Side-by-side comparison of GPT-4o (OpenAI) and DeepSeek Coder V2 (DeepSeek) — benchmarks, pricing, and capabilities.
| GPT-4o OpenAI | DeepSeek Coder V2 DeepSeek | |
|---|---|---|
| Category | LLMs | Code Models |
| Specifications | ||
| Context Window | 128K | 128K |
| Pricing (per 1M tokens) | ||
| Input Cost | $2.50 | $0.14 |
| Output Cost | $10.00 | $0.28 |
| Performance | ||
| Overall Score | 92.5 | 84.5 |
| ARC-Challenge | 96.9 | 89.7 |
| BigBench Hard | 87.2 | — |
| Chatbot Arena ELO | 1270.0 | — |
| DROP | 88.1 | — |
| GSM8K | 73.5 | 83.2 |
| HumanEval | 92.0 | 90.8 |
| MATH | 76.6 | 59.8 |
| MBPP | — | 86.5 |
| MMLU | 88.7 | 78.2 |
| TruthfulQA | 72.2 | 72.7 |
| WinoGrande | 89.6 | 85.9 |
| Community | ||
| User Rating | ★ 4.7 | ★ 4.5 |
| Reviews | 1240 | 445 |