Skip to main content

Mistral Small 4 (Reasoning)

MistralMistral
Release Date
2026-03-16
Parameters
Context Length
256K
Modalities
image, text

Capability Radar

18
general
38
coding
77
reasoning
50
scienceest.
65
agents
60
multimodal

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

Rankings

Domain#RankScoreSource
Code Ranking226
44.0
AA
General Ranking259
40.0
AA
Science157
53.0
AA

Benchmark Scores (LLM Stats)

Biology

GPQA71.2%SR

Code

LiveCodeBench63.6%SR

Creativity

Arena Hard58.3%SR

Finance

MMLU-Pro78.0%SR

General

MMMU-Pro60.0%SR
IFBench48.0%SR

Language

COLLIE62.9%SR

Long Context

AA-LCR71.2%SR

Math

AIME 202583.8%SR

AA Evaluation Indices

Intelligence Index
20.8
Gpqa
0.8
Ifbench
0.5
Lcr
0.4
Tau2
0.4
Scicode
0.4
Terminalbench Hard
0.2
Hle
0.1

LLM Stats Category Scores

Legal
80
Math
80
Finance
80
Healthcare
80
Language
70
Long Context
70
Physics
70
Reasoning
70
Biology
70
Chemistry
70
Multimodal
60
General
60
Code
60
Creativity
60
Vision
60
Writing
60
Instruction Following
50

Pricing

Input Price$0.15 / 1M tokens
Output Price$0.6 / 1M tokens
Blended Price (3:1)$0.262 / 1M tokens

Speed

Tokens/sec177.0
Time to First Token0.59s
Time to Answer11.89s

Provider Price Ranking

Provider Price Ranking

3 providers

Cheapest: MistralMost Expensive: Regolo AI
ProviderInputOutput
1MistralPRIMARY
$0.15
$0.6
2NanoGPT
$0.4
$1.4
3Regolo AI
$0.75
$3

Compare pricing across different API providers for this model.

External Sources