modelbenchmark.io

Llama 3.1 8B Instruct

Meta · llama-3-1-8b

Compare

Open Llama instruction model for multilingual chat, reasoning, and coding

Specification

most-agreed values

Context
128K
Max output
8K
Released
2024-07-23
Knowledge cutoff
2023-12
Retires
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.22
Output
$0.22

Quality

4 benchmarks · 1 source

Composite
11th
percentile of 334 scored models
Rank
296 / 334
±0.07 sd
Evidence
4 × 1
one source, or fewer than 3 benchmarks
Effort range
one configuration only
reasoning11th2/4 bench
math12th2/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
Chess Puzzles0.0 ±0.0defaultEpoch AI2026-08-27
MATH level 522.9 ±0.9defaultEpoch AI2025-01-27
OTIS Mock AIME 2024-20251.7 ±0.9defaultEpoch AI2026-08-27
GPQA diamond27.0 ±1.9defaultEpoch AI2026-08-27

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
llamagate · llamagate$0.03$0.05131K8K
vercel_ai_gateway · vercel-ai-gateway$0.05$0.08131K131K
vercel$0.22$0.22128K8K

Other listings of this model

this page is one of them

The corpus files Llama 3.1 8B Instruct under several keys. This page is the llama-3-1-8b listing. The full record — every host, every price and every benchmark score — is on the main Llama 3.1 8B Instruct page.

More from Meta

most-hosted first