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 4.3 (batch)
| GPT-5.6 Sol OpenAI | Grok 4.3 (batch) xAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $2.00 | $1.00 |
| Output $/1M | $10.00 | $2.00 |
| Blended $/1M (3:1) | $4.00 | $1.25 |
| Cache read $/1M | $0.20 | $0.16 |
| Cache write $/1M | $2.50 | — |
| Quality indices | ||
| Intelligence Index | 47 | 24.9 |
| Coding Index | 77.4 | 42.2 |
| Math Index | — | — |
| Agentic Index | 50.2 | 15.5 |
| Speed & latency | ||
| Output speed (tok/s) | 65 | 0 |
| Time to first token | 64.46s | 0s |
| Time to first answer token | 64.46s | 0s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 94.1% | 90.1% |
| Humanity's Last Exam | 49.5% | 37.2% |
| SciCode | 57.1% | 48.3% |
| IFBench | 72.7% | 81.3% |
| AA-LCR (Long Context Reasoning) | 84.0% | 73.0% |
| Terminal-Bench Hard | 65.9% | 37.9% |
| Terminal-Bench 2.1 | 88.0% | 39.7% |
| τ²-Bench (Telecom) | 85.1% | 97.7% |
| τ³-Bench Banking | 44.3% | 12.4% |
| Design Arena (Elo) | ||
| Website | — | 1,207 |
| Web apps | — | 1,144 |
| Full-stack | — | 1,017 |
| Mobile apps | — | 1,092 |
| Android native | — | 972 |
| UI components | — | 1,207 |
| Data viz | — | 1,197 |
| SVG | — | 1,109 |
| 3D | — | 1,154 |
| Game dev | — | 1,198 |
| Agentic game dev | — | 1,007 |
| Godot game dev | — | 1,035 |
| HTML slides | — | 1,011 |
| PPTX slides | — | 1,071 |
| Python→PPTX slides | — | 1,072 |
| Agentic slides | — | 1,072 |
| Agentic HTML slides | — | 1,066 |
| Agentic slides (HTML) | — | 1,066 |
| Agentic slides (Python PPTX) | — | 1,068 |
| Code categories | — | 1,202 |
| ASCII art | — | 1,157 |
| Specs | ||
| Context window | 1.05M | 1M |
| Max output tokens | 128K | 900K |
| Input modalities | file, image, text | text, image, file |
| Tokenizer | GPT | Grok |