Cohere: Command A+ vs OpenAI: GPT-6 Luna Pro (batch)
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| Cohere: Command A+ | OpenAI: GPT-6 Luna Pro (batch) | |
|---|---|---|
| Vendor | cohere | openai |
| Quality Score | 100 | 100 |
| Benchmark Score | 32.5 | - |
| Input Price | $0.30/M | $0.05/M |
| Output Price | $1.50/M | $0.25/M |
| Context Window | 192,000 | 1,050,000 |
| Max Output | 64,000 | 128,000 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | 37.1 | - |
| ai_index_agentic | 15.1 | - |
| ai_index_coding | 45.9 | - |
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 Command A+ costs $0.68, so GPT-6 Luna Pro (batch) is about 6.0 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 288 pages for Command A+.
Across the 20 tasks where they differ, Command A+ scores higher on 16 (SQL Generation, Code Review, Bug Fixing and others), GPT-6 Luna Pro (batch) on 4 (Code Completion, Code Refactoring, Code Documentation and others).
Pick Command A+ if you need the stronger all-round task scores; pick GPT-6 Luna Pro (batch) if you need lower cost or long documents.
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 | Cohere: Command A+ | OpenAI: GPT-6 Luna Pro (batch) |
|---|---|---|
| SQL Generation | 144 | 134 |
| Code Review | 137 | 132 |
| Code Completion | 128 | 131 |
| Code Refactoring | 134 | 136 |
| Bug Fixing | 143 | 136 |
| Unit Test Generation | 131 | 124 |
| Code Documentation | 128 | 131 |
| Regex Writing | 126 | 119 |
| CI/CD Pipelines | 125 | 120 |
| Frontend Component Design | 131 | 122 |
| Data Analysis | 140 | 124 |
| CSV / Spreadsheet Cleanup | 134 | 134 |
| ETL Scripting | 130 | 128 |
| JSON Extraction | 139 | 131 |
| Bulk Data Labeling | 131 | 129 |
| OCR / Document Parsing | 133 | 131 |
| Table Extraction from PDFs | 133 | 131 |
| Long-Document Summarization | 134 | 138 |
| Short-Form Summarization | 126 | 123 |
| Blog Post Writing | 124 | 122 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →