Noometry

Model comparison

Claude 3.5 Haiku vs Muse Glimmer

Muse Glimmer is the stronger model overall, scoring 41.7 to 29.2 on the Noometry Index.

Last verified . 14 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

Muse Glimmer Meta

41.7

Rank #131 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Muse Glimmer in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Muse Glimmer leads 38.8 to 14.7.
  • The biggest single-benchmark swing is SciCode: 27.4% for Claude 3.5 Haiku and 44.9% for Muse Glimmer.
  • Muse Glimmer has downloadable open weights; the other is API-only.

Side by side

Claude 3.5 HaikuMuse Glimmer
ProviderAnthropicMeta
Noometry Index29.241.7
Released2024-10-222026-08-10
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4915

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

Category by category

Coding Muse Glimmer leads

Claude 3.5 Haiku: 32.9 (#265), Muse Glimmer: 40.4 (#142)

BenchmarkClaude 3.5 HaikuMuse Glimmer
SciCode27.4%44.9%
LMArena Coding12861416
Aider Polyglot28%—
LMArena WebDev—1355
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 28.0 (#95), Muse Glimmer: —

BenchmarkClaude 3.5 HaikuMuse Glimmer
BALROG19.3%—

Reasoning Muse Glimmer leads

Claude 3.5 Haiku: 17.7 (#290), Muse Glimmer: 25.7 (#144)

BenchmarkClaude 3.5 HaikuMuse Glimmer
CritPt0%2.6%
LMArena Hard Prompts12511396
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math Muse Glimmer leads

Claude 3.5 Haiku: 14.7 (#300), Muse Glimmer: 38.8 (#125)

BenchmarkClaude 3.5 HaikuMuse Glimmer
LMArena Math12441417
OTIS Mock AIME 2024-20254.3%—
Omni-MATH22.4%—
LiveBench Math35.5%—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Muse Glimmer leads

Claude 3.5 Haiku: 18.7 (#281), Muse Glimmer: 38.5 (#143)

BenchmarkClaude 3.5 HaikuMuse Glimmer
LMArena Expert12081386
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.8 (#117), Muse Glimmer: —

BenchmarkClaude 3.5 HaikuMuse Glimmer
LMArena Vision1092—
GeoBench34%—

Multilingual Muse Glimmer leads

Claude 3.5 Haiku: 40.0 (#218), Muse Glimmer: 50.5 (#122)

BenchmarkClaude 3.5 HaikuMuse Glimmer
LMArena Non-English12381384
LMArena Chinese12291412
LMArena Russian12531390
LMArena French1264—
LMArena German1237—
LMArena Japanese1175—
LMArena Korean1173—
LMArena Spanish1261—

Instruction Following Muse Glimmer leads

Claude 3.5 Haiku: 62.9 (#234), Muse Glimmer: 72.6 (#135)

BenchmarkClaude 3.5 HaikuMuse Glimmer
LMArena Instruction Following12411375
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context Muse Glimmer leads

Claude 3.5 Haiku: 38.3 (#200), Muse Glimmer: 42.1 (#129)

BenchmarkClaude 3.5 HaikuMuse Glimmer
LMArena Longer Query12611382

Writing & Preference Muse Glimmer leads

Claude 3.5 Haiku: 42.7 (#234), Muse Glimmer: 57.5 (#126)

BenchmarkClaude 3.5 HaikuMuse Glimmer
LMArena Text12551389
LMArena Creative Writing12331339
LMArena Multi-Turn12651399
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Muse Glimmer?

Muse Glimmer is the stronger model overall, scoring 41.7 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or Muse Glimmer better for coding?

Muse Glimmer scores higher on coding benchmarks: 40.4 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and Muse Glimmer share?

14 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Muse Glimmer has 15.

Related comparisons

Go deeper