OpenAI: GPT-5.6 Luna vs OpenAI: GPT-5.4 Mini
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| OpenAI: GPT-5.6 Luna | OpenAI: GPT-5.4 Mini | |
|---|---|---|
| Vendor | openai | openai |
| Quality Score | 100 | 100 |
| Benchmark Score | 89.4 | 70.8 |
| Input Price | $0.20/M | $0.75/M |
| Output Price | $1.20/M | $4.50/M |
| Context Window | 1,050,000 | 400,000 |
| Max Output | 128,000 | 128,000 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | 84.5 | 66.0 |
| ai_index_agentic | 75.2 | 49.8 |
| ai_index_coding | 100.0 | 92.5 |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, GPT-5.6 Luna costs $0.50 and GPT-5.4 Mini costs $1.88, so GPT-5.6 Luna is about 3.8 times cheaper for the same work.
GPT-5.6 Luna reads up to 1,050,000 tokens at once, roughly 1,575 pages of text, against about 600 pages for GPT-5.4 Mini.
On our blended benchmark score GPT-5.6 Luna leads 89.4 to 70.8.
Across the 20 tasks where they differ, GPT-5.6 Luna scores higher on 20 (SQL Generation, Code Review, Code Completion and others).
GPT-5.6 Luna was released in July 2026 and GPT-5.4 Mini in March 2026.
Pick GPT-5.6 Luna if you need lower cost, long documents, benchmark performance 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 | OpenAI: GPT-5.6 Luna | OpenAI: GPT-5.4 Mini |
|---|---|---|
| SQL Generation | 171 | 164 |
| Code Review | 166 | 159 |
| Code Completion | 133 | 132 |
| Code Refactoring | 163 | 158 |
| Bug Fixing | 179 | 170 |
| Unit Test Generation | 154 | 148 |
| Code Documentation | 143 | 140 |
| Regex Writing | 136 | 132 |
| CI/CD Pipelines | 144 | 139 |
| Frontend Component Design | 146 | 141 |
| Data Analysis | 170 | 160 |
| CSV / Spreadsheet Cleanup | 154 | 151 |
| ETL Scripting | 154 | 149 |
| JSON Extraction | 149 | 146 |
| Bulk Data Labeling | 135 | 133 |
| OCR / Document Parsing | 146 | 144 |
| Table Extraction from PDFs | 146 | 144 |
| Long-Document Summarization | 159 | 154 |
| Short-Form Summarization | 132 | 129 |
| Blog Post Writing | 140 | 136 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →