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 SolQwen3.7 Max
| GPT-5.6 Sol OpenAI | Qwen3.7 Max Alibaba (Qwen) | |
|---|---|---|
| Pricing | ||
| Input $/1M | $5.00 | $1.48 |
| Output $/1M | $30.00 | $4.42 |
| Blended $/1M (3:1) | $11.25 | $2.21 |
| Cache read $/1M | $0.50 | $0.295 |
| Cache write $/1M | $6.25 | $1.84 |
| Quality indices | ||
| Intelligence Index | 58.9 | 46 |
| Coding Index | 77.4 | 66 |
| Math Index | — | — |
| Agentic Index | 54 | 30.6 |
| Speed & latency | ||
| Output speed (tok/s) | 67 | 207 |
| Time to first token | 120.38s | 1.55s |
| Time to first answer token | 120.38s | 13.16s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 94.1% | 92.3% |
| Humanity's Last Exam | 47.2% | 38.1% |
| SciCode | 56.1% | 48.8% |
| IFBench | 72.7% | 80.5% |
| AA-LCR (Long Context Reasoning) | 73.7% | 69.0% |
| Terminal-Bench Hard | 65.9% | 50.8% |
| Terminal-Bench 2.1 | 88.0% | 74.5% |
| τ²-Bench (Telecom) | 85.1% | 94.7% |
| τ³-Bench Banking | 33.0% | 10.9% |
| Design Arena (Elo) | ||
| Website | — | 1,291 |
| Web apps | — | 1,253 |
| Full-stack | — | 1,225 |
| Mobile apps | — | 1,208 |
| Android native | — | 1,182 |
| UI components | — | 1,313 |
| Data viz | — | 1,304 |
| SVG | — | 1,267 |
| 3D | — | 1,310 |
| Game dev | — | 1,315 |
| Agentic game dev | — | 1,180 |
| Godot game dev | — | 1,248 |
| HTML slides | — | 1,191 |
| Python→PPTX slides | — | 1,229 |
| Code categories | — | 1,299 |
| ASCII art | — | 1,261 |
| Specs | ||
| Context window | 1.05M | 1M |
| Max output tokens | 128K | 66K |
| Input modalities | file, image, text | text |
| Tokenizer | GPT | Qwen |