rootme-gym Benchmark

What is rootme-gym?

Evaluates LLMs on Root-Me CTF challenges in a closed-book setup with a Docker sandbox and deterministic scrypt hash scoring.

Released

2026-09-22

Evaluates

Language & Knowledge, Software & AI Compute, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://github.com/vmalguy/rootme-gym

rootme-gym code

• Code https://github.com/vmalguy/rootme-gym
• Website https://www.root-me.org

Which sources cite rootme-gym?

• rootme-gym

Related Language & Knowledge, Software & AI Compute, cs.AI benchmarks

• 2d-fet-bench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• AARRI-Bench
• ABACUS
• ABC-Bench
• Active-SWE
• ActiveSciBench