Side-by-side comparison of text-embedding-3-large (OpenAI) and Llama 3.1 405B (Meta) — benchmarks, pricing, and capabilities.
| text-embedding-3-large OpenAI | Llama 3.1 405B Meta | |
|---|---|---|
| Category | Embedding Models | LLMs |
| Specifications | ||
| Context Window | 8K | 128K |
| Pricing (per 1M tokens) | ||
| Input Cost | $0.13 | Free |
| Output Cost | — | Free |
| Performance | ||
| Overall Score | 91.0 | 88.4 |
| ARC-Challenge | — | 87.6 |
| BigBench Hard | — | 82.3 |
| Chatbot Arena ELO | — | 1126.0 |
| DROP | — | 82.0 |
| GSM8K | — | 69.7 |
| HumanEval | — | 85.0 |
| MATH | — | 70.1 |
| MMLU | — | 76.4 |
| MTEB | 64.6 | — |
| TruthfulQA | — | 65.2 |
| WinoGrande | — | 79.4 |
| Community | ||
| User Rating | ★ 4.5 | ★ 4.4 |
| Reviews | 890 | 420 |