Side-by-side comparison of Claude Computer Use (Anthropic) and Gemini 1.5 Pro (Google) — benchmarks, pricing, and capabilities.
| Claude Computer Use Anthropic | Gemini 1.5 Pro Google | |
|---|---|---|
| Category | AI Agents | LLMs |
| Specifications | ||
| Context Window | 200K | 1.0M |
| Pricing (per 1M tokens) | ||
| Input Cost | $3.00 | $1.25 |
| Output Cost | $15.00 | $5.00 |
| Performance | ||
| Overall Score | 86.0 | 90.8 |
| ARC-Challenge | — | 89.5 |
| BigBench Hard | — | 85.1 |
| Chatbot Arena ELO | — | 1126.0 |
| DROP | — | 85.8 |
| GSM8K | — | 93.2 |
| HumanEval | — | 89.1 |
| MATH | — | 74.0 |
| MMLU | — | 85.3 |
| SWE-bench Verified | 49.0 | — |
| TruthfulQA | — | 65.1 |
| WinoGrande | — | 84.2 |
| Community | ||
| User Rating | ★ 4.3 | ★ 4.5 |
| Reviews | 210 | 654 |