Side-by-side comparison of Grok 2 (xAI) and Mistral Large (Mistral AI) — benchmarks, pricing, and capabilities.
| Grok 2 xAI | Mistral Large Mistral AI | |
|---|---|---|
| Category | LLMs | LLMs |
| Specifications | ||
| Context Window | 128K | 128K |
| Pricing (per 1M tokens) | ||
| Input Cost | $2.00 | $2.00 |
| Output Cost | $10.00 | $6.00 |
| Performance | ||
| Overall Score | 89.0 | 87.1 |
| ARC-Challenge | 94.9 | 90.3 |
| BigBench Hard | — | 80.1 |
| Chatbot Arena ELO | 1185.0 | 1286.0 |
| DROP | — | 80.5 |
| GSM8K | 64.7 | 67.5 |
| HumanEval | 88.4 | 84.2 |
| MATH | 76.1 | 68.2 |
| MMLU | 87.5 | 83.5 |
| TruthfulQA | 61.9 | 63.8 |
| WinoGrande | 80.1 | 78.9 |
| Community | ||
| User Rating | ★ 4.4 | ★ 4.3 |
| Reviews | 380 | 312 |