Home/Models/Kimi K2 0711
moonshotai logo

Kimi K2 0711

by moonshotai · Released Jul 2025

Open Source
58.4
avg score
Rank #75
Compare
Better than 68% of all models
Context
131K tokens (~66 books)
Input $/1M
$0.57
Output $/1M
$2.30
Type
text
License
Open Source
Benchmarks
12 tested
Data updated today
About

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

Tested on 12 benchmarks with 56.2% average. Top scores: Lech Mazur Writing (86.9%), HELM — WildBench (86.2%), HELM — IFEval (85.0%).

Looking for similar performance at lower cost?
DeepSeek V3.2 scores 58.7 (101% as good) at $0.25/1M input · 56% cheaper
Capabilities
coding
32.8
#114 globally
reasoning
48.9
#49 globally
math
65.4
#39 globally
knowledge
73.8
#10 globally
language
85.0
#33 globally
Benchmark Scores
Compare All
Tested on 12 benchmarks · Ranked across 5 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
Aider polyglot

Multi-language code editing from Aider. Tests editing ability across Python, JavaScript, TypeScript, Java, C++, Go, Rust, and more.

59.1
WeirdML

Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.

39.4
Terminal Bench

Complex terminal-based engineering tasks. Models must use command-line tools, navigate filesystems, and debug systems through shell interaction.

27.8
HELM — WildBench

Stanford HELM WildBench evaluation. Tests reasoning on challenging real-world tasks.

86.2
SimpleBench

Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.

11.6
HELM — Omni-MATH

Stanford HELM evaluation of mathematical reasoning across diverse problem types.

65.4
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
kimi-k2
Specifications
  • Typetext
  • Context131K tokens (~66 books)
  • ReleasedJul 2025
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.003
Available On
moonshotai logomoonshotai$0.57
Share & Export
Tweet
Kimi K2 0711 is an open-source text AI model by moonshotai, released in July 2025. It has an average benchmark score of 58.4. Context window: 131K tokens.