Google: Gemma 4 31B (free) vs Mistral: Mistral Small 4
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| Google: Gemma 4 31B (free) | Mistral: Mistral Small 4 | |
|---|---|---|
| Vendor | mistralai | |
| Quality Score | 100 | 100 |
| Benchmark Score | 53.7 | 6.1 |
| Input Price | Free | $0.15/M |
| Output Price | Free | $0.60/M |
| Context Window | 262,144 | 262,144 |
| Max Output | 32,768 | 209,715 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | 48.4 | 7.7 |
| ai_index_agentic | 23.8 | - |
| ai_index_coding | 71.7 | - |
| eqbench | 57.5 | - |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Gemma 4 31B (free) costs $0 and Mistral Small 4 costs $0.30, so Gemma 4 31B (free) is free for the same work.
Both read up to 262,144 tokens at once, roughly 393 pages of text.
Only Gemma 4 31B (free) offers video input.
On our blended benchmark score Gemma 4 31B (free) leads 53.7 to 6.1.
Across the 20 tasks where they differ, Gemma 4 31B (free) scores higher on 20 (SQL Generation, Code Review, Code Completion and others).
Gemma 4 31B (free) was released in April 2026 and Mistral Small 4 in March 2026.
Pick Gemma 4 31B (free) if you need lower cost, video input, benchmark performance or the stronger all-round task scores.
Costs use current list prices per million tokens; page counts assume about 0.75 words per token and 500 words per page.
Who wins by task?
| Task | Google: Gemma 4 31B (free) | Mistral: Mistral Small 4 |
|---|---|---|
| SQL Generation | 156 | 132 |
| Code Review | 152 | 127 |
| Code Completion | 131 | 129 |
| Code Refactoring | 151 | 129 |
| Bug Fixing | 160 | 131 |
| Unit Test Generation | 143 | 122 |
| Code Documentation | 137 | 127 |
| Regex Writing | 131 | 120 |
| CI/CD Pipelines | 135 | 118 |
| Frontend Component Design | 138 | 122 |
| Data Analysis | 152 | 125 |
| CSV / Spreadsheet Cleanup | 145 | 128 |
| ETL Scripting | 143 | 123 |
| JSON Extraction | 143 | 131 |
| Bulk Data Labeling | 133 | 129 |
| OCR / Document Parsing | 140 | 128 |
| Table Extraction from PDFs | 140 | 128 |
| Long-Document Summarization | 149 | 130 |
| Short-Form Summarization | 129 | 124 |
| Blog Post Writing | 133 | 120 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →