Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

reference performance of AI models on coding tasks #278

Open
monperrus opened this issue Mar 21, 2025 · 6 comments
Open

reference performance of AI models on coding tasks #278

monperrus opened this issue Mar 21, 2025 · 6 comments

Comments

@monperrus
Copy link
Contributor

monperrus commented Mar 21, 2025 •
edited
Loading

we copy-paste notable coding leaderboard snapshots, with source

this will be useful to argue for the choice of models in our future papers.
@monperrus
Copy link
Contributor Author

LMarena coding March 21 2025

Image

@monperrus
Copy link
Contributor Author

LiveCodeBench code generation March 21 2025

Image

@monperrus
Copy link
Contributor Author

RepairBench 21 March 2025

Image

@monperrus
Copy link
Contributor Author

CodeArena: A Collective Evaluation Platform for LLM Code Generation
https://arxiv.org/pdf/2503.01295

tldr: This work introduces CodeArena, an online evaluation framework tailored for LLM code generation, which dynamically recalibrates individual model scores based on the holistic performance of all participating models, mitigating score biases caused by widespread benchmark leakage.

Image

@monperrus
Copy link
Contributor Author

BigCode leaderboard (HumanEval benchmark and MultiPL-E.) March 25 2025

Image

@monperrus
Copy link
Contributor Author

BigO(Bench) Leaderboard https://facebookresearch.github.io/BigOBench/leaderboard.html

Image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@monperrus