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.
Command AGPT-5.6 Sol
| Command A Cohere | GPT-5.6 Sol OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $2.50 | $5.00 |
| Output $/1M | $10.00 | $30.00 |
| Blended $/1M (3:1) | $4.38 | $11.25 |
| Cache read $/1M | — | $0.50 |
| Cache write $/1M | — | $6.25 |
| Quality indices | ||
| Intelligence Index | 7.7 | 58.9 |
| Coding Index | 27.8 | 77.4 |
| Math Index | 13 | — |
| Agentic Index | 9.2 | 54 |
| Speed & latency | ||
| Output speed (tok/s) | 61 | 70 |
| Time to first token | 0.34s | 112.90s |
| Time to first answer token | 0.34s | 112.90s |
| Benchmarks (Artificial Analysis) | ||
| MMLU-Pro | 71.2% | — |
| GPQA Diamond | 52.7% | 94.1% |
| Humanity's Last Exam | 4.6% | 47.2% |
| LiveCodeBench | 28.7% | — |
| SciCode | 28.1% | 56.1% |
| MATH-500 | 81.9% | — |
| AIME | 9.7% | — |
| AIME 2025 | 13.0% | — |
| IFBench | 36.5% | 72.7% |
| AA-LCR (Long Context Reasoning) | 18.0% | 73.7% |
| Terminal-Bench Hard | 0.8% | 65.9% |
| Terminal-Bench 2.1 | — | 88.0% |
| τ²-Bench (Telecom) | 15.2% | 85.1% |
| τ³-Bench Banking | — | 33.0% |
| Specs | ||
| Context window | 256K | 1.05M |
| Max output tokens | 8K | 128K |
| Input modalities | text | file, image, text |
| Tokenizer | Other | GPT |