Kimi Code Bench v2

Kimi Code Bench v2 is Moonshot AI's in-house benchmark for evaluating coding agents on realistic software engineering tasks across 10+ mainstream programming languages and a production tech stack spanning backend services, infrastructure, performance engineering, systems programming, security, frontend development, and ML/data engineering.

Kimi K2.7 Code from Moonshot AI currently leads the Kimi Code Bench v2 leaderboard with a score of 0.620 across 1 evaluated AI models.

About this benchmark

What Kimi Code Bench v2 measures

Kimi Code Bench v2 is a text benchmark that evaluates large language models on agents and coding tasks. LLM Stats tracks 1 model on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.6, with the leader reaching 0.6.

Compare leaders on the best AI for agents and best AI for coding leaderboards.

Moonshot AIKimi K2.7 Code leads with 62.0%.

Progress Over Time

Interactive timeline showing model performance evolution on Kimi Code Bench v2

State-of-the-art frontier
Open
Proprietary

Kimi Code Bench v2 Leaderboard

1 models
ContextCostLicense
1
Moonshot AI
Moonshot AI
1.0T262K$0.95 / $4.00
Notice missing or incorrect data?

FAQ

Common questions about Kimi Code Bench v2.

What is the Kimi Code Bench v2 benchmark?

Kimi Code Bench v2 is Moonshot AI's in-house benchmark for evaluating coding agents on realistic software engineering tasks across 10+ mainstream programming languages and a production tech stack spanning backend services, infrastructure, performance engineering, systems programming, security, frontend development, and ML/data engineering.

What is the Kimi Code Bench v2 leaderboard?

The Kimi Code Bench v2 leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, Kimi K2.7 Code by Moonshot AI leads with a score of 0.620. The average score across all models is 0.620.

What is the highest Kimi Code Bench v2 score?

The highest Kimi Code Bench v2 score is 0.620, achieved by Kimi K2.7 Code from Moonshot AI.

How many models are evaluated on Kimi Code Bench v2?

1 models have been evaluated on the Kimi Code Bench v2 benchmark, with 0 verified results and 1 self-reported results.

What categories does Kimi Code Bench v2 cover?

Kimi Code Bench v2 is categorized under agents and coding. The benchmark evaluates text models with multilingual support.

What is the best open-source model on Kimi Code Bench v2?

Kimi K2.7 Code by Moonshot AI is the top-ranked open-source model on Kimi Code Bench v2, with a score of 0.620 (rank #1).

Which model offers the best value on Kimi Code Bench v2?

Among models scoring within 10% of the leader, Kimi K2.7 Code from Moonshot AI is the cheapest, at $0.95 per million input tokens with a score of 0.620.

How recent are the Kimi Code Bench v2 leaderboard results?

The Kimi Code Bench v2 leaderboard was last updated in June 2026 and currently includes 1 evaluated models.

More evaluations to explore

Related benchmarks in the same category

View all agents
BrowseComp

BrowseComp is a benchmark comprising 1,266 questions that challenge AI agents to persistently navigate the internet in search of hard-to-find, entangled information. The benchmark measures agents' ability to exercise persistence in information gathering, demonstrate creativity in web navigation, and find concise, verifiable answers. Despite the difficulty of the questions, BrowseComp is simple and easy-to-use, as predicted answers are short and easily verifiable against reference answers.

agents
48 models
Terminal-Bench 2.0

Terminal-Bench 2.0 is an updated benchmark for testing AI agents' tool use ability to operate a computer via terminal. It evaluates how well models can handle real-world, end-to-end tasks autonomously, including compiling code, training models, setting up servers, system administration, security tasks, data science workflows, and cybersecurity vulnerabilities.

agents
46 models
SWE-Bench Pro

SWE-Bench Pro is an advanced version of SWE-Bench that evaluates language models on complex, real-world software engineering tasks requiring extended reasoning and multi-step problem solving.

agents
29 models
Terminal-Bench

Terminal-Bench is a benchmark for testing AI agents in real terminal environments. It evaluates how well agents can handle real-world, end-to-end tasks autonomously, including compiling code, training models, setting up servers, system administration, security tasks, data science workflows, and cybersecurity vulnerabilities. The benchmark consists of a dataset of ~100 hand-crafted, human-verified tasks and an execution harness that connects language models to a terminal sandbox.

agents
25 models
MCP Atlas

MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.

agents
23 models
t2-bench

t2-bench is a benchmark for evaluating agentic tool use capabilities, measuring how well models can select, sequence, and utilize tools to solve complex tasks. It tests autonomous planning and execution in multi-step scenarios.

agents
23 models