← comparisons / gpt-5.6-luna-vs-north-mini-code-1-0
GPT-5.6 Luna vs North Mini Code
01Head to head
| GPT-5.6 Luna | North Mini Code | |
|---|---|---|
| Creator | OpenAI | Cohere |
| Released | 2026-07-09 | 2026-06-09 |
| Context | 1.1M | 256K |
| Max output | 128K | 64K |
| Input $/M | — | — |
| Output $/M | — | — |
| Knowledge cutoff | 2026-02 | — |
| Modalities | text + image → text | text → text |
| Capabilities | tool-use, extended-thinking, structured-output | — |
| Providers | OpenAI API |
02Benchmarks · vendor-reported unless verified
| GPT-5.6 Luna | North Mini Code | |
|---|---|---|
| BrowseComp (accuracy) | 83.3 | — |
| DeepSWE | 67.2% | — |
| FrontierMath (accuracy) | 78.6 | — |
| GPQA Diamond (accuracy) | 92.3 | — |
| SWE-bench Pro | 62.7% | — |
| Terminal-Bench (success rate) | 84.7 | — |