Side-by-side comparison of Claude 3 Opus (Anthropic) and Codestral (Mistral AI) — benchmarks, pricing, and capabilities.
| Claude 3 Opus Anthropic | Codestral Mistral AI | |
|---|---|---|
| Category | LLMs | Code Models |
| Specifications | ||
| Context Window | 200K | 32K |
| Pricing (per 1M tokens) | ||
| Input Cost | $15.00 | $0.20 |
| Output Cost | $75.00 | $0.60 |
| Performance | ||
| Overall Score | 90.5 | 86.2 |
| ARC-Challenge | 90.7 | — |
| BigBench Hard | 84.5 | — |
| Chatbot Arena ELO | 1178.0 | — |
| DROP | 85.5 | — |
| GSM8K | 73.7 | 84.0 |
| HumanEval | 84.9 | 92.5 |
| MATH | 60.1 | 60.5 |
| MBPP | — | 88.0 |
| MMLU | 86.8 | 79.0 |
| TruthfulQA | 66.9 | — |
| WinoGrande | 84.0 | — |
| Community | ||
| User Rating | ★ 4.6 | ★ 4.6 |
| Reviews | 720 | 289 |