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 SolStep 3.7 Flash
| GPT-5.6 Sol OpenAI | Step 3.7 Flash Stepfun | |
|---|---|---|
| Pricing | ||
| Input $/1M | $2.00 | $0.20 |
| Output $/1M | $10.00 | $1.15 |
| Blended $/1M (3:1) | $4.00 | $0.438 |
| Cache read $/1M | $0.20 | $0.04 |
| Cache write $/1M | $2.50 | — |
| Quality indices | ||
| Intelligence Index | 47 | 19.5 |
| Coding Index | 77.4 | 39.6 |
| Math Index | — | — |
| Agentic Index | 50.2 | — |
| Speed & latency | ||
| Output speed (tok/s) | 65 | 179 |
| Time to first token | 64.46s | 1.39s |
| Time to first answer token | 64.46s | 12.59s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 94.1% | 80.9% |
| Humanity's Last Exam | 49.5% | 21.4% |
| SciCode | 57.1% | 43.9% |
| IFBench | 72.7% | 67.3% |
| AA-LCR (Long Context Reasoning) | 84.0% | 73.7% |
| Terminal-Bench Hard | 65.9% | 35.6% |
| Terminal-Bench 2.1 | 88.0% | 39.3% |
| τ²-Bench (Telecom) | 85.1% | 98.5% |
| τ³-Bench Banking | 44.3% | 12.0% |
| Design Arena (Elo) | ||
| Website | — | 1,207 |
| UI components | — | 1,198 |
| Data viz | — | 1,185 |
| SVG | — | 1,099 |
| 3D | — | 1,157 |
| Game dev | — | 1,181 |
| Code categories | — | 1,196 |
| ASCII art | — | 1,167 |
| Specs | ||
| Context window | 1.05M | 262K |
| Max output tokens | 128K | 230K |
| Input modalities | file, image, text | text, image, video |
| Tokenizer | GPT | Other |