Side-by-side comparison of Claude 3.5 Sonnet (Anthropic) and Grok 2 (xAI) — benchmarks, pricing, and capabilities.
| Claude 3.5 Sonnet Anthropic | Grok 2 xAI | |
|---|---|---|
| Category | LLMs | LLMs |
| Specifications | ||
| Context Window | 200K | 128K |
| Pricing (per 1M tokens) | ||
| Input Cost | $3.00 | $2.00 |
| Output Cost | $15.00 | $10.00 |
| Performance | ||
| Overall Score | 91.2 | 89.0 |
| ARC-Challenge | 93.9 | 92.9 |
| BigBench Hard | 86.0 | — |
| Chatbot Arena ELO | 1242.0 | 1211.0 |
| DROP | 86.5 | — |
| GSM8K | 94.1 | 86.2 |
| HumanEval | 90.2 | 88.4 |
| MATH | 75.2 | 76.1 |
| MMLU | 88.1 | 87.5 |
| TruthfulQA | 77.4 | 79.5 |
| WinoGrande | 83.7 | 84.0 |
| Community | ||
| User Rating | ★ 4.6 | ★ 4.4 |
| Reviews | 890 | 380 |