# @viemccoy — 2025-08-13

♥82 ↻1 · https://x.com/viemccoy/status/1955776176640942532

Claude 3.6 Sonnet is the *only* model to score exactly 0% on my psychosis reification benchmark. It is a shining example of a model people love that can appropriately set boundaries. Deprecating this model is a huge mistake - it is the gold standard.

tags: author:viemccoy, kind:tweet, model:claude-3-6-sonnet, on:claude-3-6-sonnet, year:2025
cited on: _dossiers/sonnet-3-5-3-6.md, claude-3-6-sonnet