Local Model Bench — Full Leaderboard

Static leaderboard. All 40 models that completed the current v1 paperwork suite. Practical Score = 50%% resolved cases + 50%% core passes. Local LM Studio runs were executed on a Mac mini M4 with 64 GB unified memory. Generated 2026-09-27T17:53:49Z.

The full leaderboard table is rendered as a static HTML page (Ghost's Lexical sanitizer strips <table>). Open it here: