Compare AI models

Specifications
Parameters
8B/70B/405B24B
Context window
128k128k
API pricing
Cheapest input
$0.02DeepInfra—
Cheapest output
$0.04DeepInfra—
$6.00DeepInfra · fp8—
Benchmarks
GPQA Diamond
49%70.07%
Overview
CompanyMetaMistral
Release dateJul 23 2024Sep 17 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Magistral Small 1.2 leads LLaMA 3.1 on 1 of the 1 benchmark they both report (GPQA Diamond). LLaMA 3.1 shipped 421 days before Magistral Small 1.2, so benchmark comparisons should account for the intervening progress.

LLaMA 3.1 has 8B/70B/405B parameters, while Magistral Small 1.2 has 24B. Context windows are 128k (LLaMA 3.1) vs 128k (Magistral Small 1.2).

On GPQA Diamond, Magistral Small 1.2 leads at 70.07% vs LLaMA 3.1 at 49%.