P
promptbench
microsoftarchive/promptbench
A unified evaluation framework for large language models
★2.8kstars
Python
MIT
Updated: 3d ago
📋 Project at a Glance
Tap to expand
What's this?A , built with Python open-source project in the Security & Governance category, core strengths: adversarial-attacks/benchmark
Who made it?Maintained by microsoftarchive team, 2.8K⭐ on GitHub, #85 out of 413 in Security & Governance
Why does it exist?The microsoftarchive team recognized that existing adversarial-attacks tools in Security & Governance were hard to use. promptbench was designed to make benchmark more accessible.
What can it do?Key use cases: chatgpt, evaluation, large-language-models
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/microsoftarchive/promptbench | 官网 http://aka.ms/promptbench
🔗 github.com/microsoftarchive/promptbench | 官网 http://aka.ms/promptbench
Topics
adversarial-attacksbenchmarkchatgptevaluationlarge-language-modelspromptprompt-engineeringrobustness