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.
Mistral Medium 3.5GPT-5.6 Sol
| Mistral Medium 3.5 Mistral | GPT-5.6 Sol OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $1.50 | $5.00 |
| Output $/1M | $7.50 | $30.00 |
| Blended $/1M (3:1) | $3.00 | $11.25 |
| Cache read $/1M | — | $0.50 |
| Cache write $/1M | — | $6.25 |
| Quality indices | ||
| Intelligence Index | 29.9 | 58.9 |
| Coding Index | 46.9 | 77.4 |
| Math Index | — | — |
| Agentic Index | 19 | 54 |
| Speed & latency | ||
| Output speed (tok/s) | 135 | 67 |
| Time to first token | 0.80s | 120.38s |
| Time to first answer token | 15.59s | 120.38s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 74.8% | 94.1% |
| Humanity's Last Exam | 12.8% | 47.2% |
| SciCode | 39.6% | 56.1% |
| IFBench | 68.8% | 72.7% |
| AA-LCR (Long Context Reasoning) | 61.0% | 73.7% |
| Terminal-Bench Hard | 33.3% | 65.9% |
| Terminal-Bench 2.1 | 50.6% | 88.0% |
| τ²-Bench (Telecom) | 94.2% | 85.1% |
| τ³-Bench Banking | 14.4% | 33.0% |
| Specs | ||
| Context window | 262K | 1.05M |
| Max output tokens | — | 128K |
| Input modalities | text, image, file | file, image, text |
| Tokenizer | Mistral | GPT |