LLMOpen weights

Llama 3 70B Instruct

Meta

Updated May 22, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type: LLM
Access: Open weights
Released: April 18, 2024
Context window: 8,192 tokens
Knowledge cutoff: December 31, 2023
Output speed: 45 tok/s
Latency (TTFT): 0.7s
Input: Text
Output: Text
API pricing: $0.51 in · $0.74 out / 1M tokens

Capabilities

Structured output

Benchmarks

Reasoning

37.9

Coding

19.8

Math

48.3

General

MMLU-Pro	57.4
Humanity’s Last Exam	4.4

Compare Llama 3 70B Instruct with

vs Sonar Reasoning Pro vs R1 1776 vs Qwen3.7 Max vs Gemini 3.5 Flash

See all Llama 3 70B Instruct alternatives →