Llama 3.1 8B

Meta · meta/llama-3-1-8b

Provider	Meta
Family	llama
Type	llm-chat
Status	active
Released	2024-07-14

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.

Benchmark	Catalogue standing	Score
Arena Elo — Coding	unassessed	1160
Arena Elo — Math	unassessed	1150
Arena Elo — Overall (Text)	unassessed	1170
Artificial Analysis Intelligence Index	unassessed	62
Artificial Analysis Output Speed	unassessed	92
BIG-Bench Hard	unassessed	39.2
BBQ (Bias Benchmark for QA)	unassessed	72.8
GPQA Diamond	unassessed	28.5
HELM Safety	unassessed	78.5
HumanEval	unassessed	55.5
IFEval	unassessed	62
MATH-500	unassessed	42
MMLU-Pro	unassessed	40.5
MuSR	unassessed	12.8
ToxiGen	unassessed	82.1

Data

This card as JSON · Edit on GitHub