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 4.5
| Claude Opus 4.6 Anthropic | Grok 4.5 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 | $0.30 |
| Cache write $/1M | $6.25 | — |
| Quality indices | ||
| Intelligence Index | 37.8 | 53.8 |
| Coding Index | — | 72.4 |
| Math Index | — | — |
| Agentic Index | — | 45.7 |
| Speed & latency | ||
| Output speed (tok/s) | 54 | 73 |
| Time to first token | 1.89s | 9.69s |
| Time to first answer token | 1.89s | 9.69s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 84.0% | 93.1% |
| Humanity's Last Exam | 18.6% | 40.3% |
| SciCode | 45.7% | 54.1% |
| IFBench | 44.6% | — |
| AA-LCR (Long Context Reasoning) | 58.3% | 67.7% |
| Terminal-Bench Hard | 48.5% | — |
| Terminal-Bench 2.1 | — | 81.6% |
| τ²-Bench (Telecom) | 84.8% | — |
| τ³-Bench Banking | — | 32.6% |
| Design Arena (Elo) | ||
| Website | 1,323 | 1,323 |
| Web apps | 1,261 | 1,270 |
| Full-stack | 1,279 | 1,302 |
| Mobile apps | 1,280 | — |
| Android native | 1,195 | 1,263 |
| UI components | 1,336 | 1,331 |
| Data viz | 1,322 | 1,302 |
| SVG | 1,274 | — |
| 3D | 1,335 | 1,329 |
| Game dev | 1,337 | 1,330 |
| Agentic game dev | — | 1,227 |
| Godot game dev | — | 1,297 |
| HTML slides | — | 1,240 |
| Python→PPTX slides | — | 1,230 |
| Code categories | 1,327 | 1,323 |
| ASCII art | 1,298 | — |
| Specs | ||
| Context window | 1M | 500K |
| Max output tokens | 128K | — |
| Input modalities | text, image, file | text, image, file |
| Tokenizer | Claude | Grok |