Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
39.33Avg@10 Accuracy
15
Apr 7, 2026
90.07Avg@5 Accuracy
15
Apr 7, 2026
0.773vbal Score
15
Apr 7, 2026
0.778VBAL Score
15
Apr 7, 2026
97.9Pass@1 Accuracy
15
Apr 6, 2026
72.2Pass@1 Accuracy
15
Apr 6, 2026
52.56Mean Value (MV)
15
Apr 3, 2026
83.6Accuracy
15
Apr 1, 2026
62.45Avg@8
15
Apr 14, 2026
89.6Accuracy (GSM8K)
15
Mar 27, 2026
89.84Accuracy
15
Mar 27, 2026
2.414Speedup Ratio
15
Mar 26, 2026
30.4Accuracy
15
Mar 10, 2026
82.2Accuracy
15
Mar 10, 2026
94.1Accuracy
15
Mar 10, 2026
64.79Accuracy
15
Mar 4, 2026
68.77Accuracy
15
May 12, 2026
54.6Throughput
15
Feb 26, 2026
0.457Accuracy (@avg1)
15
Feb 26, 2026
81.6Accuracy (@avg1)
15
Feb 26, 2026
15.6Accuracy (avg@32)
15
Feb 26, 2026
80.8Accuracy
15
Feb 26, 2026
96.36AVG@8
15
Feb 26, 2026
51.8@1 Success Rate
15
Mar 13, 2026
19.6Average@16
15
Feb 26, 2026