geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk
COMPARE.
AI models
mistral

Magistral Small

AI model Released

Context window
131,072 tokens
Maximum output
8,192 tokens
Open weights
Yes

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

Magistral Small

Radar task score

Unrated

1/4 core tests · not enough evidence

2 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

Magistral Small 56.1*% Approx. 95% interval: 49.1–63.0%

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

Magistral Small Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

Magistral Small Not available

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

Magistral Small Not available

Competition mathematics

OTIS Mock AIME 2024-2025 · Separate result

Competition problems with model-extracted answers checked against an exact key. Earlier grading procedures are excluded.

Magistral Small 30.0*% Approx. 95% interval: 18.4–41.6%

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

Run it locally

Inference · memory estimate

Magistral Small

Not enough verified architecture information for a reliable VRAM estimate.

API cost

USD / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Magistral Small

Capabilities

Context window
131,072 tokens
Maximum output
8,192 tokens
Reasoning
Yes
Tool calling
Yes
Open weights
Yes
Model license
Apache 2.0

Input modalities

  • text

Output modalities

  • text

* Provisional data