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.
GPT-5.6 SolMiMo-V2.5
| GPT-5.6 Sol OpenAI | MiMo-V2.5 Xiaomi | |
|---|---|---|
| Pricing | ||
| Input $/1M | $5.00 | $0.14 |
| Output $/1M | $30.00 | $0.28 |
| Blended $/1M (3:1) | $11.25 | $0.175 |
| Cache read $/1M | $0.50 | $0.0028 |
| Cache write $/1M | $6.25 | — |
| Quality indices | ||
| Intelligence Index | 58.9 | 37.2 |
| Coding Index | 77.4 | 56.8 |
| Math Index | — | — |
| Agentic Index | 54 | 23.7 |
| Speed & latency | ||
| Output speed (tok/s) | 70 | 63 |
| Time to first token | 112.90s | 3.40s |
| Time to first answer token | 112.90s | 34.93s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 94.1% | 84.9% |
| Humanity's Last Exam | 47.2% | 25.2% |
| SciCode | 56.1% | 43.1% |
| IFBench | 72.7% | 67.1% |
| AA-LCR (Long Context Reasoning) | 73.7% | 62.7% |
| Terminal-Bench Hard | 65.9% | 41.7% |
| Terminal-Bench 2.1 | 88.0% | 63.7% |
| τ²-Bench (Telecom) | 85.1% | 90.6% |
| τ³-Bench Banking | 33.0% | 6.6% |
| Design Arena (Elo) | ||
| Website | — | 1,288 |
| UI components | — | 1,294 |
| Data viz | — | 1,279 |
| SVG | — | 1,218 |
| 3D | — | 1,273 |
| Game dev | — | 1,291 |
| Code categories | — | 1,286 |
| ASCII art | — | 1,175 |
| Specs | ||
| Context window | 1.05M | 1.05M |
| Max output tokens | 128K | 131K |
| Input modalities | file, image, text | text, audio, image, video |
| Tokenizer | GPT | Other |