MetaReleased Aug 10, 2026
Open weights

Muse Glimmer

Its best results are in Computer Use (#89 of 186) and Academic Reasoning (#111 of 223); weakest in Programmatic Reasoning (#117 of 187). Abstract Reasoning and Mathematical Reasoning are estimated, because no results are published yet.

Composite IQ ?
105
#106 of 186 ranked models · ahead of 43%
Meta's #8 model, behind Muse Wonder Full (133)
Effective cost
$0.563/1M
$0.33 in · $1.35 out
Speed
107tok/s
24s typical response
Context
128Ktokens
128,000 tokens in
Evidence
5of 7 dims
15 of 39 benchmarks

IQ profile

Seven dimensions, averaged equally into Composite IQ
Compare shape with
100 avg human130160● Abstract88#133 · est.● Math94#154 · est.● Academic119#111● Coding104#117● Computer Use112#89● Reliability112#94● Knowledge Work109#96
MeasuredEstimated95% range
#1 in dimensionTop-10 median

IQ dimensions

Ranks are among models scored in each dimension. Ranges are model-based estimates, not calibrated confidence intervals.

DimensionIQPosition · 70–160RankEvidencevs Top 10
88estimated
#133 / 221
0/5
-44.5
94estimated
#154 / 186
0/5
-55.5
119measured
#111 / 223
5/6
-16
104measured
#117 / 187
1/6
-47
112measured
#89 / 186
1/5
-34.5
112measured
#94 / 188
2/6
-23.5
109measured
#96 / 186
6/6
-23
Muse Glimmer95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

15 of 39 Composite IQ benchmarks have a published result for Muse Glimmer. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 88 · estimatedNo published results0/5
No published results yet for Abstract Reasoning. The 88 shown is estimated from Muse Glimmer's other dimensions and will be replaced as results come in. How estimates work
ARC-AGI-3ARC-AGI-2ARC-AGI-1Chess PuzzlesMystery Game Puzzles
Mathematical Reasoning IQ 94 · estimatedNo published results0/5
No published results yet for Mathematical Reasoning. The 94 shown is estimated from Muse Glimmer's other dimensions and will be replaced as results come in. How estimates work
FrontierMath Tier 4FrontierMath Tier 1-3ProofBench 1.1MathArenaAIME
Academic Reasoning IQ 119 · measuredBest: #92 of 167 on SciCode5/6
BenchmarkScorePercentileRankLeader · source
SciCode
Artificial Analysis v4.3.2 · Oct 27
44.9%
#92 / 167
Leader opus-5.5 · 66.9%
Artificial Analysis v4.3.2 · Oct 27
GPQA Diamond
Artificial Analysis v5.0.1 · Nov 13
83.5%
#90 / 147
Leader gpt-6-astra · 96.1%
Artificial Analysis v5.0.1 · Nov 13
CritPt
Artificial Analysis v4.3.2 · Oct 27
2.6%
#101 / 159
Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27
MMMU-Pro
Artificial Analysis v5.0.1 · Nov 13
74.3%
#59 / 90
Leader fable-5.1 · 90.6%
Artificial Analysis v5.0.1 · Nov 13
Humanity's Last Exam
Artificial Analysis v4.3.2 · Oct 27
22.0%
#114 / 167
Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
MMLU-Pro
Programmatic Reasoning IQ 104 · measuredBest: #71 of 109 on Terminal-Bench 4.01/6
BenchmarkScorePercentileRankLeader · source
Terminal-Bench 4.0
Artificial Analysis v5.0.1 · Nov 13
0.5%
#71 / 109
Leader Kimi K3.1 Pro · 67.2%
Artificial Analysis v5.0.1 · Nov 13
Not yet reported
LiveCodeBenchIOI V2ProgramBenchSWE-rebenchMirrorCode
Computer Use IQ 112 · measuredBest: #19 of 24 on OSWorld-Verified1/5
BenchmarkScorePercentileRankLeader · source
OSWorld-Verified
Full source leaderboard reconciliation · Oct 23
65.9%
#19 / 24
Leader fable-5 · 85.0%
Full source leaderboard reconciliation · Oct 23
Not yet reported
BrowseCompMCP AtlasArena.ai Agent ArenaAgents' Last Exam
Reliability IQ 112 · measuredBest: #14 of 154 on AA Long Context Reasoning v1.12/6
BenchmarkScorePercentileRankLeader · source
AA Long Context Reasoning v1.1
Artificial Analysis v4.3.2 · Oct 27
83.3%
#14 / 154
Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27
AA Omniscience
Artificial Analysis v4.3.2 · Oct 27
-32.8
#127 / 158
Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
SimpleQA VerifiedBullshitBench v2IFBenchFACTS Grounding
Knowledge Work IQ 109 · measuredBest: #67 of 111 on GDP.pdf6/6
BenchmarkScorePercentileRankLeader · source
GDP.pdf
Artificial Analysis v5.0.1 · Nov 13
10.0%
#67 / 111
Leader Muse Wonder Full · 32.6%
Artificial Analysis v5.0.1 · Nov 13
AutomationBench-AA
Artificial Analysis v5.0.1 · Nov 13
6.8%
#75 / 112
Leader Gemini 4 Carbon · 77.8%
Artificial Analysis v5.0.1 · Nov 13
GDPval-AA v2.1 normalized score
Artificial Analysis v4.3.2 · Oct 23
14.1%
#90 / 124
Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 23
AA-Briefcase v1.1 Elo
Artificial Analysis v5.0.1 · Nov 13
478
#94 / 116
Leader sonnet-5.5 · 1,816
Artificial Analysis v5.0.1 · Nov 13
EnterpriseOps-Gym-AA
Artificial Analysis v1117-task-strict-2026-09-29 · Oct 15
34.7%
#27 / 31
Leader fable-5 · 51.1%
Artificial Analysis v1117-task-strict-2026-09-29 · Oct 15
AA-AnalystAgent
Artificial Analysis vpass^5-2026-09-29 · Oct 15
20.0%
#31 / 35
Leader gemini-3.7-flash · 60.0%
Artificial Analysis vpass^5-2026-09-29 · Oct 15

