General Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
25.8Accuracy
4
Apr 13, 2026
86.6Accuracy
4
Apr 10, 2026
55.6Accuracy
4
Apr 10, 2026
81.9Accuracy
4
Apr 10, 2026
61.48Performance Score
4
Mar 12, 2026
31.5Avg@8
4
Mar 10, 2026
96.1Mean@1
4
Feb 26, 2026
84.15Mean@16
4
Feb 26, 2026
66.26Accuracy
4
Feb 26, 2026
162.3Throughput (Tokens/s)
3
Mar 12, 2026
54.77Macro Accuracy
2
May 22, 2026
49.29Macro Accuracy
2
May 22, 2026
53Winrate
1
Jun 23, 2026