Side-by-side comparison of Phi-3 Medium (Microsoft) and Llama 3.1 405B (Meta) — benchmarks, pricing, and capabilities.
| Phi-3 Medium Microsoft | Llama 3.1 405B Meta | |
|---|---|---|
| Category | LLMs | LLMs |
| Specifications | ||
| Context Window | 128K | 128K |
| Pricing (per 1M tokens) | ||
| Input Cost | Free | Free |
| Output Cost | Free | Free |
| Performance | ||
| Overall Score | 78.2 | 88.4 |
| ARC-Challenge | — | 91.8 |
| BigBench Hard | 68.0 | 82.3 |
| Chatbot Arena ELO | — | 1142.0 |
| DROP | 70.0 | 82.0 |
| GSM8K | 78.0 | 91.0 |
| HumanEval | 70.0 | 85.0 |
| MATH | 48.0 | 70.1 |
| MMLU | 78.0 | 84.2 |
| TruthfulQA | 52.0 | 65.1 |
| WinoGrande | — | 76.7 |
| Community | ||
| User Rating | ★ 4.2 | ★ 4.4 |
| Reviews | 312 | 420 |