Compare AI models

Specifications
Parameters
70B7B
Context window
128k32k
API pricing
Cheapest input
$0.10DeepInfra—
Cheapest output
$0.32DeepInfra—
$36.00DeepInfra · turbo · fp8—
Benchmarks
HumanEval
88.4%38.4%
MATH
77%13.2%
Overview
CompanyMetaMistral
Release dateDec 6 2024May 22 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3.3 leads Mistral 7B v0.3 on 2 of the 2 benchmarks they both report (HumanEval, MATH). Mistral 7B v0.3 shipped 198 days before LLaMA 3.3, so benchmark comparisons should account for the intervening progress.

LLaMA 3.3 has 70B parameters, while Mistral 7B v0.3 has 7B. Context windows are 128k (LLaMA 3.3) vs 32k (Mistral 7B v0.3).

On HumanEval, LLaMA 3.3 leads at 88.4% vs Mistral 7B v0.3 at 38.4%. On MATH, LLaMA 3.3 leads at 77% vs Mistral 7B v0.3 at 13.2%.