01Overview02Models03Rankings04Compare05Quiz06Guide

Model

Mistral Small 4 NO.26

Tiny Apache-2.0 multimodal model unifying reasoning, vision and coding.

CompareBack to the index

Mistral AI · Mistral · Fast · Open weights

Specification

Fig.01 — Mistral — Mistral AI

FRANCE

Context window
262Ktokens
Max output
33Ktokens
Input price
$0.15/ 1M
Output price
$0.60/ 1M
Throughput
169tok/s
Class
Fast
Modalities
Text, Image
Weights
Open
Parameters
24B
License
Apache 2.0
Knowledge cutoff
—
Released
Mar 2026

Overview

Mistral Small 4 (2603) is a compact Apache-2.0 model that merges Mistral's previously separate Magistral (reasoning), Pixtral (vision) and Devstral (coding) lines into one small, cheap set of weights with an optional reasoning mode. It is one of the best-value small multimodal models and fully unrestricted for commercial use, but it is not built for hard, long agentic coding. Ideal for edge, local, and high-volume deployments where openness and cost dominate.

Strengths

  • Fully open Apache 2.0 license
  • Very fast output (~169 t/s) and cheap
  • Unified reasoning + vision + coding
  • 256K context, self-hostable on modest hardware

Trade-offs

  • Absolute capability below larger models
  • Agentic reliability limited
  • Weaker on hardest reasoning/coding
  • Small-model recall limits on long context

Fit

Best for

  • Local and edge deployment
  • High-volume cheap inference
  • Fine-tuning with no license friction
  • Lightweight multimodal tasks

Not ideal for

  • Complex agentic coding
  • Frontier reasoning workloads

Capabilities

Ten axes, normalized 0–100 and scored the same way across the whole catalog — so a 78 here means what a 78 means anywhere else on the bench.

Fig.02 — Capability radar

0 — 100

Reasoning
66
Coding
64
Math
64
Writing
72
Knowledge
72
Speed
90
Agentic
58
Vision
66
Multilingual
80
Long Context
76

Benchmarks

Public results, with independent third-party runs marked. Bars normalize percentages against 100 and Elo ratings against a 1500 ceiling.

Independent index

Artificial Analysis Intelligence Index

Composite of ~9–10 independent evals · Artificial Analysis

21/ 100

BenchmarkResult
Artificial Analysis Intelligence IndexIndependentGeneral · Artificial Analysis
21%
τ-benchIndependentAgentic · τ-bench
65.8%

Alternatives

Models in roughly the same class — the ones worth weighing against this record.

Compare side by side
01Llama 4 ScoutMeta AIUltra-long 10M-token context, efficient single-GPU open model.02Qwen3-30B-A3B-Instruct-2507Alibaba QwenSmall, fast open-weight MoE with big-model manners.03Magistral Medium 1.2Mistral AIMistral's transparent-chain reasoning flagship, now multimodal.

Index

PreviousMistral Medium 3.5NextMagistral Medium 1.2
All models/EDUCATION