Share your thoughts, 1 month free Claude Pro on usSee more
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 1mo 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