LLMOpen weights

Llama 3.3 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: December 6, 2024
License: llama_3_3_community_license_agreement
Context window: 131,072 tokens
Knowledge cutoff: December 31, 2023
Output speed: 2220 tok/s
Latency (TTFT): 0.5s
Input: Text
Output: Text
API pricing: $0.10 in · $0.32 out / 1M tokens

Capabilities

Function callingStructured output

Benchmarks

Reasoning

50.5

Coding

HumanEval	88.4
LiveCodeBench	28.8

Math

MATH	77
MGSM	91.1
AIME 2025	7.7
MATH-500	77.3

General

IFEval	92.1
MMLU	86
MMLU-Pro	68.9
Humanity’s Last Exam	4

Compare Llama 3.3 70B Instruct with

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

See all Llama 3.3 70B Instruct alternatives →