picksbymodel Get API access →
head-to-head

Mistral: Mistral Medium 3.5 vs Mistral: Mistral Small 4

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-06-19.

Mistral: Mistral Medium 3.5 Mistral: Mistral Small 4
Vendormistralaimistralai
Quality Score100100
Benchmark Score63.36.1
Input Price$1.50/M$0.15/M
Output Price$7.50/M$0.60/M
Context Window262,144262,144
Max Output--
Tool Calling✓✓
Structured Output✓✓
Reasoning Mode✓✓
Vision✓✓
Audio--
Benchmark Scores
ai_index49.47.7
ai_index_agentic87.7-
ai_index_coding58.4-

Who wins by task?

TaskMistral: Mistral Medium 3.5Mistral: Mistral Small 4
SQL Generation 158 132
Code Review 151 127
Code Completion 116 129
Code Refactoring 147 129
Bug Fixing 165 131
Unit Test Generation 142 122
Code Documentation 132 127
Regex Writing 130 120
CI/CD Pipelines 134 118
Frontend Component Design 139 122
Data Analysis 160 125
CSV / Spreadsheet Cleanup 141 128
ETL Scripting 140 123
JSON Extraction 133 131
Bulk Data Labeling 123 129
OCR / Document Parsing 138 128
Table Extraction from PDFs 138 128
Long-Document Summarization 144 130
Short-Form Summarization 120 124
Blog Post Writing 131 120

Scores reflect capability match + benchmark data + pricing for each task. Methodology →

Related comparisons

MoonshotAI: Kimi K2.7 Code vs Mistral: Mistral Medium 3.5 MoonshotAI: Kimi K2.7 Code vs Mistral: Mistral Small 4 Qwen: Qwen3.7 Plus vs Mistral: Mistral Medium 3.5 Qwen: Qwen3.7 Plus vs Mistral: Mistral Small 4 MiniMax: MiniMax M3 vs Mistral: Mistral Medium 3.5 MiniMax: MiniMax M3 vs Mistral: Mistral Small 4 StepFun: Step 3.7 Flash vs Mistral: Mistral Medium 3.5 StepFun: Step 3.7 Flash vs Mistral: Mistral Small 4