Noometry

Model comparison

Magistral Medium vs Mistral Large 3

Mistral Large 3 is the stronger model overall, scoring 39.1 to 35.2 on the Noometry Index.

Last verified . 18 shared benchmarks.

Magistral Medium Mistral AI

35.2

Rank #227 Confirmed

Mistral Large 3 Mistral AI

39.1

Rank #176 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Magistral Medium scores higher in 1 category and Mistral Large 3 in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Mistral Large 3 leads 60.0 to 46.3.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 16.2% for Magistral Medium and 50.9% for Mistral Large 3.
  • Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $2 / $5 for Magistral Medium.

Side by side

Magistral MediumMistral Large 3
ProviderMistral AIMistral AI
Noometry Index35.239.1
Released2025-03-172025-12-02
WeightsOpenOpen
Context window262K262K
Max output16K8K
Input $ / M tokens$2$0.25
Output $ / M tokens$5$0.75
Results tracked2224

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

Category by category

Coding Magistral Medium leads

Magistral Medium: 39.1 (#161), Mistral Large 3: 34.4 (#237)

BenchmarkMagistral MediumMistral Large 3
LMArena Coding13191448
LMArena WebDev—1230
SciCode39.2%—

Reasoning Mistral Large 3 leads

Magistral Medium: 8.6 (#348), Mistral Large 3: 15.2 (#319)

BenchmarkMagistral MediumMistral Large 3
Kagi LLM Benchmark16.2%50.9%
LMArena Hard Prompts12671429
ARC-AGI-20%—
NYT Connections (extended)—7.5%
ARC-AGI-16.1%—
CritPt0.3%—
Thematic Generalization—23%

Math Mistral Large 3 leads

Magistral Medium: 35.1 (#189), Mistral Large 3: 38.7 (#129)

BenchmarkMagistral MediumMistral Large 3
LMArena Math12501414

Knowledge Mistral Large 3 leads

Magistral Medium: 33.5 (#202), Mistral Large 3: 36.0 (#177)

BenchmarkMagistral MediumMistral Large 3
LMArena Expert12231421
Vectara Hallucination Rate—14.5%

Multimodal Not comparable

Magistral Medium: —, Mistral Large 3: 38.2 (#66)

BenchmarkMagistral MediumMistral Large 3
LMArena Vision—1221

Multilingual Mistral Large 3 leads

Magistral Medium: 39.6 (#224), Mistral Large 3: 52.5 (#84)

BenchmarkMagistral MediumMistral Large 3
LMArena Non-English12321413
LMArena Chinese12271447
LMArena French12671455
LMArena German12481437
LMArena Japanese11751394
LMArena Korean11251384
LMArena Russian12241411
LMArena Spanish12711440

Instruction Following Mistral Large 3 leads

Magistral Medium: 66.0 (#211), Mistral Large 3: 74.0 (#108)

BenchmarkMagistral MediumMistral Large 3
LMArena Instruction Following12541403

Long Context Mistral Large 3 leads

Magistral Medium: 39.3 (#183), Mistral Large 3: 43.1 (#105)

BenchmarkMagistral MediumMistral Large 3
LMArena Longer Query12951413

Writing & Preference Mistral Large 3 leads

Magistral Medium: 46.3 (#219), Mistral Large 3: 60.0 (#101)

BenchmarkMagistral MediumMistral Large 3
LMArena Text12551428
LMArena Creative Writing12451386
LMArena Multi-Turn12751429
EQ-Bench Creative Writing—1412

Frequently asked questions

Is Magistral Medium better than Mistral Large 3?

Mistral Large 3 is the stronger model overall, scoring 39.1 to 35.2 on the Noometry Index.

Which is cheaper, Magistral Medium or Mistral Large 3?

Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Magistral Medium lists at $2 and $5.

Is Magistral Medium or Mistral Large 3 better for coding?

Magistral Medium scores higher on coding benchmarks: 39.1 versus 34.4 in the Noometry coding category.

Which has the bigger context window?

Both accept 262K tokens.

How many benchmarks do Magistral Medium and Mistral Large 3 share?

18 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Mistral Large 3 has 24.

Related comparisons

Go deeper