Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Mathematical Reasoning on BeyondAIME (Mean@10)

71.8Mean@10

FlashMLA

69.40870.02970.6571.271Feb 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
71.8
2026.02
70.2
2026.02
69.9
2026.02
69.5