Noometry

Model comparison

GPT-4.1 mini vs Muse Spark

Muse Spark is the stronger model overall, scoring 50.6 to 33.6 on the Noometry Index.

Last verified . 23 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

Muse Spark Meta

50.6

Rank #46 Confirmed

Summary

  • They share 23 benchmarks with published results for both. GPT-4.1 mini scores higher in 0 categories and Muse Spark in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Muse Spark leads 65.7 to 34.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 44.7% for GPT-4.1 mini and 88.9% for Muse Spark.

Side by side

GPT-4.1 miniMuse Spark
ProviderOpenAIMeta
Noometry Index33.650.6
Released2025-04-142026-04-08
WeightsProprietaryProprietary
Context window1.05M—
Max output33K—
Input $ / M tokens$0.40—
Output $ / M tokens$1.60—
Results tracked4727

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

Category by category

Coding Muse Spark leads

GPT-4.1 mini: 30.6 (#293), Muse Spark: 46.2 (#69)

BenchmarkGPT-4.1 miniMuse Spark
SciCode40.4%51.5%
LMArena Coding13671481
SWE-bench Verified (bash only)23.9%—
Aider Polyglot32.4%—
WeirdML37.6%—
BigCodeBench Instruct48.9%—
CadEval16%—

Agentic & Tool Use Not comparable

GPT-4.1 mini: 33.3 (#55), Muse Spark: —

BenchmarkGPT-4.1 miniMuse Spark
Berkeley Function Calling Leaderboard50.5%—

Reasoning Muse Spark leads

GPT-4.1 mini: 10.8 (#340), Muse Spark: 35.9 (#67)

BenchmarkGPT-4.1 miniMuse Spark
CritPt0%11.3%
LMArena Hard Prompts13491474
Epoch Capabilities Index135.01152.04
ARC-AGI-20%—
Kagi LLM Benchmark48.6%—
ARC-AGI-13.5%—
Chess Puzzles7%—
Mystery Game Puzzles7%—
DTBench68.8%—
LMCA21.1%—

Math Muse Spark leads

GPT-4.1 mini: 24.1 (#270), Muse Spark: 47.8 (#66)

BenchmarkGPT-4.1 miniMuse Spark
OTIS Mock AIME 2024-202544.7%88.9%
LMArena Math13431455
FrontierMath (Feb 2025 set)4.5%39%
FrontierMath (Tiers 1-3)6.7%—
ProofBench—17%
Omni-MATH49.1%—
MATH Level 587.3%—
FrontierMath Tier 4 (v1)—14.6%

Knowledge Muse Spark leads

GPT-4.1 mini: 34.7 (#194), Muse Spark: 65.7 (#13)

BenchmarkGPT-4.1 miniMuse Spark
GPQA Diamond65.8%89.8%
LMArena Expert13381457
Humanity's Last Exam—40.6%
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
GPQA (HELM)61.4%—

Multimodal Muse Spark leads

GPT-4.1 mini: 35.8 (#82), Muse Spark: 43.4 (#24)

BenchmarkGPT-4.1 miniMuse Spark
LMArena Vision11811306
LMArena Document—1444

Multilingual Muse Spark leads

GPT-4.1 mini: 45.7 (#166), Muse Spark: 56.1 (#24)

BenchmarkGPT-4.1 miniMuse Spark
LMArena Non-English13181464
LMArena Chinese13291509
LMArena French13581497
LMArena German13511497
LMArena Korean12981459
LMArena Russian13241466
LMArena Spanish13191472
LMArena Japanese1290—

Instruction Following Muse Spark leads

GPT-4.1 mini: 73.7 (#118), Muse Spark: 75.9 (#51)

BenchmarkGPT-4.1 miniMuse Spark
LMArena Instruction Following13331442
IFEval90.4%—

Long Context Muse Spark leads

GPT-4.1 mini: 31.8 (#275), Muse Spark: 44.4 (#69)

BenchmarkGPT-4.1 miniMuse Spark
LMArena Longer Query13441451
Fiction.LiveBench44.4%—

Writing & Preference Muse Spark leads

GPT-4.1 mini: 48.6 (#199), Muse Spark: 66.0 (#39)

BenchmarkGPT-4.1 miniMuse Spark
LMArena Text13401474
LMArena Creative Writing13001459
LMArena Multi-Turn13541477
EQ-Bench Creative Writing1147—
WildBench83.8%—

Frequently asked questions

Is GPT-4.1 mini better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.6 to 33.6 on the Noometry Index.

Is GPT-4.1 mini or Muse Spark better for coding?

Muse Spark scores higher on coding benchmarks: 46.2 versus 30.6 in the Noometry coding category.

How many benchmarks do GPT-4.1 mini and Muse Spark share?

23 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Muse Spark has 27.

Related comparisons

Go deeper