Kimi K2

Moonshot AI llm

A 1-trillion-parameter (32B active) mixture-of-experts model from Moonshot AI built and post-trained for agentic tool-use and coding tasks.

overall ⌄

34.1

80 of 93 ranked

price · $/M tokens

self-hosted

open weights, no first-party API

to run it yourself ⌄

600 GB

minimum · 2.4 TB recommended

Benchmarks

What its maker published, and what anyone else measured. Every figure links the document it came from.

benchmarkpublishedmeasured
MMLU-Pro81.1
GPQA75.1
AIME 202549.5
SWE-bench65.8

Lineage

↓ finetune Kimi K2.5
view in full graph →

Metadata

orgMoonshot AI
released2025-07-11
params1T-A32B
licensemodified-mit
hf idmoonshotai/Kimi-K2-Instruct