Kimi-Dev-72B
About Kimi-Dev-72B
Kimi-Dev-72B is a new open-source coding large language model achieving 60.4% on SWE-bench Verified, setting a state-of-the-art result among open-source models. Optimized through large-scale reinforcement learning, it autonomously patches real codebases in Docker and earns rewards only when full test suites pass. This ensures the model delivers correct, robust, and practical solutions aligned with real-world software engineering standards
Explore how Kimi-Dev-72B's state-of-the-art coding capabilities autonomously resolve complex software engineering challenges.
Automated Software Patching
Kimi-Dev-72B autonomously identifies and applies fixes to real-world software issues, ensuring patches pass all test suites in a Dockerized environment.
Use Case Example:
"Automatically resolved a critical bug in a Python web framework's authentication module, generating a robust patch that passed 100% of unit and integration tests."
Advanced Code Debugging & Optimization
Pinpoint subtle logical errors and suggest performance enhancements across large codebases, validated by passing comprehensive test suites.
Use Case Example:
"Optimized a Java microservice's database query logic, reducing latency by 30% and ensuring all existing integration tests continued to pass."
Test-Driven Feature Development
Accelerate development by generating new code features that are inherently robust, as they are designed to pass pre-defined or generated test cases.
Use Case Example:
"Developed a new data processing pipeline feature in Go, generating both the implementation and corresponding unit tests, ensuring immediate functional correctness."
Legacy Code Refactoring & Modernization
Transform outdated codebases into modern, maintainable systems, ensuring functional equivalence and test suite compatibility throughout the refactoring process.
Use Case Example:
"Refactored a legacy C# desktop application to use modern .NET asynchronous patterns, verifying functional integrity by ensuring all original UI and backend tests passed."
Metadata
Specification
State
Deprecated
Architecture
Qwen2
Calibrated
Yes
Mixture of Experts
No
Total Parameters
1000B
Activated Parameters
1000B
Reasoning
No
Precision
FP8
Context length
131K
Max Tokens
131K
Compare with Other Models
See how this model stacks up against others.
Moonshot AI
chat
Kimi-K2.5
Release on: Jan 30, 2026
Total Context:
262K
Max output:
262K
Input:
$
0.55
/ M Tokens
Output:
$
3.0
/ M Tokens
Moonshot AI
chat
Kimi-K2-Thinking
Release on: Nov 7, 2025
Total Context:
262K
Max output:
262K
Input:
$
0.55
/ M Tokens
Output:
$
2.5
/ M Tokens
Moonshot AI
chat
Kimi-K2-Instruct-0905
Release on: Sep 8, 2025
Total Context:
262K
Max output:
262K
Input:
$
0.4
/ M Tokens
Output:
$
2.0
/ M Tokens
Moonshot AI
chat
Kimi-K2-Instruct
Release on: Jul 13, 2025
Total Context:
131K
Max output:
131K
Input:
$
0.58
/ M Tokens
Output:
$
2.29
/ M Tokens
Moonshot AI
chat
Kimi-Dev-72B
Release on: Jun 19, 2025
Total Context:
131K
Max output:
131K
Input:
$
0.29
/ M Tokens
Output:
$
1.15
/ M Tokens
