AI快讯 / AI 开源项目

vals-ai

Vals AI is an independent AI model evaluation company that publishes private, domain-specific benchmarks in legal, tax, finance, medical, and coding domains, and operates the Vals Platform - scalable evaluation infrastructure that lets labs and engineering teams build test suites, run LLM evaluations with LLM-as-judge and expert review, and wire…

原文来源AI 开源 Releases
查看官方原文

Vals AI is an independent AI model evaluation company that publishes private, domain-specific benchmarks in legal, tax, finance, medical, and coding domains, and operates the Vals Platform - scalable evaluation infrastructure that lets labs and engineering teams build test suites, run LLM evaluations with LLM-as-judge and expert review, and wire…