Compare models
Pick up to 4 models for a side-by-side spec sheet. Hover any dotted metric name for what the test measures. Best value in each row is highlighted.
North Mini Code (free)GPT-5.6 Sol
| North Mini Code (free) Cohere | GPT-5.6 Sol OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | Free | $5.00 |
| Output $/1M | Free | $30.00 |
| Blended $/1M (3:1) | Free | $11.25 |
| Cache read $/1M | — | $0.50 |
| Cache write $/1M | — | $6.25 |
| Quality indices | ||
| Intelligence Index | 19.8 | 58.9 |
| Coding Index | 36.5 | 77.4 |
| Math Index | — | — |
| Agentic Index | 3.1 | 54 |
| Speed & latency | ||
| Output speed (tok/s) | 96 | 70 |
| Time to first token | 0.24s | 112.90s |
| Time to first answer token | 21.06s | 112.90s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 75.7% | 94.1% |
| Humanity's Last Exam | 10.0% | 47.2% |
| SciCode | 38.2% | 56.1% |
| IFBench | 57.6% | 72.7% |
| AA-LCR (Long Context Reasoning) | 32.3% | 73.7% |
| Terminal-Bench Hard | 31.1% | 65.9% |
| Terminal-Bench 2.1 | 35.6% | 88.0% |
| τ²-Bench (Telecom) | 37.4% | 85.1% |
| τ³-Bench Banking | 6.4% | 33.0% |
| Specs | ||
| Context window | 256K | 1.05M |
| Max output tokens | 64K | 128K |
| Input modalities | text | file, image, text |
| Tokenizer | Cohere | GPT |