Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
40.91Avg@8
14
Feb 26, 2026
25.34Average Score @8
14
Feb 26, 2026
23.9Avg@8
14
Feb 26, 2026
80.73Avg@8 Score
14
Feb 26, 2026
52.5Avg@8
14
Feb 26, 2026
19.17Avg@8
14
Feb 26, 2026
58.76GSM8K Accuracy
14
Feb 26, 2026
76.2Accuracy (pass@1)
14
Feb 26, 2026
38.2Pass@1
14
Feb 26, 2026
212Token Count
14
Feb 26, 2026
0.445NLL
14
Feb 26, 2026
90Avg Score @16
14
Feb 26, 2026
85.8AIME 2024 Avg Score
14
Feb 26, 2026
39.2Greedy Success
14
Mar 4, 2026
93Accuracy
14
Feb 26, 2026
473TPF
14
Feb 26, 2026
5.07TPF
14
Feb 26, 2026
25.1Avg@8 Score
14
Mar 13, 2026
52Latency (min)
14
Feb 26, 2026
75.8Accuracy
14
Feb 26, 2026
69.9Accuracy
14
Feb 26, 2026
36.7Accuracy
14
Feb 26, 2026
90.5Avg@32 Accuracy
14
Feb 26, 2026
52.8Pass@1 (Avg@32)
14
Feb 26, 2026
73.8Pass@1 (Avg@32)
14
Feb 26, 2026