Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
99.2Accuracy
8
Mar 24, 2026
100Accuracy
8
Mar 24, 2026
96.7Accuracy (Acc)
8
Mar 24, 2026
99.2Accuracy
8
Mar 24, 2026
100Accuracy
8
Mar 24, 2026
89.2Accuracy
8
Mar 24, 2026
99.44Accuracy (Clean)
8
Mar 17, 2026
85.2Accuracy
8
Mar 16, 2026
60.77Accuracy
8
Mar 12, 2026
81.26Accuracy
8
Mar 12, 2026
58Cumulative Score (CS)
8
Mar 10, 2026
80.82Accuracy
8
Mar 6, 2026
49.2Accuracy
8
Mar 4, 2026
49.9Accuracy
8
Mar 4, 2026
80.83Accuracy (MATH Test)
8
Mar 4, 2026
53.8Answer Correctness Rate
8
Feb 26, 2026
82.6Accuracy
8
Feb 26, 2026
83.2Accuracy
8
Feb 26, 2026
83.8Accuracy
8
Feb 26, 2026
82Accuracy
8
Feb 26, 2026
51.63Last Score
8
Feb 26, 2026
21.4Avg@8 (AIME)
8
Feb 26, 2026
81.48ACC (%)
8
Feb 26, 2026
12.37Throughput
8
Feb 26, 2026
49.36GSM8K Accuracy
8
Feb 26, 2026