus)
6
May 27, 2026
96.13Accuracy (Raw Consensus)
6
May 27, 2026
69.3AIME 26 Score
6
May 27, 2026