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 SolGrok 4.20
| GPT-5.6 Sol OpenAI | Grok 4.20 xAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $5.00 | $1.25 |
| Output $/1M | $30.00 | $2.50 |
| Blended $/1M (3:1) | $11.25 | $1.56 |
| Cache read $/1M | $0.50 | $0.20 |
| Cache write $/1M | $6.25 | — |
| Quality indices | ||
| Intelligence Index | 58.9 | 37 |
| Coding Index | 77.4 | — |
| Math Index | — | — |
| Agentic Index | 54 | — |
| Speed & latency | ||
| Output speed (tok/s) | 67 | 230 |
| Time to first token | 120.38s | 16.10s |
| Time to first answer token | 120.38s | 16.10s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 94.1% | 91.1% |
| Humanity's Last Exam | 47.2% | 32.2% |
| SciCode | 56.1% | 45.6% |
| IFBench | 72.7% | 81.2% |
| AA-LCR (Long Context Reasoning) | 73.7% | 58.0% |
| Terminal-Bench Hard | 65.9% | 37.9% |
| Terminal-Bench 2.1 | 88.0% | — |
| τ²-Bench (Telecom) | 85.1% | 93.0% |
| τ³-Bench Banking | 33.0% | — |
| Design Arena (Elo) | ||
| Website | — | 1,255 |
| Web apps | — | 1,200 |
| Full-stack | — | 1,111 |
| Mobile apps | — | 1,181 |
| Android native | — | 1,154 |
| UI components | — | 1,245 |
| Data viz | — | 1,241 |
| SVG | — | 1,211 |
| 3D | — | 1,249 |
| Game dev | — | 1,255 |
| Godot game dev | — | 1,089 |
| HTML slides | — | 1,180 |
| Code categories | — | 1,252 |
| ASCII art | — | 1,219 |
| Specs | ||
| Context window | 1.05M | 2M |
| Max output tokens | 128K | — |
| Input modalities | file, image, text | text, image, file |
| Tokenizer | GPT | Grok |