# BigCodeArena: Judging code generations end to end with code executions

DevFeed: [BigCodeArena: Judging code generations end to end with code executions](<https://devfeed.tech/articles/bigcodearena-judging-code-generations-end-to-end-with-code-executions-7130.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/bigcode/arena>)

Author: Terry Yue Zhuo

Published: 2025-10-07T09:37:25Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [Code generation](<https://devfeed.tech/topics/code-generation.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Programming](<https://devfeed.tech/topics/programming.md>), [React](<https://devfeed.tech/topics/react.md>), [JavaScript](<https://devfeed.tech/topics/javascript.md>), [Python](<https://devfeed.tech/topics/python.md>)

Tags: [code-generation](<https://devfeed.tech/tags/code-generation.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [leaderboard](<https://devfeed.tech/tags/leaderboard.md>), [llms](<https://devfeed.tech/tags/llms.md>), [python](<https://devfeed.tech/tags/python.md>), [react](<https://devfeed.tech/tags/react.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>), [typescript](<https://devfeed.tech/tags/typescript.md>)

## AI overview

BigCodeArena is a platform for comparing code-generation models side by side by executing their outputs and letting users vote on the better result. It addresses limitations of static benchmarks and human review by providing execution feedback in isolated sandboxes, interactive testing, visual output, and community leaderboards.

## Source excerpt

Inspired by LMArena for LLMs, we've built a platform that allows anyone to compare code generation models side-by-side, but with a crucial difference: you can actually run the code and see what it produces. Just submit a coding task, watch two different models generate solutions, execute both programs, and vote on which model produced better results. The outcomes are organized into a leaderboard that displays the community's highest-rated models.