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 SolQwen3.5 397B A17B
| GPT-5.6 Sol OpenAI | Qwen3.5 397B A17B Alibaba (Qwen) | |
|---|---|---|
| Pricing | ||
| Input $/1M | $5.00 | $0.39 |
| Output $/1M | $30.00 | $2.34 |
| Blended $/1M (3:1) | $11.25 | $0.877 |
| Cache read $/1M | $0.50 | — |
| Cache write $/1M | $6.25 | — |
| Quality indices | ||
| Intelligence Index | 58.9 | 33.7 |
| Coding Index | 77.4 | 48.2 |
| Math Index | — | — |
| Agentic Index | 54 | 19.8 |
| Speed & latency | ||
| Output speed (tok/s) | 67 | 61 |
| Time to first token | 120.38s | 1.75s |
| Time to first answer token | 120.38s | 53.69s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 94.1% | 89.3% |
| Humanity's Last Exam | 47.2% | 27.3% |
| SciCode | 56.1% | 42.0% |
| IFBench | 72.7% | 78.8% |
| AA-LCR (Long Context Reasoning) | 73.7% | 65.7% |
| Terminal-Bench Hard | 65.9% | 40.9% |
| Terminal-Bench 2.1 | 88.0% | 51.3% |
| τ²-Bench (Telecom) | 85.1% | 95.6% |
| τ³-Bench Banking | 33.0% | 13.4% |
| Design Arena (Elo) | ||
| Website | — | 1,218 |
| UI components | — | 1,205 |
| Data viz | — | 1,212 |
| SVG | — | 1,188 |
| 3D | — | 1,219 |
| Game dev | — | 1,198 |
| Code categories | — | 1,213 |
| Specs | ||
| Context window | 1.05M | 262K |
| Max output tokens | 128K | 66K |
| Input modalities | file, image, text | text, image, video |
| Tokenizer | GPT | Qwen3 |