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 3GPT-5.6 Sol
| Mistral Medium 3 Mistral | GPT-5.6 Sol OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $0.40 | $5.00 |
| Output $/1M | $2.00 | $30.00 |
| Blended $/1M (3:1) | $0.80 | $11.25 |
| Cache read $/1M | $0.04 | $0.50 |
| Cache write $/1M | — | $6.25 |
| Quality indices | ||
| Intelligence Index | 12.5 | 58.9 |
| Coding Index | — | 77.4 |
| Math Index | 30.3 | — |
| Agentic Index | — | 54 |
| Speed & latency | ||
| Output speed (tok/s) | 50 | 67 |
| Time to first token | 0.55s | 120.38s |
| Time to first answer token | 0.55s | 120.38s |
| Benchmarks (Artificial Analysis) | ||
| MMLU-Pro | 76.0% | — |
| GPQA Diamond | 57.8% | 94.1% |
| Humanity's Last Exam | 4.3% | 47.2% |
| LiveCodeBench | 40.0% | — |
| SciCode | 33.1% | 56.1% |
| MATH-500 | 90.7% | — |
| AIME | 44.0% | — |
| AIME 2025 | 30.3% | — |
| IFBench | 39.3% | 72.7% |
| AA-LCR (Long Context Reasoning) | 28.0% | 73.7% |
| Terminal-Bench Hard | 3.8% | 65.9% |
| Terminal-Bench 2.1 | — | 88.0% |
| τ²-Bench (Telecom) | 24.3% | 85.1% |
| τ³-Bench Banking | — | 33.0% |
| Design Arena (Elo) | ||
| Website | 1,107 | — |
| UI components | 1,069 | — |
| Data viz | 1,069 | — |
| 3D | 1,141 | — |
| Game dev | 1,077 | — |
| Code categories | 1,103 | — |
| Specs | ||
| Context window | 131K | 1.05M |
| Max output tokens | — | 128K |
| Input modalities | text, image, file | file, image, text |
| Tokenizer | Mistral | GPT |