head-to-head

OpenAI: GPT-5.6 Luna vs Mistral: Mistral Medium 3.5

Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-09-23.

OpenAI: GPT-5.6 Luna Mistral: Mistral Medium 3.5
Vendoropenaimistralai
Quality Score100100
Benchmark Score62.319.3
Input Price$0.20/M$1.50/M
Output Price$1.20/M$7.50/M
Context Window1,050,000262,144
Max Output128,000209,715
Tool Calling
Structured Output
Reasoning Mode
Vision
Audio--
Benchmark Scores
ai_index61.623.4

Who wins by task?

TaskOpenAI: GPT-5.6 LunaMistral: Mistral Medium 3.5
SQL Generation 141 133
Code Review 143 130
Code Completion 133 115
Code Refactoring 145 131
Bug Fixing 147 134
Unit Test Generation 131 124
Code Documentation 137 126
Regex Writing 125 120
CI/CD Pipelines 127 120
Frontend Component Design 129 124
Data Analysis 133 127
CSV / Spreadsheet Cleanup 136 128
ETL Scripting 136 125
JSON Extraction 131 122
Bulk Data Labeling 129 119
OCR / Document Parsing 134 129
Table Extraction from PDFs 134 129
Long-Document Summarization 147 132
Short-Form Summarization 126 115
Blog Post Writing 129 121

Scores reflect capability match + benchmark data + pricing for each task. Methodology →

Related comparisons

Anthropic: Claude Opus 5 (batch) vs OpenAI: GPT-5.6 Luna Anthropic: Claude Sonnet 5 vs Mistral: Mistral Medium 3.5 ByteDance Seed: Seed-2.0-Code vs OpenAI: GPT-5.6 Luna ByteDance Seed: Seed 2.1 Turbo vs OpenAI: GPT-5.6 Luna DeepSeek: DeepSeek V4.1 Flash vs OpenAI: GPT-5.6 Luna DeepSeek: DeepSeek V4 Flash Vision Exp vs OpenAI: GPT-5.6 Luna Google: Gemini 3.1 Flash Lite vs Mistral: Mistral Medium 3.5 Google: Gemini 3.5 Flash Lite (batch) vs OpenAI: GPT-5.6 Luna

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.