picksbymodel Get API access →
head-to-head

Google: Gemma 4 31B vs Mistral: Mistral Small 4

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-06-16.

Google: Gemma 4 31B Mistral: Mistral Small 4
Vendorgooglemistralai
Quality Score100100
Benchmark Score68.57.1
Input Price$0.12/M$0.15/M
Output Price$0.35/M$0.60/M
Context Window262,144262,144
Max Output262,144-
Tool Calling✓✓
Structured Output✓✓
Reasoning Mode✓✓
Vision✓✓
Audio--
Benchmark Scores
ai_index64.716.8
ai_index_agentic67.6-
ai_index_coding63.9-
eqbench70.8-

Who wins by task?

TaskGoogle: Gemma 4 31BMistral: Mistral Small 4
SQL Generation 164 133
Code Review 161 129
Code Completion 132 129
Code Refactoring 157 130
Bug Fixing 173 133
Unit Test Generation 148 123
Code Documentation 141 127
Regex Writing 135 121
CI/CD Pipelines 140 119
Frontend Component Design 143 124
Data Analysis 163 126
CSV / Spreadsheet Cleanup 146 129
ETL Scripting 149 124
JSON Extraction 143 131
Bulk Data Labeling 133 129
OCR / Document Parsing 141 129
Table Extraction from PDFs 141 129
Long-Document Summarization 155 132
Short-Form Summarization 131 124
Blog Post Writing 138 121

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

Related comparisons

MoonshotAI: Kimi K2.7 Code vs Google: Gemma 4 31B MoonshotAI: Kimi K2.7 Code vs Mistral: Mistral Small 4 Qwen: Qwen3.7 Plus vs Google: Gemma 4 31B Qwen: Qwen3.7 Plus vs Mistral: Mistral Small 4 MiniMax: MiniMax M3 vs Google: Gemma 4 31B MiniMax: MiniMax M3 vs Mistral: Mistral Small 4 StepFun: Step 3.7 Flash vs Google: Gemma 4 31B StepFun: Step 3.7 Flash vs Mistral: Mistral Small 4