picksbymodel Get API access →
head-to-head

Mistral: Mistral Medium 3.5 vs Google: Gemma 4 31B

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-08-03.

Mistral: Mistral Medium 3.5 Google: Gemma 4 31B
Vendormistralaigoogle
Quality Score100100
Benchmark Score52.556.9
Input Price$1.50/M$0.10/M
Output Price$7.50/M$0.34/M
Context Window262,144262,144
Max Output-262,144
Tool Calling✓✓
Structured Output✓✓
Reasoning Mode✓✓
Vision✓✓
Audio--
Benchmark Scores
ai_index49.448.4
ai_index_agentic31.323.8
ai_index_coding77.471.7
eqbench-70.8

Who wins by task?

TaskMistral: Mistral Medium 3.5Google: Gemma 4 31B
SQL Generation 153 157
Code Review 147 154
Code Completion 116 132
Code Refactoring 144 152
Bug Fixing 155 161
Unit Test Generation 140 143
Code Documentation 131 138
Regex Writing 128 131
CI/CD Pipelines 132 136
Frontend Component Design 137 138
Data Analysis 151 152
CSV / Spreadsheet Cleanup 142 146
ETL Scripting 138 144
JSON Extraction 134 143
Bulk Data Labeling 123 133
OCR / Document Parsing 139 140
Table Extraction from PDFs 139 140
Long-Document Summarization 141 150
Short-Form Summarization 119 129
Blog Post Writing 129 134

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

Related comparisons

Thinking Machines: Inkling Small vs Mistral: Mistral Medium 3.5 Thinking Machines: Inkling Small vs Google: Gemma 4 31B Qwen: Qwen3.7 Flash vs Mistral: Mistral Medium 3.5 Qwen: Qwen3.7 Flash vs Google: Gemma 4 31B Google: Gemini 3.6 Flash vs Mistral: Mistral Medium 3.5 Google: Gemini 3.6 Flash vs Google: Gemma 4 31B Google: Gemini 3.5 Flash Lite vs Mistral: Mistral Medium 3.5 Google: Gemini 3.5 Flash Lite vs Google: Gemma 4 31B