AI Tools Review

Muse Ember

By Meta

Released: 2026-11-09

LLM
Meta
Paid
New

Muse Ember is Meta's AI model, released 09/11/2026. Meta calls Muse Ember its smallest and most efficient model, built for agent subtasks such as tool calls, coding, routing, extraction and long-document parsing. At max reasoning it beats Claude Haiku 5.5 and GPT-6 Luna on most printed rows but trails Haiku 5.5 on FrontierCode 2.0-AA and ties it on the Artificial Analysis Index. Meta also says it matches Haiku 5.5 on intelligence at about a third of the cost per task.

Visit Muse Ember

AI-Powered

Leverages advanced AI technology to deliver cutting-edge capabilities and results.

Fast & Efficient

Optimized performance ensures quick results without compromising on quality.

Purpose-Built

Specifically designed for llms tasks and workflows.

How does Meta Muse Ember score on independent benchmarks?

Meta Muse Ember ranks #15 of 28 models on the Artificial Analysis Intelligence Index (v5.0.1) with a score of 36, as measured on 22 November 2026.

Intelligence Index
36
AA v5.0.1
Coding Agent Index
39.7
in Muse Code
Cost per task
$0.14
AA Intelligence Index task
Price per 1M tokens
$0.1 / $0.5
input / output

Where does Meta Muse Ember rank against other models?

How good is Meta Muse Ember at agentic coding?

How does Meta Muse Ember do on individual tests?

Evaluation (run by Artificial Analysis)Meta Muse EmberBest of any model
Terminal-Bench 4.040.9%67.2%
FrontierCode 2.027.2%48.8%
Humanity's Last Examn/a74.3%
GDPval-AA (Elo)n/a1866

How has Meta Muse Ember's score changed over time?

We have tracked Meta Muse Ember on Intelligence Index v5.0.1 since 22/11/2026. A point is added each day the score, coding index or price changes, so this chart fills in over time.

What does the Meta Muse Ember system card report?

Meta calls Muse Ember its smallest and most efficient model, built for agent subtasks such as tool calls, coding, routing, extraction and long-document parsing. At max reasoning it beats Claude Haiku 5.5 and GPT-6 Luna on most printed rows but trails Haiku 5.5 on FrontierCode 2.0-AA and ties it on the Artificial Analysis Index. Meta also says it matches Haiku 5.5 on intelligence at about a third of the cost per task.

These are Meta's own published results (self-reported, with the vendor's harness and settings), so they are not directly comparable with other labs' numbers. Sources: Muse Ember Evaluation Report (methodology) (undefined/11/2026), Muse Ember research blog (09/11/2026). Last checked 22/11/2026.

Agents & tool use

BenchmarkMeta Muse EmberClaude Haiku 5.5GPT-6 LunaMuse Spark 1.3
AutomationBench-AAstrict pass@1; max reasoning37.8%13.9%20.2%n/a
Agents' Last Exam (Linux subset)max reasoning; common internal agent loop61.6%57%57.1%n/a
Personal Superintelligence Indexinternal composite of eight evaluations; max reasoning46.8%36.1%37%n/a
OSWorld 2.1 (partial credit)108 workflows; common internal framework; max reasoning69.5%68.9%50.5%n/a
OSWorld 2.1 (binary)strict full-completion rate; max reasoning33.8%27.8%17%n/a

Coding

BenchmarkMeta Muse EmberClaude Haiku 5.5GPT-6 LunaMuse Spark 1.3
Terminal-Bench 4.0best published harness: mini-swe-agent for Ember, Claude Code for Haiku 5.5, Codex for GPT-6 Luna; max reasoning40.9%39.2%16.4%n/a
Coding Agent Index-AAArtificial Analysis; Muse Code for Ember, Claude Code for Haiku 5.5, Codex for Luna46 points3731n/a
FrontierCode 2.0-AAArtificial Analysis private 132-task set; max reasoning27.2%34.9%25.2%n/a

Multimodal

BenchmarkMeta Muse EmberClaude Haiku 5.5GPT-6 LunaMuse Spark 1.3
GDP.pdf-AAall-pass share of answers meeting every rubric criterion; Artificial Analysis22.8%20.8%22.8%n/a
PerceptionBench3,000 questions, with tools; pass@180.6%78.6%62.8%n/a

Other

BenchmarkMeta Muse EmberClaude Haiku 5.5GPT-6 LunaMuse Spark 1.3
Artificial Analysis Intelligence Indexmax reasoning; v536 points362837

What did safety testing find for Meta Muse Ember?

Safety level: Meta Superintelligence Scaling Framework: below the framework's high-risk thresholds in the categories assessed (chemical and biological, cybersecurity, loss of control); no named risk level published

  • Meta states it was evaluated under the Meta Superintelligence Scaling Framework for chemical and biological, cybersecurity and loss-of-control risks and remained below the high-risk thresholds.
  • Received the same core safety training and testing as the larger Muse models.
  • Behavioural evaluations covered respecting user intent, handling sensitive information, resisting hidden instructions in web pages, documents and tool outputs, and seeking human input before high-impact actions.
  • Muse Ember is the first model trained using Muse Wonder Full.
  • The blog gives no numeric safety scores; the published evaluation report covers capability methodology only.

Independent figures: Artificial Analysis, refreshed daily on our AI model benchmarks page. Full analysis: our Meta Muse Ember deep dive.

Meta Model Timeline

Muse EmberCurrent

1M tokens input; up to 512K output tokens context

Muse Wonder Full

1M tokens at inference context

Muse Wonder

1M tokens at inference context

Specifications

pricing$0.1/$0.5 per 1M tokens (input/output)
context Window1M tokens input; up to 512K output tokens