Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
56.1Final Answer Accuracy
5
Feb 26, 2026
91.8Accuracy
5
Feb 26, 2026
82.5Pass@1 Mean
5
Feb 26, 2026
48.3Pass@1 Mean Score
5
Feb 26, 2026
63.2Pass@1 Mean
5
Feb 26, 2026
96Accuracy
5
Feb 26, 2026
59.5GPQA Score
5
Feb 26, 2026
91.6Accuracy
5
Feb 26, 2026
55.3Avg Math Score
5
Feb 26, 2026
800TPF
5
Feb 26, 2026
65.4Accuracy (avg@16)
5
Feb 26, 2026
13.28Accuracy
5
Feb 26, 2026
88.4Accuracy
5
Feb 26, 2026
87.6Score
5
Feb 26, 2026
2.21Speedup
5
Feb 26, 2026
843.05Throughput (TPS)
5
Feb 26, 2026
791.23Throughput (TPS)
5
Feb 26, 2026
65.62Avg@16
5
Feb 26, 2026
79.5Accuracy
5
Feb 26, 2026
36Accuracy
5
Feb 26, 2026
60Accuracy
5
Feb 26, 2026
80.8Micro Avg. Accuracy
5
Feb 26, 2026
44.8Accuracy (5-shot)
5
Feb 26, 2026
1.437AMC 12 2024 Score
5
Feb 26, 2026
33Accuracy (P_clean, Avg)
5
Feb 26, 2026