Muse Ember: benchmarks, price and rank
Muse Ember from Meta is 18th of 123 rated AI models on Spezia's leaderboard. It costs $0.10 in, $0.50 out per million tokens.
- 18th of 123 rated models
- Rating 1,654
- Rated on 5 benchmarks
- Closed
- Released Nov 9, 2026
- 1 million tokens of context
Where it is strongest
Not in the top tenth on any benchmark in use.
Where it falls behind
- 6th of 6 on OSWorld 2.1
- 12th of 17 on Terminal-Bench 4.0
Price: $0.10 in, $0.50 out per million tokens.
Its headline results
The benchmarks that count most in the rating, with its place among the models measured the same way, and where each number came from.
- APEX-Agents64.3%
Long tasks written by investment banking analysts, management consultants and corporate lawyers from their own work, done across files and apps in a realistic work setup.
15th of 56. Independent result from Epoch AI.
- Terminal-Bench 4.040.9%
Hard jobs done in a real computer terminal: building and fixing software, setting up systems, and science and engineering problems.
12th of 17. The maker's own number, from Meta, via LLM Stats.
- OSWorld 2.133.8%
The newer version of OSWorld, with longer desktop tasks that are graded at several checkpoints along the way.
6th of 6. The maker's own number, from Meta, via LLM Stats.
- SimpleBench72.7%
Multiple-choice puzzles about everyday situations, space, time and people, written to trip up models that pattern-match instead of think. Ordinary adults do well on them.
21st of 68. Independent result from Epoch AI.
- LMArena WebDev1,609
People ask two anonymous models to build the same web page or app and vote for the better one.
25th of 98. Independent result from LMArena.
Its full profile is in Spezia.
Every result with its source, what it costs per task, what jumped with its release, side by side with any other model, and answers to your questions about when to use it.
Models ranked near it
How the rating works, and every benchmark it uses: the model leaderboard.