Noometry

Model comparison

Muse Spark vs Phi-4

Muse Spark is the stronger model overall, scoring 50.6 to 31.2 on the Noometry Index.

Last verified . 19 shared benchmarks.

Muse Spark Meta

50.6

Rank #46 Confirmed

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Muse Spark scores higher in 8 categories and Phi-4 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Muse Spark leads 65.7 to 32.6.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for Muse Spark and 13.8% for Phi-4.
  • Phi-4 has downloadable open weights; the other is API-only.

Side by side

Muse SparkPhi-4
ProviderMetaMicrosoft
Noometry Index50.631.2
Released2026-04-082024-12-11
WeightsProprietaryOpen
Context window—128K
Max output—4K
Input $ / M tokens—$0.07
Output $ / M tokens—$0.14
Results tracked2737

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

Category by category

Coding Muse Spark leads

Muse Spark: 46.2 (#69), Phi-4: 34.4 (#239)

BenchmarkMuse SparkPhi-4
LMArena Coding14811231
SciCode51.5%—
BigCodeBench Instruct—45.5%
LiveBench Coding—30.7%
BigCodeBench Complete—55.4%

Agentic & Tool Use Not comparable

Muse Spark: —, Phi-4: 22.8 (#128)

BenchmarkMuse SparkPhi-4
Berkeley Function Calling Leaderboard—28.8%
BALROG—11.6%

Reasoning Muse Spark leads

Muse Spark: 35.9 (#67), Phi-4: 17.7 (#291)

BenchmarkMuse SparkPhi-4
LMArena Hard Prompts14741220
Epoch Capabilities Index152.04130.42
CritPt11.3%—
Chess Puzzles—1%
LiveBench Reasoning—47.8%
LiveBench Data Analysis—45.2%
LiveBench—41.6%

Math Muse Spark leads

Muse Spark: 47.8 (#66), Phi-4: 20.8 (#285)

BenchmarkMuse SparkPhi-4
OTIS Mock AIME 2024-202588.9%13.8%
LMArena Math14551246
ProofBench17%—
LiveBench Math—42%
MATH Level 5—64.9%
FrontierMath (Feb 2025 set)39%—
FrontierMath Tier 4 (v1)14.6%—

Knowledge Muse Spark leads

Muse Spark: 65.7 (#13), Phi-4: 32.6 (#209)

BenchmarkMuse SparkPhi-4
GPQA Diamond89.8%56.1%
LMArena Expert14571203
Humanity's Last Exam40.6%—
Confabulations—29.4%
Vectara Hallucination Rate—3.7%
MMLU—84.8%

Multimodal Not comparable

Muse Spark: 43.4 (#24), Phi-4: —

BenchmarkMuse SparkPhi-4
LMArena Vision1306—
LMArena Document1444—

Multilingual Muse Spark leads

Muse Spark: 56.1 (#24), Phi-4: 37.2 (#237)

BenchmarkMuse SparkPhi-4
LMArena Non-English14641197
LMArena Chinese15091212
LMArena French14971224
LMArena German14971222
LMArena Korean14591151
LMArena Russian14661209
LMArena Spanish14721234
LMArena Japanese—1158

Instruction Following Muse Spark leads

Muse Spark: 75.9 (#51), Phi-4: 60.4 (#251)

BenchmarkMuse SparkPhi-4
LMArena Instruction Following14421201
LiveBench Instruction Following—58.4%

Long Context Muse Spark leads

Muse Spark: 44.4 (#69), Phi-4: 36.9 (#226)

BenchmarkMuse SparkPhi-4
LMArena Longer Query14511217

Writing & Preference Muse Spark leads

Muse Spark: 66.0 (#39), Phi-4: 40.5 (#244)

BenchmarkMuse SparkPhi-4
LMArena Text14741217
LMArena Creative Writing14591182
LMArena Multi-Turn14771206
Short-Story Creative Writing—62.6%
LiveBench Language—25.6%

Frequently asked questions

Is Muse Spark better than Phi-4?

Muse Spark is the stronger model overall, scoring 50.6 to 31.2 on the Noometry Index.

Is Muse Spark or Phi-4 better for coding?

Muse Spark scores higher on coding benchmarks: 46.2 versus 34.4 in the Noometry coding category.

How many benchmarks do Muse Spark and Phi-4 share?

19 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and Phi-4 has 37.

Related comparisons

Go deeper