Side-by-side comparison of GPT-o1 (OpenAI) and DeepSeek Coder V2 (DeepSeek) — benchmarks, pricing, and capabilities.
| GPT-o1 OpenAI | DeepSeek Coder V2 DeepSeek | |
|---|---|---|
| Category | LLMs | Code Models |
| Specifications | ||
| Context Window | 200K | 128K |
| Pricing (per 1M tokens) | ||
| Input Cost | $15.00 | $0.14 |
| Output Cost | $60.00 | $0.28 |
| Performance | ||
| Overall Score | 93.5 | 84.5 |
| ARC-Challenge | — | 89.7 |
| BigBench Hard | 90.5 | — |
| DROP | 90.2 | — |
| GSM8K | 97.8 | 72.7 |
| HumanEval | 92.4 | 90.8 |
| MATH | 94.8 | 59.8 |
| MBPP | — | 86.5 |
| MMLU | 91.8 | 73.3 |
| TruthfulQA | 74.5 | 72.7 |
| WinoGrande | — | 85.9 |
| Community | ||
| User Rating | ★ 4.6 | ★ 4.5 |
| Reviews | 520 | 445 |