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

Home/Benchmarks

Code Generation on Multiple

78.51Score

MONA

Updated 7d ago

Evaluation Results

Method	Links
MONA 2026.05		78.51
Muon 2026.05		78.36
ckpt_-1 2026.05		60.82

SOTA Paper

MONA

MONA: Muon Optimizer with Nesterov Acceleration for Scalable Language Model Training

Dataset

Multiple

Follow for update

@wizwand_team Discord

Related Benchmarks

Multi-task Language Understanding on MMLU (Generic Score)Code Generation on LeetCode Mathematical Reasoning on Bigmath Mathematics Mathematical Reasoning on ProofWriter Commonsense Reasoning on Knowledge-Specific

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs