Noometry

Model comparison

Muse Spark vs o4-mini

Muse Spark is the stronger model overall, scoring 50.6 to 41.6 on the Noometry Index.

Last verified . 24 shared benchmarks.

Muse Spark Meta

50.6

Rank #46 Confirmed

o4-mini OpenAI

41.6

Rank #132 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Muse Spark scores higher in 8 categories and o4-mini in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Muse Spark leads 65.7 to 43.6.
  • The biggest single-benchmark swing is Humanity's Last Exam: 40.6% for Muse Spark and 18.1% for o4-mini.

Side by side

Muse Sparko4-mini
ProviderMetaOpenAI
Noometry Index50.641.6
Released2026-04-082025-04-16
WeightsProprietaryProprietary
Context window—200K
Max output—100K
Input $ / M tokens—$1.10
Output $ / M tokens—$4.40
Results tracked2760

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

Category by category

Coding Muse Spark leads

Muse Spark: 46.2 (#69), o4-mini: 40.9 (#127)

BenchmarkMuse Sparko4-mini
LMArena Coding14811368
SWE-bench Verified (bash only)—45%
Aider Polyglot—72%
SciCode51.5%—
GSO—3.6%
WeirdML—52.6%
CadEval—62%
ALE-Bench—826.17
AlgoTune—1.72

Agentic & Tool Use Not comparable

Muse Spark: —, o4-mini: 32.6 (#61)

BenchmarkMuse Sparko4-mini
Berkeley Function Calling Leaderboard—53.2%
GDPval—25.3%
METR Time Horizons—63.9%

Reasoning Muse Spark leads

Muse Spark: 35.9 (#67), o4-mini: 24.6 (#162)

BenchmarkMuse Sparko4-mini
CritPt11.3%0.6%
LMArena Hard Prompts14741351
Epoch Capabilities Index152.04145.64
ARC-AGI-2—6.1%
SimpleBench—38.7%
Kagi LLM Benchmark—67.6%
ARC-AGI-1—58.7%
Chess Puzzles—26%
EnigmaEval—9.2%
Mystery Game Puzzles—5%
DTBench—77.6%
LMCA—26.5%
ForecastBench—61.8

Math Muse Spark leads

Muse Spark: 47.8 (#66), o4-mini: 40.8 (#89)

BenchmarkMuse Sparko4-mini
OTIS Mock AIME 2024-202588.9%81.7%
LMArena Math14551389
FrontierMath (Feb 2025 set)39%24.8%
FrontierMath Tier 4 (v1)14.6%6.3%
FrontierMath (Tiers 1-3)—36.1%
FrontierMath Tier 4—4.9%
ProofBench17%—
Omni-MATH—72%
MATH Level 5—97.8%

Knowledge Muse Spark leads

Muse Spark: 65.7 (#13), o4-mini: 43.6 (#91)

BenchmarkMuse Sparko4-mini
GPQA Diamond89.8%79.6%
Humanity's Last Exam40.6%18.1%
LMArena Expert14571343
SimpleQA Verified—19.6%
MMLU-Pro—82%
Confabulations—15.8%
Vectara Hallucination Rate—18.6%
GPQA (HELM)—73.5%

Multimodal Muse Spark leads

Muse Spark: 43.4 (#24), o4-mini: 40.2 (#49)

BenchmarkMuse Sparko4-mini
LMArena Vision13061194
GeoBench—64%
VPCT—57.5%
LMArena Document1444—

Multilingual Muse Spark leads

Muse Spark: 56.1 (#24), o4-mini: 47.0 (#154)

BenchmarkMuse Sparko4-mini
LMArena Non-English14641337
LMArena Chinese15091354
LMArena French14971364
LMArena German14971336
LMArena Korean14591312
LMArena Russian14661334
LMArena Spanish14721347
LMArena Japanese—1308

Instruction Following Too close to call

Muse Spark: 75.9 (#51), o4-mini: 75.2 (#68)

BenchmarkMuse Sparko4-mini
LMArena Instruction Following14421321
IFEval—92.8%

Long Context o4-mini leads

Muse Spark: 44.4 (#69), o4-mini: 45.5 (#33)

BenchmarkMuse Sparko4-mini
LMArena Longer Query14511315
Fiction.LiveBench—77.8%

Writing & Preference Muse Spark leads

Muse Spark: 66.0 (#39), o4-mini: 54.0 (#152)

BenchmarkMuse Sparko4-mini
LMArena Text14741353
LMArena Creative Writing14591294
LMArena Multi-Turn14771350
Short-Story Creative Writing—75%
WildBench—85.4%

Frequently asked questions

Is Muse Spark better than o4-mini?

Muse Spark is the stronger model overall, scoring 50.6 to 41.6 on the Noometry Index.

Is Muse Spark or o4-mini better for coding?

Muse Spark scores higher on coding benchmarks: 46.2 versus 40.9 in the Noometry coding category.

How many benchmarks do Muse Spark and o4-mini share?

24 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and o4-mini has 60.

Related comparisons

Go deeper