Organization
Chatbot Arena
2 stories · sorted newest first · 📡 RSS
Chatbot Arena's Unique Approach to LLM Evaluation Called into Question
Recent concerns about Chatbot Arena's reliance on user preference for ranking large language models may undermine its credibility
BigCodeArena: Open Human Evaluation Platform for Assessing AI-Generated Code Quality
Researchers introduce BigCodeArena, an open platform enabling real-time assessment of LLM-generated code quality through execution