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 (batch)
| Claude Opus 4.6 Anthropic | Grok 4.3 (batch) xAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $5.00 | $1.00 |
| Output $/1M | $25.00 | $2.00 |
| Blended $/1M (3:1) | $10.00 | $1.25 |
| Cache read $/1M | $0.50 | $0.16 |
| Cache write $/1M | $6.25 | — |
| Quality indices | ||
| Intelligence Index | 26.4 | 24.9 |
| Coding Index | — | 42.2 |
| Math Index | — | — |
| Agentic Index | — | 15.5 |
| Speed & latency | ||
| Output speed (tok/s) | 0 | 0 |
| Time to first token | 0s | 0s |
| Time to first answer token | 0s | 0s |
| Benchmarks (Artificial Analysis) | ||
| GPQA Diamond | 84.0% | 90.1% |
| Humanity's Last Exam | 19.1% | 37.2% |
| SciCode | — | 48.3% |
| IFBench | 44.6% | 81.3% |
| AA-LCR (Long Context Reasoning) | 67.0% | 73.0% |
| Terminal-Bench Hard | 48.5% | 37.9% |
| Terminal-Bench 2.1 | — | 39.7% |
| τ²-Bench (Telecom) | 84.8% | 97.7% |
| τ³-Bench Banking | — | 12.4% |
| Design Arena (Elo) | ||
| Website | 1,303 | 1,207 |
| Web apps | 1,219 | 1,144 |
| Full-stack | 1,229 | 1,017 |
| Mobile apps | 1,238 | 1,092 |
| Android native | 1,216 | 972 |
| UI components | 1,300 | 1,207 |
| Data viz | 1,296 | 1,197 |
| SVG | 1,251 | 1,109 |
| 3D | 1,303 | 1,154 |
| Game dev | 1,301 | 1,198 |
| Agentic game dev | 1,215 | 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 | 1,304 | 1,202 |
| ASCII art | 1,273 | 1,157 |
| Specs | ||
| Context window | 1M | 1M |
| Max output tokens | 128K | 900K |
| Input modalities | text, image, file | text, image, file |
| Tokenizer | Claude | Grok |