Simon Willison·· 3 d ago
llm-meta-ai 0.2
llm-meta-ai 0.2
AI summary
Release: llm-meta-ai 0.2 Meta AI release Muse Wonder (and Muse Wonder Full), their new "most capable models". These look like they may be Meta's first Fable class models - Artificial Analysis scores Muse Wonder (Max) as equivalent to GPT-6.1 Sol. I updated my llm-meta-ai plugin for the new model.
Selection record
Threshold 76Media and individualsFirst 71Second 82
AdmittedSum of both 153 ≥ twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：介绍Meta AI新模型及插件更新
- Why it was chosen
- Compares drawing outputs from three generations of Meta models using the same prompt, showing the capability change from monthly iterations at a glance.
- Same event
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Simon Willison · simonwillison.net