Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Aggregate Language and Logic Tasks on HumanEval++, MATH, MMLU-Redux

94.61Average Accuracy

HieraMAS

82.681285.778188.87591.9719Feb 23, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
94.61
2026.02
92.78
2026.02
92.69
2026.02
91.6
2026.02
91.45
2026.02
90.89
2026.02
90.85
2026.02
90.68
2026.02
89.81
2026.02
89.77
2026.02
83.14