Compare AI models

Specifications
Parameters
—1T
Context window
40k256k
API pricing
Cheapest input
—$0.49AtlasCloud
Cheapest output
—$2.50AtlasCloud
—$223AtlasCloud · int4
Benchmarks
LiveCodeBench
59.35%85%
GPQA Diamond
71.46%87.6%
Overview
CompanyMistralMoonshot AI
Release dateJul 24 2025Jan 27 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2.5 leads Magistral Medium 1.1 on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Magistral Medium 1.1 shipped 187 days before Kimi K2.5, so benchmark comparisons should account for the intervening progress.

Context windows are 40k (Magistral Medium 1.1) vs 256k (Kimi K2.5). Magistral Medium 1.1 is closed, while Kimi K2.5 is open weight.

On LiveCodeBench, Kimi K2.5 leads at 85% vs Magistral Medium 1.1 at 59.35%. On GPQA Diamond, Kimi K2.5 leads at 87.6% vs Magistral Medium 1.1 at 71.46%.