Muse Glimmer 30B

Meta's Muse Glimmer 30B is a dense, open-weight multimodal model distilled from Muse Spark for long-horizon agents and coding workflows. It supports multi-step reasoning, reliable tool use, failure recovery, image understanding, and more than 100 languages.

  • Reasoning
  • Vision
  • Tool Calling
  • Structured Output

Added Aug 11, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.35
Output
$1.50
Cache read
$0.040
Compare provider prices

Specifications

Context window
131.1K
Max output
131.1K
Parameters
30B
Avg output (7d)
359 tokens
Longer than 32% of models

Benchmarks

Sourced from Artificial Analysis.

Intelligence Index

17.5

Better than 64% of models compared

Coding Index

49.0

Better than 56% of models compared

Agentic Index

8.5

Better than 42% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

6.8%

Better than 32% of models compared

AutomationBench-AA Tasks Completed

Fully completed workflows without guardrail violations

0.8%

Better than 7% of models compared

AA-Briefcase

Agentic knowledge work (Elo)

477 Elo

Better than 22% of models compared

GDPval-AA v2

Economically valuable tasks (Elo)

790 Elo

Better than 36% of models compared

Document reasoning

GDP.pdf

Professional PDF reasoning: all-pass rate

10.0%

Better than 40% of models compared

AA-LCR v1.1

Long context reasoning with updated grading

83.3%

Better than 96% of models compared

MLCR-AA

Medical long-context reasoning

20.0%

Better than 68% of models compared

Reasoning

HLE

Humanity's Last Exam

22.0%

Better than 69% of models compared

CritPt

Research-level physics reasoning

2.6%

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

0.5%

Better than 35% of models compared

SciCode

Python programming for scientific computing

44.9%

Better than 38% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

27.0%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

81.9%

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

83.5%

Better than 74% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

83.3%

Better than 96% of models compared

GDPval-AA (unversioned / legacy)

Economically valuable tasks

14.5%

Last updated Oct 10, 2026

Artificial Analysis

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Loading provider options…