Compare AI models

Specifications
Parameters
—117B
Context window
40k128k
API pricing
Cheapest input
—$0.03AkashML
Cheapest output
—$0.15Near AI
—$13.50Venice · int4
Benchmarks
AIME 2024
72.03%95.8%
AIME 2025
60.99%92.5%
GPQA Diamond
71.46%80.1%
Overview
CompanyMistralOpenAI
Release dateJul 24 2025Aug 5 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

gpt-oss-120b leads Magistral Medium 1.1 on 3 of the 3 benchmarks they both report (AIME 2024, AIME 2025, GPQA Diamond). Magistral Medium 1.1 shipped 12 days before gpt-oss-120b, so benchmark comparisons should account for the intervening progress.

Context windows are 40k (Magistral Medium 1.1) vs 128k (gpt-oss-120b). Magistral Medium 1.1 is closed, while gpt-oss-120b is open weight.

On AIME 2024, gpt-oss-120b leads at 95.8% vs Magistral Medium 1.1 at 72.03%. On AIME 2025, gpt-oss-120b leads at 92.5% vs Magistral Medium 1.1 at 60.99%. On GPQA Diamond, gpt-oss-120b leads at 80.1% vs Magistral Medium 1.1 at 71.46%.