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

Home/Benchmarks

Knowledge Evaluation on MMLU-Pro (test)

58.84Accuracy (%)

T2M

Updated 1mo ago

Evaluation Results

Method	Links
T2M 2026.04		58.84
T2T 2026.04		58.78

SOTA Paper

T2M

Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Large Language Models

Dataset

MMLU-Pro

Follow for update

@wizwand_team Discord

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs