Compare AI models

Specifications
Parameters
—7B
Context window
100k32k
Benchmarks
HumanEval
71.2%38.4%
Overview
CompanyAnthropicMistral
Release dateJul 11 2023May 22 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 2 leads Mistral 7B v0.3 on 1 of the 1 benchmark they both report (HumanEval). Claude 2 shipped 316 days before Mistral 7B v0.3, so benchmark comparisons should account for the intervening progress.

Context windows are 100k (Claude 2) vs 32k (Mistral 7B v0.3). Claude 2 is closed, while Mistral 7B v0.3 is open weight.

On HumanEval, Claude 2 leads at 71.2% vs Mistral 7B v0.3 at 38.4%.