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.
Claude Opus 4.6Grok 4.6
| Claude Opus 4.6 Anthropic | Grok 4.6 xAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $5.00 | $2.00 |
| Output $/1M | $25.00 | $6.00 |
| Blended $/1M (3:1) | $10.00 | $3.00 |
| Cache read $/1M | $0.50 | $0.50 |
| Cache write $/1M | $6.25 | — |
| Quality indices | ||
| Intelligence Index | 26.4 | 44.3 |
| Coding Index | — | 76.8 |
| Math Index | — | — |
| Agentic Index | — | 53 |
| Speed & latency | ||
| Output speed (tok/s) | 0 | 58 |
| Time to first token | 0s | 34.50s |
| Time to first answer token | 0s | 34.50s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 84.0% | 94.9% |
| Humanity's Last Exam | 19.1% | 42.9% |
| SciCode | — | 56.5% |
| IFBench | 44.6% | — |
| AA-LCR (Long Context Reasoning) | 67.0% | 80.3% |
| Terminal-Bench Hard | 48.5% | — |
| Terminal-Bench 2.1 | — | 88.4% |
| τ²-Bench (Telecom) | 84.8% | — |
| τ³-Bench Banking | — | 50.7% |
| Design Arena (Elo) | ||
| Website | 1,303 | 1,304 |
| Web apps | 1,219 | 1,264 |
| Full-stack | 1,229 | 1,274 |
| Mobile apps | 1,238 | 1,267 |
| Android native | 1,216 | 1,301 |
| UI components | 1,300 | 1,305 |
| Data viz | 1,296 | 1,303 |
| SVG | 1,251 | 1,263 |
| 3D | 1,303 | 1,305 |
| Game dev | 1,301 | 1,321 |
| Agentic game dev | 1,215 | 1,210 |
| HTML slides | — | 1,253 |
| Python→PPTX slides | — | 1,242 |
| Code categories | 1,304 | 1,309 |
| ASCII art | 1,273 | 1,297 |
| Specs | ||
| Context window | 1M | 500K |
| Max output tokens | 128K | 450K |
| Input modalities | text, image, file | text, image, file |
| Tokenizer | Claude | Grok |