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 4.3
| Claude Opus 4.6 Anthropic | Grok 4.3 xAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $5.00 | $1.25 |
| Output $/1M | $25.00 | $2.50 |
| Blended $/1M (3:1) | $10.00 | $1.56 |
| Cache read $/1M | $0.50 | $0.20 |
| Cache write $/1M | $6.25 | — |
| Quality indices | ||
| Intelligence Index | 37.8 | 37.6 |
| Coding Index | — | 42.2 |
| Math Index | — | — |
| Agentic Index | — | 24.1 |
| Speed & latency | ||
| Output speed (tok/s) | 54 | 122 |
| Time to first token | 1.89s | 32.04s |
| Time to first answer token | 1.89s | 32.04s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 84.0% | 90.1% |
| Humanity's Last Exam | 18.6% | 35.0% |
| SciCode | 45.7% | 47.3% |
| IFBench | 44.6% | 81.3% |
| AA-LCR (Long Context Reasoning) | 58.3% | 64.3% |
| Terminal-Bench Hard | 48.5% | 37.9% |
| Terminal-Bench 2.1 | — | 39.7% |
| τ²-Bench (Telecom) | 84.8% | 97.7% |
| τ³-Bench Banking | — | 12.2% |
| Design Arena (Elo) | ||
| Website | 1,323 | 1,221 |
| Web apps | 1,261 | 1,179 |
| Full-stack | 1,279 | 1,070 |
| Mobile apps | 1,280 | 1,130 |
| Android native | 1,195 | 1,056 |
| UI components | 1,336 | 1,236 |
| Data viz | 1,322 | 1,222 |
| SVG | 1,274 | 1,128 |
| 3D | 1,335 | 1,182 |
| Game dev | 1,337 | 1,235 |
| Agentic game dev | — | 1,017 |
| Godot game dev | — | 1,061 |
| HTML slides | — | 1,045 |
| 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 | 1,327 | 1,221 |
| ASCII art | 1,298 | 1,184 |
| Specs | ||
| Context window | 1M | 1M |
| Max output tokens | 128K | — |
| Input modalities | text, image, file | text, image, file |
| Tokenizer | Claude | Grok |