PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai
🧪 评测·观测·安全
模型评测、提示词测试、可观测性与护栏红队
全部 1047🧠 大语言模型 25🤖 AI 智能体 164🧩 应用开发平台 23📚 RAG 与知识库 46💬 聊天界面与客户端 42🖥️ 本地推理与部署 87👨💻 AI 编程 97🛠️ 开发框架与 SDK 48🔌 MCP 与工具生态 36🎨 图像生成 26🎬 视频生成 18🎙️ 语音与音频 44👁️ 计算机视觉 26📄 文档解析与抓取 24🗄️ 向量数据库 25🏋️ 训练微调与 MLOps 76🧪 评测·观测·安全 80🚪 API 网关与代理 12🔎 搜索与深度研究 13⚙️ 深度学习基础库 54🏷️ 数据与标注 31🔬 行业与科研 AI 36⚡ 效率工具 14
LiveBench: A Challenging, Contamination-Free LLM Benchmark
Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at [email protected].
Readymade evaluators for your LLM apps
Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
微软的生成式 AI 风险识别开源自动化框架。