Mistral: Mistral Medium 3.5 vs MoonshotAI: Kimi Latest
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| Mistral: Mistral Medium 3.5 | MoonshotAI: Kimi Latest | |
|---|---|---|
| Vendor | mistralai | ~moonshotai |
| Quality Score | 100 | 100 |
| Benchmark Score | 53.0 | - |
| Input Price | $1.50/M | $0.16/M |
| Output Price | $7.50/M | $10.14/M |
| Context Window | 262,144 | 1,048,576 |
| Max Output | 209,715 | 943,718 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | 49.4 | - |
| ai_index_agentic | 31.3 | - |
| ai_index_coding | 77.4 | - |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Kimi Latest costs $2.69 and Mistral Medium 3.5 costs $3.38, so Kimi Latest is about 1.3 times cheaper for the same work.
Kimi Latest reads up to 1,048,576 tokens at once, roughly 1,573 pages of text, against about 393 pages for Mistral Medium 3.5.
Only Kimi Latest offers video input.
Across the 20 tasks where they differ, Mistral Medium 3.5 scores higher on 17 (SQL Generation, Code Review, Code Refactoring and others), Kimi Latest on 3 (Code Completion, Bulk Data Labeling, Short-Form Summarization).
Pick Mistral Medium 3.5 if you need the stronger all-round task scores; pick Kimi Latest if you need lower cost, long documents 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 Medium 3.5 | MoonshotAI: Kimi Latest |
|---|---|---|
| SQL Generation | 153 | 133 |
| Code Review | 147 | 132 |
| Code Completion | 116 | 129 |
| Code Refactoring | 144 | 136 |
| Bug Fixing | 155 | 136 |
| Unit Test Generation | 140 | 124 |
| Code Documentation | 131 | 129 |
| Regex Writing | 128 | 117 |
| CI/CD Pipelines | 132 | 120 |
| Frontend Component Design | 137 | 122 |
| Data Analysis | 151 | 124 |
| CSV / Spreadsheet Cleanup | 142 | 133 |
| ETL Scripting | 138 | 128 |
| JSON Extraction | 134 | 129 |
| Bulk Data Labeling | 123 | 126 |
| OCR / Document Parsing | 139 | 131 |
| Table Extraction from PDFs | 139 | 131 |
| Long-Document Summarization | 141 | 137 |
| Short-Form Summarization | 119 | 121 |
| Blog Post Writing | 129 | 121 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →