Co-Design-Bench
Co-Design-Bench is a benchmark that tests whether coding agents correctly revise existing web applications from real user requests for developers and researchers.
What it is good for
- Checking whether a coding agent correctly revises an existing web app
- Comparing how well different AI coding agents handle real user requests
- Scoring app changes against expert criteria using screenshots and source code
At a glance
- Who it is for
- Setup
- Requires programming
Level 5 of 5. You need to write code to use it.
- Cost
- Free and open source
- Type
- Other
- Tasks
- Works with
- Claude CLI, Node.js, Playwright, Chromium
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 56
GitHub numbers as of Nov 2, 2026. Updated weekly.
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is Co-Design-Bench free?
- Yes. It is free and open source.
- Do I need to know how to code to use Co-Design-Bench?
- Yes. You need to write code to use it.
- What does Co-Design-Bench work with?
- According to its own documentation, it works with Claude CLI, Node.js, Playwright, and Chromium.
- What is Co-Design-Bench good for?
- Checking whether a coding agent correctly revises an existing web app, comparing how well different AI coding agents handle real user requests, and scoring app changes against expert criteria using screenshots and source code.
Similar agents to Co-Design-Bench
- Parsimony
Parsimony is a benchmark that ranks AI coding models by how much extra code they add to fix bugs, for developers comparing models.
- Understand-Anything
Understand-Anything is a plugin that turns a codebase, knowledge base, or docs into an interactive graph you can explore and ask questions about, for people new to a project.
- DeerFlow
DeerFlow is an open-source super agent that researches topics, writes code, and creates content over tasks that take minutes to hours, for people who need multi-step work done.
- OmO
OmO is a coding agent app that turns a single prompt into finished software work for developers and builders who want agents to handle multi-step jobs.
- AgenticSeek
AgenticSeek is a self-hosted agent app that browses the web, writes code, and plans tasks for people who want to keep their data on their own machine.
- GitDiagram
GitDiagram is an MCP server and web tool that turns a GitHub repository into an architecture diagram or narrated video for people who need to understand a codebase.