Mistral: Mistral Small 4 vs Google: Gemini 3.1 Pro Preview Custom Tools
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| Mistral: Mistral Small 4 | Google: Gemini 3.1 Pro Preview Custom Tools | |
|---|---|---|
| Vendor | mistralai | |
| Quality Score | 100 | 100 |
| Benchmark Score | 6.1 | - |
| Input Price | $0.15/M | $2.00/M |
| Output Price | $0.60/M | $12.00/M |
| Context Window | 262,144 | 1,048,576 |
| Max Output | 209,715 | 65,536 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | ✓ |
| Benchmark Scores | ||
| ai_index | 7.7 | - |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Mistral Small 4 costs $0.30 and Gemini 3.1 Pro Preview Custom Tools costs $5.00, so Mistral Small 4 is about 16.7 times cheaper for the same work.
Gemini 3.1 Pro Preview Custom Tools reads up to 1,048,576 tokens at once, roughly 1,573 pages of text, against about 393 pages for Mistral Small 4.
Only Gemini 3.1 Pro Preview Custom Tools offers audio input and video input.
Across the 20 tasks where they differ, Mistral Small 4 scores higher on 7 (Code Completion, Regex Writing, Frontend Component Design and others), Gemini 3.1 Pro Preview Custom Tools on 13 (SQL Generation, Code Review, Code Refactoring and others).
Mistral Small 4 was released in March 2026 and Gemini 3.1 Pro Preview Custom Tools in February 2026.
Pick Mistral Small 4 if you need lower cost; pick Gemini 3.1 Pro Preview Custom Tools if you need long documents, audio input or video input.
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 | Mistral: Mistral Small 4 | Google: Gemini 3.1 Pro Preview Custom Tools |
|---|---|---|
| SQL Generation | 132 | 132 |
| Code Review | 127 | 132 |
| Code Completion | 129 | 117 |
| Code Refactoring | 129 | 136 |
| Bug Fixing | 131 | 136 |
| Unit Test Generation | 122 | 124 |
| Code Documentation | 127 | 129 |
| Regex Writing | 120 | 117 |
| CI/CD Pipelines | 118 | 120 |
| Frontend Component Design | 122 | 122 |
| Data Analysis | 125 | 124 |
| CSV / Spreadsheet Cleanup | 128 | 132 |
| ETL Scripting | 123 | 128 |
| JSON Extraction | 131 | 121 |
| Bulk Data Labeling | 129 | 117 |
| OCR / Document Parsing | 128 | 131 |
| Table Extraction from PDFs | 128 | 131 |
| Long-Document Summarization | 130 | 136 |
| Short-Form Summarization | 124 | 113 |
| Blog Post Writing | 120 | 120 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →