O
openbench
minghinmatthewlam/openbench
Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open models on correctness, speed, and token cost
★97stars
G-code
MIT
Updated: 2w ago
📋 Project at a Glance
Tap to expand
What's this?A open-source Security & Governance project, built with G-code, focusing on ai-agents and benchmark
Who made it?Maintained by minghinmatthewlam team, 97⭐ on GitHub, #299 out of 413 in Security & Governance
Why does it exist?With the growing demand for ai-agents and benchmark in Security & Governance, minghinmatthewlam created openbench as a streamlined solution.
What can it do?Key use cases: coding-agents, evals, llm
How to install with AI?Use an AI coding assistant to follow the README and automatically handle the install and environment setup.
🔗 github.com/minghinmatthewlam/openbench
🔗 github.com/minghinmatthewlam/openbench
Topics
ai-agentsbenchmarkcoding-agentsevalsllmopen-models