Side-by-side comparison of Claude 3 Opus (Anthropic) and Claude Computer Use (Anthropic) — benchmarks, pricing, and capabilities.
| Claude 3 Opus Anthropic | Claude Computer Use Anthropic | |
|---|---|---|
| Category | LLMs | AI Agents |
| Specifications | ||
| Context Window | 200K | 200K |
| Pricing (per 1M tokens) | ||
| Input Cost | $15.00 | $3.00 |
| Output Cost | $75.00 | $15.00 |
| Performance | ||
| Overall Score | 90.5 | 86.0 |
| ARC-Challenge | 90.7 | — |
| BigBench Hard | 84.5 | — |
| Chatbot Arena ELO | 1178.0 | — |
| DROP | 85.5 | — |
| GSM8K | 95.0 | — |
| HumanEval | 84.9 | — |
| MATH | 60.1 | — |
| MMLU | 86.8 | — |
| SWE-bench Verified | — | 49.0 |
| TruthfulQA | 66.9 | — |
| WinoGrande | 84.0 | — |
| Community | ||
| User Rating | ★ 4.6 | ★ 4.3 |
| Reviews | 720 | 210 |