Side-by-side comparison of Grok 2 (xAI) and Claude 3.5 Haiku (Anthropic) — benchmarks, pricing, and capabilities.
| Grok 2 xAI | Claude 3.5 Haiku Anthropic | |
|---|---|---|
| Category | LLMs | LLMs |
| Specifications | ||
| Context Window | 128K | 200K |
| Pricing (per 1M tokens) | ||
| Input Cost | $2.00 | $0.80 |
| Output Cost | $10.00 | $4.00 |
| Performance | ||
| Overall Score | 89.0 | 84.0 |
| ARC-Challenge | 92.5 | — |
| BigBench Hard | — | 78.0 |
| Chatbot Arena ELO | 1124.0 | — |
| GSM8K | 67.3 | 86.5 |
| HumanEval | 88.4 | 80.5 |
| MATH | 76.1 | 65.0 |
| MMLU | 87.5 | 81.5 |
| TruthfulQA | 73.4 | — |
| WinoGrande | 75.6 | — |
| Community | ||
| User Rating | ★ 4.4 | ★ 4.4 |
| Reviews | 380 | 290 |