Codestral 25.01vsKimi K2 Thinking

Codestral 25.01
Kimi K2 Thinking
Specifications
Parameters
1T
Context window
256k256k
API pricing
Cheapest input
$0.60Google
Cheapest output
$2.50Google
Benchmarks
SWE-Bench Verified
71.3%
Overview
CompanyMistralMoonshot AI
Release dateJan 13 2025Nov 6 2025
AccessProprietaryOpen Weight

Other comparisons

Codestral 25.01vsClaude Opus 5Kimi K2 ThinkingvsClaude Opus 5Codestral 25.01vsGPT-5.6 SolKimi K2 ThinkingvsGPT-5.6 SolCodestral 25.01vsGemini 3.7 FlashKimi K2 ThinkingvsGemini 3.7 FlashCodestral 25.01vsMuse GlimmerKimi K2 ThinkingvsMuse GlimmerCodestral 25.01vsGrok 4.6Kimi K2 ThinkingvsGrok 4.6Codestral 25.01vsDeepSeek-V4-Pro-0813Kimi K2 ThinkingvsDeepSeek-V4-Pro-0813

Frequently asked questions

Codestral 25.01 and Kimi K2 Thinking don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Codestral 25.01 shipped 297 days before Kimi K2 Thinking, so benchmark comparisons should account for the intervening progress.

Context windows are 256k (Codestral 25.01) vs 256k (Kimi K2 Thinking). Codestral 25.01 is proprietary, while Kimi K2 Thinking is open weight.

Direct benchmark comparisons are unavailable — Codestral 25.01 and Kimi K2 Thinking don't publish scores on any of the same benchmarks.

Codestral 25.01 was released by Mistral on Jan 13 2025.

Kimi K2 Thinking was released by Moonshot AI on Nov 6 2025.

Codestral 25.01 has a 256k context window; Kimi K2 Thinking has 256k.

Codestral 25.01 is a proprietary model released by Mistral. Kimi K2 Thinking is an open weight model released by Moonshot AI.