Complex Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
53.4Accuracy (Seal-0)
8
Apr 21, 2026
39.3Orig Score
7
Feb 27, 2026
74.4Micro Avg Score
6
Jul 7, 2026
88Abstract Algebra Score
6
May 25, 2026
67.4BBH Solution Rate
6
Feb 26, 2026
16.26Accuracy
5
Apr 20, 2026
71.15Macro-F1
4
Jun 2, 2026
69.99Macro F1 Score
4
Jun 2, 2026
84.67Macro-F1
4
Jun 2, 2026
54.7Accuracy
4
Mar 19, 2026
54.9Accuracy
4
Mar 19, 2026
3LLM Calls
2
Mar 26, 2026
65.41BLEU-1
2
Feb 26, 2026
—
—Original Metric Value
0
Feb 26, 2026