Compare AI models

Specifications
Parameters
24B1T
Context window
128k256k
API pricing
Cheapest input
—$0.60Novita
Cheapest output
—$2.50Novita
—$245Novita · bf16
Benchmarks
SWE-Bench Verified
53.6%71.3%
Overview
CompanyMistralMoonshot AI
Release dateJul 10 2025Nov 6 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2 Thinking leads Devstral Small 1.1 on 1 of the 1 benchmark they both report (SWE-Bench Verified). Devstral Small 1.1 shipped 119 days before Kimi K2 Thinking, so benchmark comparisons should account for the intervening progress.

Devstral Small 1.1 has 24B parameters, while Kimi K2 Thinking has 1T. Context windows are 128k (Devstral Small 1.1) vs 256k (Kimi K2 Thinking).

On SWE-Bench Verified, Kimi K2 Thinking leads at 71.3% vs Devstral Small 1.1 at 53.6%.