Compare AI models

Specifications
Parameters
—24B
Context window
200k128k
Benchmarks
SWE-Bench Verified
40.6%53.6%
Overview
CompanyAnthropicMistral
Release dateOct 22 2024Jul 10 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Devstral Small 1.1 leads Claude 3.5 Haiku on 1 of the 1 benchmark they both report (SWE-Bench Verified). Claude 3.5 Haiku shipped 261 days before Devstral Small 1.1, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3.5 Haiku) vs 128k (Devstral Small 1.1). Claude 3.5 Haiku is closed, while Devstral Small 1.1 is open weight.

On SWE-Bench Verified, Devstral Small 1.1 leads at 53.6% vs Claude 3.5 Haiku at 40.6%.