RVCBench

openevals 开源

几行代码给 LLM 应用打分，快速比出哪个版本更好

Readymade evaluators for your LLM apps

next-evals-oss 开源

给 AI 出 Next.js 考题，看它到底会不会写

Evals for Next.js up to 15.5.6 to test AI model competency at Next.js

llamator 开源

给聊天机器人找茬，提前揪出安全漏洞

Red Teaming python-framework for testing chatbots and GenAI systems.

lmms-eval 开源

一套工具搞定文本/图像/视频/音频模型评测，结果可复现

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

rag-arena 开源

让用户投票，选出最好的 RAG 系统

Open-source RAG evaluation through users' feedback

Jailbreak-Foundry 开源

把越狱论文变成可跑的攻击测试，实时更新基准

A system that turns jailbreak papers into runnable attacks and benchmarks — live, a···

deepteam 开源

自动模拟越狱攻击，提前测出 LLM 安全漏洞

DeepTeam is a framework to red team LLMs and AI agents.

Gym 开源

把模型丢进环境里跑，边评测边改进智能体

Evaluate and improve models and agents using environments

LLMEvaluation 开源

选对 LLM 评测方法，少走弯路

A comprehensive guide to LLM evaluation methods designed to assist in identifying th···