Side-by-side comparison of GPT-4o (OpenAI) and Claude Computer Use (Anthropic) — benchmarks, pricing, and capabilities.
| GPT-4o OpenAI | Claude Computer Use Anthropic | |
|---|---|---|
| Category | LLMs | AI Agents |
| 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 | 86.0 |
| ARC-Challenge | 96.9 | — |
| BigBench Hard | 87.2 | — |
| Chatbot Arena ELO | 1270.0 | — |
| DROP | 88.1 | — |
| GSM8K | 95.3 | — |
| HumanEval | 92.0 | — |
| MATH | 76.6 | — |
| MMLU | 88.2 | — |
| SWE-bench Verified | — | 49.0 |
| TruthfulQA | 79.5 | — |
| WinoGrande | 89.6 | — |
| Community | ||
| User Rating | ★ 4.7 | ★ 4.3 |
| Reviews | 1240 | 210 |