Noometry

Model comparison

Mistral Medium vs Muse Spark

Muse Spark is the stronger model overall, scoring 50.6 to 36.3 on the Noometry Index.

Last verified . 24 shared benchmarks.

Mistral Medium Mistral AI

36.3

Rank #218 Confirmed

Muse Spark Meta

50.6

Rank #46 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Mistral Medium 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 25.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 32.2% for Mistral Medium and 88.9% for Muse Spark.
  • Mistral Medium has downloadable open weights; the other is API-only.

Side by side

Mistral MediumMuse Spark
ProviderMistral AIMeta
Noometry Index36.350.6
Released2023-12-112026-04-08
WeightsOpenProprietary
Context window262K—
Max output262K—
Input $ / M tokens$1.50—
Output $ / M tokens$7.50—
Results tracked3627

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

Category by category

Coding Muse Spark leads

Mistral Medium: 34.2 (#243), Muse Spark: 46.2 (#69)

BenchmarkMistral MediumMuse Spark
SciCode40.2%51.5%
LMArena Coding14341481
FrontierCode8%—
WeirdML43.7%—
ALE-Bench763.98—

Agentic & Tool Use Not comparable

Mistral Medium: 28.3 (#90), Muse Spark: —

BenchmarkMistral MediumMuse Spark
Berkeley Function Calling Leaderboard37.7%—

Reasoning Muse Spark leads

Mistral Medium: 24.0 (#167), Muse Spark: 35.9 (#67)

BenchmarkMistral MediumMuse Spark
CritPt0%11.3%
LMArena Hard Prompts14261474
Kagi LLM Benchmark50%—
DTBench75.5%—
LMCA26.1%—
Surface Evolver Bench26.9%—
Epoch Capabilities Index—152.04

Math Muse Spark leads

Mistral Medium: 28.1 (#245), Muse Spark: 47.8 (#66)

BenchmarkMistral MediumMuse Spark
OTIS Mock AIME 2024-202532.2%88.9%
ProofBench9%17%
LMArena Math14081455
FrontierMath (Feb 2025 set)0.3%39%
MATH Level 581.6%—
FrontierMath Tier 4 (v1)—14.6%

Knowledge Muse Spark leads

Mistral Medium: 25.0 (#265), Muse Spark: 65.7 (#13)

BenchmarkMistral MediumMuse Spark
GPQA Diamond59.5%89.8%
Humanity's Last Exam4.5%40.6%
LMArena Expert14081457
Vectara Hallucination Rate22.7%—

Multimodal Muse Spark leads

Mistral Medium: 35.3 (#88), Muse Spark: 43.4 (#24)

BenchmarkMistral MediumMuse Spark
LMArena Vision11721306
LMArena Document—1444

Multilingual Muse Spark leads

Mistral Medium: 52.1 (#91), Muse Spark: 56.1 (#24)

BenchmarkMistral MediumMuse Spark
LMArena Non-English14081464
LMArena Chinese14471509
LMArena French14591497
LMArena German14321497
LMArena Korean13801459
LMArena Russian14111466
LMArena Spanish14331472
LMArena Japanese1378—

Instruction Following Muse Spark leads

Mistral Medium: 73.7 (#116), Muse Spark: 75.9 (#51)

BenchmarkMistral MediumMuse Spark
LMArena Instruction Following13981442

Long Context Muse Spark leads

Mistral Medium: 42.9 (#114), Muse Spark: 44.4 (#69)

BenchmarkMistral MediumMuse Spark
LMArena Longer Query14061451

Writing & Preference Muse Spark leads

Mistral Medium: 60.0 (#103), Muse Spark: 66.0 (#39)

BenchmarkMistral MediumMuse Spark
LMArena Text14241474
LMArena Creative Writing13911459
LMArena Multi-Turn14181477
Short-Story Creative Writing77.3%—

Frequently asked questions

Is Mistral Medium better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.6 to 36.3 on the Noometry Index.

Is Mistral Medium or Muse Spark better for coding?

Muse Spark scores higher on coding benchmarks: 46.2 versus 34.2 in the Noometry coding category.

How many benchmarks do Mistral Medium and Muse Spark share?

24 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Muse Spark has 27.

Related comparisons

Go deeper