Compare AI models

Specifications
Parameters
70B24B
Context window
16k128k
These models have no shared benchmark scores.
Overview
CompanyMetaMistral
Release dateJan 29 2024Jul 10 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Code Llama 70B and Devstral Small 1.1 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Code Llama 70B shipped 528 days before Devstral Small 1.1, so benchmark comparisons should account for the intervening progress.

Code Llama 70B has 70B parameters, while Devstral Small 1.1 has 24B. Context windows are 16k (Code Llama 70B) vs 128k (Devstral Small 1.1).

Direct benchmark comparisons are unavailable — Code Llama 70B and Devstral Small 1.1 don't publish scores on any of the same benchmarks.