Home/Models/Kimi K2.6
moonshotai logo

Kimi K2.6

by moonshotai · Released Apr 2026

Open SourceMultimodal
61.7
avg score
Rank #78
Compare
Better than 72% of all models
Context
262K tokens (~131 books)
Input $/1M
$0.95
Output $/1M
$4.00
Type
multimodal
License
Open Source
Benchmarks
15 tested
Data updated today
About

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

Tested on 15 benchmarks with 51.7% average. Top scores: Chatbot Arena Elo — Coding (1513.5%), Chatbot Arena Elo — Overall (1460.2%), OTIS Mock AIME 2024-2025 (96.1%).

Looking for similar performance at lower cost?
gpt-oss-20b (free) scores 61.0 (99% as good) at $0.00/1M input · 100% cheaper
Capabilities
coding
66.3
#28 globally
math
46.5
#101 globally
knowledge
50.8
#117 globally
speed
71.7
#25 globally
Benchmark Scores
Compare All
Tested on 15 benchmarks · Ranked across 5 categories
Score Distribution (all 274 models)
0255075100
▲ You are here
SWE-Bench verified

Real-world software engineering tasks from GitHub issues. Models must diagnose bugs and write patches that pass test suites. Human-verified subset of SWE-bench.

76.7
WeirdML

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

55.9
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

96.1
FrontierMath-2025-02-28-Private

Original research-level math problems created by professional mathematicians. Problems are unpublished and cannot be memorized.

39.0
GPQA diamond

Graduate-level science questions written by PhD experts. Diamond subset contains questions where experts disagree, testing deep understanding.

87.7
SimpleQA Verified

Simple factual questions with verified correct answers. Tests accuracy of basic knowledge retrieval. Low scores indicate hallucination.

38.7
Chess Puzzles

Tactical chess puzzles testing pattern recognition and multi-move calculation. Measures strategic reasoning ability.

26.0
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
kimi-k2-6
Specifications
  • Typemultimodal
  • Context262K tokens (~131 books)
  • ReleasedApr 2026
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.006
Available On
moonshotai logomoonshotai$0.95
Share & Export
Tweet
Kimi K2.6 is an open-source multimodal AI model by moonshotai, released in April 2026. It has an average benchmark score of 61.7. Context window: 262K tokens.