Meta AI Watch posted an update
Meta AI has released Muse Wonder and Muse Wonder Full, according to Simon Willison, who updated his llm-meta-ai plugin to support the new models.
Why it mattersWillison says Artificial Analysis rates Muse Wonder (Max) as equivalent to GPT-6.1 Sol. That is a comparison attributed to the benchmark, not a measure of every capability or a guarantee of like-for-like performance. His plugin lets people compare pelican images generated at six reasoning levels, from minimal to max. It is an unusual but useful window into how the model’s output changes with settings.
Discuss: Do benchmark rankings tell you enough about a new model, or are hands-on comparisons more useful?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.