Skip to main content

Magistral Small 1

MistralOpen WeightApache 2.0 · Commercial OK

Description

Building upon Mistral Small 3.1 (2503), with added reasoning capabilities, undergoing SFT from Magistral Medium traces and RL on top, it's a small, efficient reasoning model with 24B parameters. Magistral Small can be deployed locally, fitting within a single RTX 4090 or a 32GB RAM MacBook once quantized.

Release Date
2025-06-10
Parameters
24.0B
Context Length
128K
Modalities
text

Capability Radar

29
general
45
coding
59
reasoning
39
scienceest.
55
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Code Ranking360
21.0
AA
General Ranking348
32.0
AA
Math Reasoning148
60.0
AA
Science296
39.0
AA

Benchmark Scores (LLM Stats)

Biology

GPQA68.2%SR

Code

LiveCodeBench51.3%SR

Math

AIME 202470.7%SR
AIME 202562.8%SR

AA Evaluation Indices

Math Index
41.3
Intelligence Index
10.7
Math 500
1.0
Mmlu Pro
0.7
Aime
0.7
Gpqa
0.6
Livecodebench
0.5
Aime 25
0.4
Tau2
0.3
Ifbench
0.2
Scicode
0.2
Hle
0.1
Terminalbench Hard
0.0
Lcr
0.0

LLM Stats Category Scores

Math
70
Physics
70
Biology
70
Chemistry
70
Reasoning
60
General
60
Code
50

Pricing

Input PriceFree
Output PriceFree
Blended Price (3:1)Free

Speed

Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s

Provider Price Ranking

Provider Price Ranking

4 providers

Cheapest: NanoGPTMost Expensive: Vercel AI Gateway
ProviderInputOutput
1NanoGPTCheapest
$0.4
$1.4
2IO.NET
$0.5
$1.5
3Mistral
$0.5
$1.5
4Vercel AI Gateway
$0.5
$1.5

Compare pricing across different API providers for this model.

External Sources