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

Home/Benchmarks

Code Generation on HumanEval dLLM-Var

31.7Pass@1

LR-DLLM

Updated 1mo ago

Evaluation Results

Method	Links
LR-DLLM 2026.02		31.7
dLLM-Var 2026.02		17.7

SOTA Paper

LR-DLLM

Improving Variable-Length Generation in Diffusion Language Models via Length Regularization

Dataset

HumanEval

Follow for update

@wizwand_team Discord

Related Benchmarks

Code Infilling on HumanEval Infilling Code Infilling on McEval Single-line Code Infilling on McEval Multi-line Mathematical Reasoning on MATH500 dLLM-Var (Accuracy)

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs