Side-by-side comparison of GPT-4o (OpenAI) and Claude 3.5 Sonnet (Anthropic) — benchmarks, pricing, and capabilities.
| GPT-4o OpenAI | Claude 3.5 Sonnet Anthropic | |
|---|---|---|
| Category | LLMs | LLMs |
| Specifications | ||
| Context Window | 128K | 200K |
| Pricing (per 1M tokens) | ||
| Input Cost | $2.50 | $3.00 |
| Output Cost | $10.00 | $15.00 |
| Performance | ||
| Overall Score | 92.5 | 91.2 |
| ARC-Challenge | 94.7 | 96.2 |
| BigBench Hard | 87.2 | 86.0 |
| Chatbot Arena ELO | 1256.0 | 1104.0 |
| DROP | 88.1 | 86.5 |
| GSM8K | 86.9 | 94.1 |
| HumanEval | 92.0 | 90.2 |
| MATH | 76.6 | 75.2 |
| MMLU | 88.7 | 88.1 |
| TruthfulQA | 58.7 | 71.0 |
| WinoGrande | 77.4 | 82.0 |
| Community | ||
| User Rating | ★ 4.7 | ★ 4.6 |
| Reviews | 1240 | 890 |