Kimi Research

Our research seeks the optimal conversion from energy into intelligence.

Kimi K3

2026-07-16

PerceptionBench

PerceptionBench

2026-07-16

Kimi K2.6

2026-04-20

Agent Swarm

2026-02-09

WorldVQA

2026-02-03

Kimi K2.5

2026-01-27

Kimi Vendor Verifier

Kimi Vendor Verifier

2026-01-22

Kimi K2 Thinking

Kimi K2 Thinking

2025-11-06

Kimi-K2-Instruct-0905

Kimi-K2-Instruct-0905

2025-09-05

Kimi K2

2025-07-11

Kimi-Researcher

Kimi-Researcher

2025-06-20

Kimi-Dev

2025-06-17

Kimi-Audio

2025-04-26

Kimina-Prover Preview

Kimina-Prover Preview

2025-04-15

Kimi-VL

2025-04-10

Muon is Scalable for LLM Training

Muon is Scalable for LLM Training

2025-02-23

MoBA: Mixture of Block Attention for Long-Context LLMs

MoBA: Mixture of Block Attention for Long-Context LLMs

2025-02-18

Kimi K1.5: Scaling Reinforcement Learning with LLMs

Kimi K1.5: Scaling Reinforcement Learning with LLMs

2025-01-20

Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

2024-06-26