Mistral: Mistral Medium 3.5 vs SpaceXAI: Grok 4.20
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| Mistral: Mistral Medium 3.5 | SpaceXAI: Grok 4.20 | |
|---|---|---|
| Vendor | mistralai | x-ai |
| Quality Score | 100 | 100 |
| Benchmark Score | 53.0 | 56.5 |
| Input Price | $1.50/M | $1.25/M |
| Output Price | $7.50/M | $2.50/M |
| Context Window | 262,144 | 2,000,000 |
| Max Output | 209,715 | 1,800,000 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | 49.4 | 61.0 |
| ai_index_agentic | 31.3 | - |
| ai_index_coding | 77.4 | - |
| eqbench | - | 45.7 |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Grok 4.20 costs $1.88 and Mistral Medium 3.5 costs $3.38, so Grok 4.20 is about 1.8 times cheaper for the same work.
Grok 4.20 reads up to 2,000,000 tokens at once, roughly 3,000 pages of text, against about 393 pages for Mistral Medium 3.5.
On our blended benchmark score Grok 4.20 leads 56.5 to 53.0.
Across the 19 tasks where they differ, Mistral Medium 3.5 scores higher on 12 (SQL Generation, Bug Fixing, Unit Test Generation and others), Grok 4.20 on 7 (Code Review, Code Completion, Code Refactoring and others).
Mistral Medium 3.5 was released in April 2026 and Grok 4.20 in March 2026.
Pick Grok 4.20 if you need lower cost, long documents or benchmark performance.
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 | SpaceXAI: Grok 4.20 |
|---|---|---|
| SQL Generation | 153 | 144 |
| Code Review | 147 | 149 |
| Code Completion | 116 | 121 |
| Code Refactoring | 144 | 151 |
| Bug Fixing | 155 | 153 |
| Unit Test Generation | 140 | 134 |
| Code Documentation | 131 | 140 |
| Regex Writing | 128 | 127 |
| CI/CD Pipelines | 132 | 130 |
| Frontend Component Design | 137 | 131 |
| Data Analysis | 151 | 135 |
| CSV / Spreadsheet Cleanup | 142 | 138 |
| ETL Scripting | 138 | 141 |
| JSON Extraction | 134 | 123 |
| Bulk Data Labeling | 123 | 120 |
| OCR / Document Parsing | 139 | 135 |
| Table Extraction from PDFs | 139 | 135 |
| Long-Document Summarization | 141 | 153 |
| Blog Post Writing | 129 | 132 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →