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-Pro
| GPT-5.6 Sol OpenAI | MiMo-V2.5-Pro Xiaomi | |
|---|---|---|
| Pricing | ||
| Input $/1M | $5.00 | $0.435 |
| Output $/1M | $30.00 | $0.87 |
| Blended $/1M (3:1) | $11.25 | $0.544 |
| Cache read $/1M | $0.50 | $0.0036 |
| Cache write $/1M | $6.25 | — |
| Quality indices | ||
| Intelligence Index | 58.9 | 42.2 |
| Coding Index | 77.4 | 60.2 |
| Math Index | — | — |
| Agentic Index | 54 | 29.1 |
| Speed & latency | ||
| Output speed (tok/s) | 67 | 58 |
| Time to first token | 120.38s | 2.68s |
| Time to first answer token | 120.38s | 36.90s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 94.1% | 86.6% |
| Humanity's Last Exam | 47.2% | 33.8% |
| SciCode | 56.1% | 50.2% |
| IFBench | 72.7% | 79.9% |
| AA-LCR (Long Context Reasoning) | 73.7% | 73.3% |
| Terminal-Bench Hard | 65.9% | 43.2% |
| Terminal-Bench 2.1 | 88.0% | 65.2% |
| τ²-Bench (Telecom) | 85.1% | 94.2% |
| τ³-Bench Banking | 33.0% | 8.7% |
| Design Arena (Elo) | ||
| Website | — | 1,296 |
| UI components | — | 1,281 |
| Data viz | — | 1,281 |
| SVG | — | 1,221 |
| 3D | — | 1,304 |
| Game dev | — | 1,331 |
| Code categories | — | 1,302 |
| ASCII art | — | 1,187 |
| Specs | ||
| Context window | 1.05M | 1.05M |
| Max output tokens | 128K | 131K |
| Input modalities | file, image, text | text |
| Tokenizer | GPT | Other |