Meta's Muse Ember matches Claude Haiku 5.5's best score at a third of the cost
Our Smallest, Most Efficient Model: Muse Ember
Meta's smallest model yet, Muse Ember, is built for the repetitive work agents do all day: tool calls, coding subtasks, routing, extraction, and long document parsing. On Artificial Analysis's leaderboard it sits on the efficiency frontier, matching Claude Haiku 5.5's top score at roughly a third of the cost while beating every GPT-6 Luna setting. It handles text, images, audio, and video natively, carries a 1M-token context window, and is available now on the Meta Model API at $0.10 per million input tokens.
For the hardest problems, pair it with Muse Wonder: Muse Wonder plans, Muse Ember handles the volume.
- simonw
Six effort levels (minimal, low, medium, high, xhigh, max), so here are six pelicans (actually five, "high" didn't return a complete SVG):
https://tools.simonwillison.net/markdown-svg-renderer?url=ht...
There's usually a reasonably strong correlation between thinking level and visual quality of the pelican. This is the first time I've seen that correlation appear to break - more reasoning tokens doesn't seem to produce an obviously better SVG.
- djacksondev
When Muse models first started coming out I was pretty excited that Meta models were competitive again based on the benchmarks but after trying them out it feels like Meta is making benchmaxxed models that are exciting on bench cards but not really useful in real world scenarios.
To me that is the main problem with Muse models whether it's Spark, Wonder or Ember. While it reads as frontier on benchmarks it really isn't.
This is evident when you compare Dots and Muse the products as well. The model quality is clearly still far behind.
- doodlesdev
Interesting to notice that the best benchmarks of the model are not on Meta's own agent harness, but instead on mini-swe-agent:
> 1. All models run at max reasoning effort. Artificial Analysis results are from Intelligence Index v5, as published November 9, 2026; cost per task uses each model's list pricing. Internal results are from Meta's evaluation suite. The Personal Superintelligence Index (PSI) is an internal composite of eight evaluations: Agents' Last Exam, AutomationBench, FocusBench, JobBench, OfficeQA Pro, GDP.pdf, GDP.xlsx and VBT. Terminal-Bench 4.0 uses each model's best published harness: mini-swe-agent (Muse Ember), Claude Code (Claude Haiku 5.5), and Codex (GPT-6 Luna). OSWorld 2.1 uses partial-credit reward; PerceptionBench is scored with tools.
- Retro_Dev
When they said the model was the "smallest" of their models yet, I was really hoping it would be open weights. I can't find any weights, how sad :(
- kbrannigan
This is starting to feel just like the early PC days. A bunch of Computer models coming out, all shapes and color, but eventually it settled around mouse keyboard, monitor
most people, use the office suite: Word, Spreadsheet , presentations, database.
I bet we're going to see the exact same thing with LLMs at specialized models instead of the everything models.
One for lawyers, coders, Accountants, Designers, etc…
- open-paren
I believe this is what the “crouton alpha” stealth model was
- minimaxir
> It costs $0.10 per million input tokens, $0.004 per million cached input tokens and $0.50 per million output tokens,
Notable cache cost of 4% input, compared to Luna/Haiku's 10% of input.
- segmondy
What makes it small? Anyone know the size? I don't see it anywhere. Small in relation to their current line up? Anyways, last I tried Meta was llama4. I stepped aside not because of how bad llama4 got, but also because of Zuck's move. Anyone here using Meta? I don't know anyone in my circle using it, but I'm sure folks are using it.