Side-by-side comparison of DeepSeek R1 (DeepSeek) and Grok 2 (xAI) — benchmarks, pricing, and capabilities.
| DeepSeek R1 DeepSeek | Grok 2 xAI | |
|---|---|---|
| Category | LLMs | LLMs |
| Specifications | ||
| Context Window | 128K | 128K |
| Pricing (per 1M tokens) | ||
| Input Cost | $0.55 | $2.00 |
| Output Cost | $2.19 | $10.00 |
| Performance | ||
| Overall Score | 92.0 | 89.0 |
| ARC-Challenge | — | 92.5 |
| BigBench Hard | 89.0 | — |
| Chatbot Arena ELO | — | 1124.0 |
| GSM8K | 97.3 | 67.3 |
| HumanEval | 90.5 | 88.4 |
| MATH | 93.5 | 76.1 |
| MMLU | 90.8 | 87.5 |
| TruthfulQA | — | 73.4 |
| WinoGrande | — | 75.6 |
| Community | ||
| User Rating | ★ 4.6 | ★ 4.4 |
| Reviews | 480 | 380 |