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

Home/Benchmarks

Coding on LCB (Accuracy)

2.8Accuracy

GRPO

Updated 1mo ago

Evaluation Results

Method	Links
GRPO 2025.05		2.8
INTUITOR 2025.05		2.8
Baseline 2025.05		2.3

SOTA Paper

GRPO

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Dataset

LCB

Follow for update

@wizwand_team Discord

Related Benchmarks

Math Reasoning on GSM8K (Accuracy)General Knowledge Reasoning on MMLU Pro (Accuracy)Code Generation on LiveCodeBench (LCB) (Pass@1)Code Reasoning on LiveCodeBench (LCB) v6 Code Generation on LCB (Accuracy)

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs