Side-by-side comparison of Claude Computer Use (Anthropic) and Codestral (Mistral AI) — benchmarks, pricing, and capabilities.
| Claude Computer Use Anthropic | Codestral Mistral AI | |
|---|---|---|
| Category | AI Agents | Code Models |
| Specifications | ||
| Context Window | 200K | 32K |
| Pricing (per 1M tokens) | ||
| Input Cost | $3.00 | $0.20 |
| Output Cost | $15.00 | $0.60 |
| Performance | ||
| Overall Score | 86.0 | 86.2 |
| GSM8K | — | 84.0 |
| HumanEval | — | 92.5 |
| MATH | — | 60.5 |
| MBPP | — | 88.0 |
| MMLU | — | 79.0 |
| SWE-bench Verified | 49.0 | — |
| Community | ||
| User Rating | ★ 4.3 | ★ 4.6 |
| Reviews | 210 | 289 |