Kimi K2.7 Code

Leaderboards

Where Kimi K2.7 Code sits among the top 20 in each category.

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Test results

Every test Kimi K2.7 Code has a published result on, out of 100%, with its rank among the models that took it.

• DeepSWE 1.1

  #48 / 50

  DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.

  31.0%

  Self-reported · In the coding score

• LiveBench

  #27 / 38

  LiveBench is a challenging, contamination-limited LLM benchmark that addresses test set contamination by releasing new questions monthly based on recently-released datasets, arXiv papers, news articles, and IMDb movie synopses. It comprises tasks across math, coding, reasoning, language, instruction following, and data analysis with verifiable, objective ground-truth answers.

  71.9%

  Self-reported · In the text score

• MCP Atlas

  #14 / 38

  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.

  76.0%

  Self-reported

• FrontierCode 1.1

  #19 / 23

  FrontierCode 1.1 evaluates whether coding-agent changes are mergeable, using unit tests, maintainer-defined rubrics, and verifiers. Runs flagged for unfair internet use receive a zero score.

  30.1%

  Self-reported · In the coding score

• Program Bench

  #8 / 18

  Program Bench evaluates code-generation agents by asking them to recreate a program's behavior from only a compiled binary and documentation. It spans 200 tasks from small CLI tools to large systems such as FFmpeg and SQLite, with submissions judged against more than 248,000 fuzz-generated behavioral tests.

  53.6%

  Self-reported · In the coding score

• MCP-Mark

  #1 / 9

  MCP-Mark evaluates LLMs on their ability to use Model Context Protocol (MCP) tools effectively, testing tool discovery, selection, invocation, and result interpretation across diverse MCP server scenarios.

  81.1%

  Self-reported

• MLS-Bench Lite

  #3 / 3

  MLS-Bench Lite is the official 30-task subset of MLS-Bench for evaluating whether AI systems can invent generalizable and scalable machine learning methods across LLM pretraining and post-training, robotics, world models, computer vision, reinforcement learning, optimization, ML systems, and AI for Science.

  35.1%

  Self-reported

• Kimi Code Bench v2

  #2 / 2

  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.

  62.0%

  Unverified

• Kimi Claw 24/7 Bench

  #1 / 1

  Kimi Claw 24/7 Bench is Moonshot AI's in-house benchmark for evaluating long-horizon agentic performance in persistent, multi-day coworking tasks. It spans 17 professional scenarios across 610 evaluation points, covering software engineering, ML research, recruiting, trading, and marketing tasks executed through the OpenClaw harness.

  46.9%

  Unverified