Compare AI models

Specifications
Parameters
—9B
Context window
256k128k
Benchmarks
LiveCodeBench
37.9%28.5%
HumanEval
86.6%82.3%
Overview
CompanyMistralZ.ai
Release dateJan 13 2025Jul 5 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Codestral 25.01 leads CodeGeeX4-ALL-9B on 2 of the 2 benchmarks they both report (LiveCodeBench, HumanEval). CodeGeeX4-ALL-9B shipped 192 days before Codestral 25.01, so benchmark comparisons should account for the intervening progress.

Context windows are 256k (Codestral 25.01) vs 128k (CodeGeeX4-ALL-9B). Codestral 25.01 is closed, while CodeGeeX4-ALL-9B is open weight.

On LiveCodeBench, Codestral 25.01 leads at 37.9% vs CodeGeeX4-ALL-9B at 28.5%. On HumanEval, Codestral 25.01 leads at 86.6% vs CodeGeeX4-ALL-9B at 82.3%.