Release & availability

Facts from the publisher's announcement and documentation.

Released
Developer
Meta
Access
Open weights for local deployment
Weights
Open weightsDownloadable and self-hostable
Inputs
textimage
Context
128,000 tokens
API price
$0.33 in · $1.35 outper 1M tokens · full pricing

What Meta says

  • Muse Glimmer is a 30B dense agentic model with an integrated 1.8B-parameter vision encoder.
  • Meta released it under the Apache 2.0 license.

Limitations

  • The initial release has a 128k-token context window before optional extension.

Publisher statements, not AI IQ measurements.

About this score

How much of Muse Glimmer's IQ is measured, and how the rest is estimated.

15/ 39benchmark results
5/ 7dimensions measured
2estimated
0/5Abstract
0/5Math
5/6Academic
1/6Coding
1/5Computer Use
2/6Reliability
6/6Knowledge Work
Bar height = share of benchmarks with resultsEstimatedNo score
Measured results are shown as published

Every score in the benchmark tables comes from its source unchanged. Composite IQ averages all seven dimensions equally.

Estimates fill the gaps

Abstract Reasoning and Mathematical Reasoning have no published results yet, so their IQ is estimated from Muse Glimmer's other dimensions.

A missing result is not a zero

Benchmark versions and evaluation harnesses can differ between sources, so small gaps between models may not be meaningful.

Read the scoring methodology →

Compare Muse Glimmer

Side-by-side pages for the models it is most often weighed against.

Muse GlimmerComparison model
Browse all comparisons →

Frequently asked questions

Quick answers about Muse Glimmer, drawn from the same data as the rest of this page.

How AI IQ scores models →Get this data from the API →
What is the IQ of Muse Glimmer?
Muse Glimmer has an estimated IQ of 105, which ranks #106 out of 186 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
What is Muse Glimmer best at?
Among the dimensions with published benchmark results, Muse Glimmer ranks highest in Computer Use (IQ 112, #89 of 186) and Academic Reasoning (IQ 119, #111 of 223). Its lowest-ranked measured dimension is Programmatic Reasoning (IQ 104, #117 of 187).
What is the EQ of Muse Glimmer?
Muse Glimmer doesn't have an EQ score yet. EQ (emotional reasoning) is calculated from EQ-Bench 4 and AttuneBench, and neither has published a result for Muse Glimmer. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has Muse Glimmer been tested on?
Muse Glimmer has published results on 15 of the 39 benchmarks behind AI IQ's Composite IQ, including AA Long Context Reasoning v1.1, SciCode, GDP.pdf, GPQA Diamond and CritPt.
How much does Muse Glimmer cost?
Muse Glimmer costs $0.325 per million input tokens and $1.35 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $0.5627 per million input-plus-output tokens.
Is Muse Glimmer open source?
Yes — Muse Glimmer is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
Who developed Muse Glimmer?
Muse Glimmer was developed by Meta, based in the United States.
When was Muse Glimmer released?
Muse Glimmer was publicly released on August 10, 2026.
How large is the context window of Muse Glimmer?
Muse Glimmer supports a context window of 128,000 tokens — the amount of text it can consider in a single request.
How fast is Muse Glimmer?
In independent measurements, Muse Glimmer generates about 107 tokens per second, with a typical response time of about 24 seconds.