Compare AI models

Specifications
Parameters
24B6B
Context window
32k8k
API pricing
Cheapest input
$0.04DeepInfra—
Cheapest output
$0.064DeepInfra—
$14.00DeepInfra · fp8—
Benchmarks
HumanEval
84.8%35.9%
Overview
CompanyMistralZ.ai
Release dateJan 30 2025Jul 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Small 3 leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 555 days before Mistral Small 3, so benchmark comparisons should account for the intervening progress.

Mistral Small 3 has 24B parameters, while CodeGeeX2-6B has 6B. Context windows are 32k (Mistral Small 3) vs 8k (CodeGeeX2-6B).

On HumanEval, Mistral Small 3 leads at 84.8% vs CodeGeeX2-6B at 35.9%.