Mistral: Mistral Large 4 vs OpenAI: GPT-6 Luna Pro (batch)
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-10-07.
| Mistral: Mistral Large 4 | OpenAI: GPT-6 Luna Pro (batch) | |
|---|---|---|
| Vendor | mistralai | openai |
| Quality Score | 100 | 100 |
| Input Price | $0.68/M | $0.05/M |
| Output Price | $2.09/M | $0.25/M |
| Context Window | 524,288 | 1,050,000 |
| Max Output | 262,144 | 128,000 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, GPT-6 Luna Pro (batch) costs $0.11 and Mistral Large 4 costs $1.20, so GPT-6 Luna Pro (batch) is about 10.7 times cheaper for the same work.
GPT-6 Luna Pro (batch) reads up to 1,050,000 tokens at once, roughly 1,575 pages of text, against about 786 pages for Mistral Large 4.
Across the 10 tasks where they differ, GPT-6 Luna Pro (batch) on 10 (SQL Generation, Code Completion, Code Documentation and others).
Mistral Large 4 was released in October 2026 and GPT-6 Luna Pro (batch) in September 2026.
Pick GPT-6 Luna Pro (batch) if you need lower cost, long documents 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 Large 4 | OpenAI: GPT-6 Luna Pro (batch) |
|---|---|---|
| SQL Generation | 133 | 134 |
| Code Completion | 131 | 131 |
| Code Documentation | 131 | 131 |
| Regex Writing | 119 | 119 |
| CSV / Spreadsheet Cleanup | 133 | 134 |
| JSON Extraction | 131 | 131 |
| Bulk Data Labeling | 129 | 129 |
| Long-Document Summarization | 137 | 138 |
| Short-Form Summarization | 123 | 123 |
| Blog Post Writing | 121 | 122 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →