Stop Trusting AI Benchmarks. Run Your Own.
中文摘要
别再迷信AI基准测试了。我开发了一个跨平台评估仪表板，通过LLM作为评委的方法，对13个前沿模型进行测试与评分。
English Summary
Stop relying on AI benchmarks. I built a platform-agnostic dashboard that evaluates 13 frontier models using LLM-as-judge scoring.
原文节选
I built a platform-agnostic AI Evaluation dashboard that tests 13 frontier models with LLM-as-judge scoring. Continue reading on Medium »