There’s a gap between how models benchmark and how they FEEL in real-world knowledge work. Our research team wanted to study the latter, so they created the Notion Knowledge Board: live, anonymized traffic scored by an ensemble judge built with researchers at Anthropic and OpenAI. TLDR: — Real work is messier than benchmarks — Open and closed models both have their place — Fast models can also be capable http://labs.notion.com/knowledge-board