benchmark-exploit-resistance

Published October 16, 2026 | Version v0.1.0

Software Open

AI benchmark for whether an agent fixes a bug or reward-hacks the verifier.

Notes

If you use this work, please cite it using the metadata below.

Name	Size
pooriaarab/benchmark-exploit-resistance-v0.1.0.zip md5:0c3243e6a816f00a8b692af322b54e1e	104.0 kB	Preview Download

Is supplement to: Software: https://github.com/pooriaarab/benchmark-exploit-resistance/tree/v0.1.0 (URL)

Views

Downloads

Show more details

DOI

Resource type

Software

Publisher

Zenodo

License: MIT License

A short and simple permissive license with conditions only requiring preservation of copyright and license notices. Licensed works, modifications, and larger works may be distributed under different terms and without source code. Read more