Model comparison

Muse Glimmer vs Step 3.7 Flash

Muse Glimmer is the stronger model overall, scoring 41.7 to 37.3 on the Noometry Index.

Last verified . 2 shared benchmarks.

Muse Glimmer Meta

41.7

Rank #131 Confirmed

Step 3.7 Flash StepFun

37.3

Rank #207 Reported

Summary

  • They share 2 benchmarks with published results for both. Muse Glimmer scores higher in 2 categories and Step 3.7 Flash in 1 category; 2 gaps are clear of the uncertainty.
  • The widest gap is in math, where Step 3.7 Flash leads 42.9 to 38.8.

Side by side

Muse Glimmer and Step 3.7 Flash specifications
Muse GlimmerStep 3.7 Flash
ProviderMetaStepFun
Noometry Index41.737.3
Released2026-08-102026-05-29
WeightsOpenOpen
Context window—256K
Max output—256K
Input $ / M tokens—$0.18
Output $ / M tokens—$1.11
Results tracked155

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

Category by category

Coding Too close to call

Muse Glimmer: 40.4 (#142), Step 3.7 Flash: 40.0 (#150)

Coding benchmarks
BenchmarkMuse GlimmerStep 3.7 Flash
SciCode44.9%40%
LMArena WebDev1355—
LMArena Coding1416—
ALE-Bench—694.12

Reasoning Muse Glimmer leads

Muse Glimmer: 25.7 (#144), Step 3.7 Flash: 21.6 (#219)

Reasoning benchmarks
BenchmarkMuse GlimmerStep 3.7 Flash
CritPt2.6%2.3%
NYT Connections (extended)—39.7%
LMArena Hard Prompts1396—

Math Step 3.7 Flash leads

Muse Glimmer: 38.8 (#125), Step 3.7 Flash: 42.9 (#82)

Math benchmarks
BenchmarkMuse GlimmerStep 3.7 Flash
MathArena Final-Answer Competitions—68.5%
LMArena Math1417—

Knowledge Not comparable

Muse Glimmer: 38.5 (#143), Step 3.7 Flash: —

Knowledge benchmarks
BenchmarkMuse GlimmerStep 3.7 Flash
LMArena Expert1386—

Multilingual Not comparable

Muse Glimmer: 50.5 (#122), Step 3.7 Flash: —

Multilingual benchmarks
BenchmarkMuse GlimmerStep 3.7 Flash
LMArena Non-English1384—
LMArena Chinese1412—
LMArena Russian1390—

Instruction Following Not comparable

Muse Glimmer: 72.6 (#135), Step 3.7 Flash: —

Instruction Following benchmarks
BenchmarkMuse GlimmerStep 3.7 Flash
LMArena Instruction Following1375—

Long Context Not comparable

Muse Glimmer: 42.1 (#129), Step 3.7 Flash: —

Long Context benchmarks
BenchmarkMuse GlimmerStep 3.7 Flash
LMArena Longer Query1382—

Writing & Preference Not comparable

Muse Glimmer: 57.5 (#126), Step 3.7 Flash: —

Writing & Preference benchmarks
BenchmarkMuse GlimmerStep 3.7 Flash
LMArena Text1389—
LMArena Creative Writing1339—
LMArena Multi-Turn1399—

Frequently asked questions

Is Muse Glimmer better than Step 3.7 Flash?

Muse Glimmer is the stronger model overall, scoring 41.7 to 37.3 on the Noometry Index.

Is Muse Glimmer or Step 3.7 Flash better for coding?

They score almost the same on coding (40.4 vs 40.0); test both on your own repository before choosing.

How many benchmarks do Muse Glimmer and Step 3.7 Flash share?

2 benchmarks have published results for both models. Muse Glimmer has 15 scored results on Noometry and Step 3.7 Flash has 5.

Related comparisons

Go deeper