All comparisons
HumanEval 72.6 89.0 Massive Multitask Language Understanding 82.0 88.6 Instruction-Following Evaluation 77.8 — MMLU PRO 57.4 — HellaSwag — 95.8 Chatbot Arena — 1228.0 Google-Proof Q&A — 51.5
Llama 3 70B Instruct vs Llama 3.1 405B
Side-by-side comparison of specifications, capabilities, and pricing.
| Released | 2024-04-18 | 2024-07-23 |
| Context window | 8K | 128K |
| Parameters | 70B | 405B |
| Architecture | decoder only | decoder only |
| License | Open Source | Open Source |
| Knowledge cutoff | — | — |
Capabilities | ||
| Vision | ||
| Multimodal | ||
| Reasoning | ||
| Function calling | ||
| Tool use | ||
| Structured Outputs | ||
| Code execution | ||
Availability | ||
| Providers | — | |
Benchmarks