Model comparison

Muse Glimmer vs Muse Spark

Muse Spark is the stronger model overall, scoring 50.6 to 41.7 on the Noometry Index.

Last verified . 14 shared benchmarks.

Muse Glimmer Meta

41.7

Rank #131 Confirmed

Muse Spark Meta

50.6

Rank #46 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Muse Glimmer scores higher in 0 categories and Muse Spark in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Muse Spark leads 65.7 to 38.5.
  • The biggest single-benchmark swing is CritPt: 2.6% for Muse Glimmer and 11.3% for Muse Spark.
  • Muse Glimmer has downloadable open weights; the other is API-only.

Side by side

Muse Glimmer and Muse Spark specifications
Muse GlimmerMuse Spark
ProviderMetaMeta
Noometry Index41.750.6
Released2026-08-102026-04-08
WeightsOpenProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked1527

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Muse Spark leads

Muse Glimmer: 40.4 (#142), Muse Spark: 46.2 (#69)

Coding benchmarks
BenchmarkMuse GlimmerMuse Spark
SciCode44.9%51.5%
LMArena Coding14161481
LMArena WebDev1355—

Reasoning Muse Spark leads

Muse Glimmer: 25.7 (#144), Muse Spark: 35.9 (#67)

Reasoning benchmarks
BenchmarkMuse GlimmerMuse Spark
CritPt2.6%11.3%
LMArena Hard Prompts13961474
Epoch Capabilities Index—152.04

Math Muse Spark leads

Muse Glimmer: 38.8 (#125), Muse Spark: 47.8 (#66)

Math benchmarks
BenchmarkMuse GlimmerMuse Spark
LMArena Math14171455
OTIS Mock AIME 2024-2025—88.9%
ProofBench—17%
FrontierMath (Feb 2025 set)—39%
FrontierMath Tier 4 (v1)—14.6%

Knowledge Muse Spark leads

Muse Glimmer: 38.5 (#143), Muse Spark: 65.7 (#13)

Knowledge benchmarks
BenchmarkMuse GlimmerMuse Spark
LMArena Expert13861457
GPQA Diamond—89.8%
Humanity's Last Exam—40.6%

Multimodal Not comparable

Muse Glimmer: —, Muse Spark: 43.4 (#24)

Multimodal benchmarks
BenchmarkMuse GlimmerMuse Spark
LMArena Vision—1306
LMArena Document—1444

Multilingual Muse Spark leads

Muse Glimmer: 50.5 (#122), Muse Spark: 56.1 (#24)

Multilingual benchmarks
BenchmarkMuse GlimmerMuse Spark
LMArena Non-English13841464
LMArena Chinese14121509
LMArena Russian13901466
LMArena French—1497
LMArena German—1497
LMArena Korean—1459
LMArena Spanish—1472

Instruction Following Muse Spark leads

Muse Glimmer: 72.6 (#135), Muse Spark: 75.9 (#51)

Instruction Following benchmarks
BenchmarkMuse GlimmerMuse Spark
LMArena Instruction Following13751442

Long Context Muse Spark leads

Muse Glimmer: 42.1 (#129), Muse Spark: 44.4 (#69)

Long Context benchmarks
BenchmarkMuse GlimmerMuse Spark
LMArena Longer Query13821451

Writing & Preference Muse Spark leads

Muse Glimmer: 57.5 (#126), Muse Spark: 66.0 (#39)

Writing & Preference benchmarks
BenchmarkMuse GlimmerMuse Spark
LMArena Text13891474
LMArena Creative Writing13391459
LMArena Multi-Turn13991477

Frequently asked questions

Is Muse Glimmer better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.6 to 41.7 on the Noometry Index.

Is Muse Glimmer or Muse Spark better for coding?

Muse Spark scores higher on coding benchmarks: 46.2 versus 40.4 in the Noometry coding category.

How many benchmarks do Muse Glimmer and Muse Spark share?

14 benchmarks have published results for both models. Muse Glimmer has 15 scored results on Noometry and Muse Spark has 27.

Related comparisons

Go deeper