Llama 3.1 405B Instruct

Meta · meta/llama-3-1-405b-instruct

ProviderMeta
Familyllama
Typellm-chat
Statusactive
Released2024-07-16

Reported benchmark scores

These scores carry one collection date for the whole card (2026-04) and a source list rather than a source per score, so they cannot be attributed individually. They are shown as reported and are not verified evidence. Benchmark pages carry the reviewed, dated evidence where it exists.
BenchmarkCatalogue standingScore
AlpacaEvalunassessed39.3
Arena Elo — Codingunassessed1260.0
Arena Elo — Hard Promptsunassessed1340.1
Arena Elo — Mathunassessed1250.0
Arena Elo — Overall (Text)unassessed1270.0
Arena Elo — Style Controlunassessed1334.2
Artificial Analysis Intelligence Indexunassessed80.0
Artificial Analysis Output Speedunassessed45.0
GPQA Diamondunassessed49.8
GSM8Kunassessed96.8
HumanEvalunassessed81.2
IFEvalunassessed80.0
LiveCodeBenchunassessed30.5
MATH-500unassessed73.8
MedQAunassessed82.9
MMLU-Prounassessed67.5

Data

This card as JSON · Edit on GitHub