Llama 3.1 40B Instruct

NEW HOT

Meta AI · Llama

Open SourceAPI

An advanced instruction-tuned model from the Llama family, offering strong performance for general language tasks and coding assistance.

TextCodeReasoning

Scores 82% on MMLU, competitive across 4 standard benchmarks.

Data aggregated and editorially reviewed by TrendMing.

Benchmark Performance

MMLU82%
HumanEval78%
MATH55%
GPQA40%

Scores sourced from published evaluations. Higher = better.

Quick Specs

Context Window64K tokens
Parameters40B
Input pricingN/A (self-hosted)
Output pricingN/A (self-hosted)
Released2026-03-15