Compare AI models

Specifications
Parameters
—21B
Context window
128k128k
API pricing
Cheapest input
—$0.018AkashML
Cheapest output
—$0.09AkashML
—$8.10Darkbloom · fp8
Benchmarks
GPQA Diamond
65.7%71.5%
Overview
CompanyMistralOpenAI
Release dateAug 12 2025Aug 5 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

gpt-oss-20b leads Mistral Medium 3.1 on 1 of the 1 benchmark they both report (GPQA Diamond). gpt-oss-20b shipped 7 days before Mistral Medium 3.1, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Mistral Medium 3.1) vs 128k (gpt-oss-20b). Mistral Medium 3.1 is closed, while gpt-oss-20b is open weight.

On GPQA Diamond, gpt-oss-20b leads at 71.5% vs Mistral Medium 3.1 at 65.7%.