MoonshotAI: Kimi K2 0905

● Excellent

by Moonshotai Intelligent Coding Rank #38 of 75

8.4
/ 10

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

Choose a model to compare against MoonshotAI: Kimi K2 0905

Specifications

Specifications for MoonshotAI: Kimi K2 0905
AttributeValue
Lab Moonshotai
Tags Intelligent Coding
Overall Score 8.4/10
Release Date 2025-09
Context Window 262,144 tokens
Input Price / 1M $0.60
Output Price / 1M $2.50
Input Modalities Text
Output Modalities Text

Strengths

  • Updated coding and reasoning capabilities
  • Competitive pricing at $0.60/$2.50
  • Strong Chinese+English bilingual performance
  • Agentic tool use

Weaknesses

  • Limited Western benchmark coverage
  • Smaller context window than leading models

Best For

  • Bilingual coding tasks
  • Chinese market applications
  • Cost-effective agent workflows

Sources & Further Reading

Related Models

Scores are aggregated from public benchmarks (MMLU, HumanEval, MATH, GSM8K, LMSYS) and normalized to a 1–10 scale. Methodology →