Mistral: Mistral Medium 3.5 vs Google: Gemma 4 26B A4B (free)
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| Mistral: Mistral Medium 3.5 | Google: Gemma 4 26B A4B (free) | |
|---|---|---|
| Vendor | mistralai | |
| Quality Score | 100 | 100 |
| Benchmark Score | 53.0 | 48.4 |
| Input Price | $1.50/M | Free |
| Output Price | $7.50/M | Free |
| Context Window | 262,144 | 262,144 |
| Max Output | 209,715 | 32,768 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | 49.4 | 42.4 |
| ai_index_agentic | 31.3 | 18.1 |
| ai_index_coding | 77.4 | 64.9 |
| eqbench | - | 56.3 |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Gemma 4 26B A4B (free) costs $0 and Mistral Medium 3.5 costs $3.38, so Gemma 4 26B A4B (free) is free for the same work.
Both read up to 262,144 tokens at once, roughly 393 pages of text.
Only Gemma 4 26B A4B (free) offers video input.
On our blended benchmark score Mistral Medium 3.5 leads 53.0 to 48.4.
Across the 19 tasks where they differ, Mistral Medium 3.5 scores higher on 4 (Frontend Component Design, Data Analysis, OCR / Document Parsing and others), Gemma 4 26B A4B (free) on 15 (Code Review, Code Completion, Code Refactoring and others).
Pick Mistral Medium 3.5 if you need benchmark performance; pick Gemma 4 26B A4B (free) if you need lower cost, video input 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 | Mistral: Mistral Medium 3.5 | Google: Gemma 4 26B A4B (free) |
|---|---|---|
| Code Review | 147 | 150 |
| Code Completion | 116 | 131 |
| Code Refactoring | 144 | 148 |
| Bug Fixing | 155 | 156 |
| Unit Test Generation | 140 | 140 |
| Code Documentation | 131 | 136 |
| Regex Writing | 128 | 130 |
| CI/CD Pipelines | 132 | 133 |
| Frontend Component Design | 137 | 136 |
| Data Analysis | 151 | 148 |
| CSV / Spreadsheet Cleanup | 142 | 143 |
| ETL Scripting | 138 | 141 |
| JSON Extraction | 134 | 142 |
| Bulk Data Labeling | 123 | 133 |
| OCR / Document Parsing | 139 | 138 |
| Table Extraction from PDFs | 139 | 138 |
| Long-Document Summarization | 141 | 147 |
| Short-Form Summarization | 119 | 129 |
| Blog Post Writing | 129 | 132 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →