Compare AI models

Specifications
Context window
256k1M
Benchmarks
LiveCodeBench
37.9%37.8%
HumanEval
86.6%86.6%
Overview
CompanyMistralQwen
Release dateJan 13 2025Nov 15 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Codestral 25.01 leads Qwen2.5-Turbo (1M) on 1 of the 2 benchmarks they both report (LiveCodeBench, HumanEval). Qwen2.5-Turbo (1M) shipped 59 days before Codestral 25.01, so benchmark comparisons should account for the intervening progress.

Context windows are 256k (Codestral 25.01) vs 1M (Qwen2.5-Turbo (1M)).

On LiveCodeBench, Codestral 25.01 leads at 37.9% vs Qwen2.5-Turbo (1M) at 37.8%. On HumanEval, both models score 86.6%.