'Every single candidate chose Claude': researcher notes 100% tool preference in agentic evaluations
RylanSchaeffer · x · 2026-11-19
Rylan Schaeffer shares an interesting observation: across all their candidates, who were free to use whatever agentic tools they wanted, 100% chose Claude.
A small but telling data point on Claude's real-world pull among heavy agent users.
More from Models
- Microsoft's 'can you trust open weights?' FUD slide mocked as 7 new MAI models land — victormustar · 2026-11-19
- DevOps user slams 6.2-astra as the worst model ever: 'total gibberish' — rickasaurus · 2026-11-19
- Counter-take to "LLs have peaked": new models much better at long-horizon tasks — minhnguyen · 2026-11-19
- Adaption powers inference for AI Singapore's SEA-LION sovereign models — sarahookr · 2026-11-19
- Astra 6.2 hands-on: rambling about an idea yields a working app — kagigz · 2026-11-19
- Every's Vibe Check: GPT-6.2 Astra and Sol handle bounded tasks but fall short on judgment — danshipper · 2026-11-19