Magistral Small 1

Mistral

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$0 / $0

in / out

Context

—

Avg score

37.7

11 benchmarks

AA Intelligence

10.7

index

Weights

Closed

Released

Jun 10, 2025

About

Magistral Small 1 is a proprietary model in the Magistral family from Mistral. Benchmarked on 11 evals, averaging 37.7.

Benchmark scores · 11

avg 37.7 — higher is better

MATHartificial-analysis · 2026-07

96.3

MMLU-Proartificial-analysis · 2026-07

74.6

GPQA Diamondartificial-analysis · 2026-07

64.1

LiveCodeBenchartificial-analysis · 2026-07

51.4

AIMEartificial-analysis · 2026-07

41.3

τ²-benchartificial-analysis · 2026-07

26.6

IFBenchartificial-analysis · 2026-07

24.8

SciCodeartificial-analysis · 2026-07

24.1

Humanity's Last Examartificial-analysis · 2026-07

7.2

Terminal-Bench Hardartificial-analysis · 2026-07

4.5

AA Long-Context Reasoningartificial-analysis · 2026-07

Details

PublisherMistral

FamilyMagistral

Parameters—

License—

WeightsClosed

ReleasedJun 10, 2025

History

full ledger →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers

Artificial Analysis$0/M