Home/AI Agents/CoDA-Bench
CoDA-Bench logo

CoDA-Bench

ruc-datalab/CoDA-Bench

Benchmark for code agents on data-intensive tasks

GraphCanon updated Oct 18, 2026 · GitHub synced Oct 18, 2026

48 stars1 forksLast push Sep 29, 2026 Python MIT

Decision brief

Unverified catalog guidance: CoDA-Bench provides secure isolation for evaluating code agents in data-intensive tasks via Docker-mode execution.

Good fit when

  • Unverified catalog guidance: When you aim to evaluate the reliability and security of an AI-powered code agent with strict control over network access and data isolation.
  • Unverified catalog guidance: For benchmarking purposes specifically involving complex, data-related tasks where reproducibility across different machines is crucial.

Avoid when

  • Unverified catalog guidance: If your project does not require Docker-level secure isolation or if the overhead of setting up a Docker environment is prohibitive for your workflow.
  • Unverified catalog guidance: When you are dealing with less complex data tasks that do not demand stringent security measures such as restricted network environments and resource limits.
Pricing:
freemium - Available under the MIT License, free to use but may require additional costs for API credentials if using external services like OpenAI's APIs.
Requirements:
Requires Docker

Observed Jul 16, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Active (19d since push)
As of Oct 18, 2026
Provenance
Not a fork · Organization account
As of Oct 18, 2026
Security (OSV)
No lockfile
As of Jul 15, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

Package installation is not established from the available documentation. Check the source repository for setup instructions.

git clone https://github.com/ruc-datalab/coda-bench
Source repository

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

CoDA-Bench is designed to evaluate the performance of AI-powered code agents in handling complex data-related tasks.

Capability facts

Docker
Docker configuration present

Source: dockerfile:docker/openhands/Dockerfile · Oct 18, 2026

CLI
Declared CLI entrypoint

Source: pyproject.toml:[project.scripts] · Oct 18, 2026

MCP server
Unknown; MCP server not established by this scan

Source: repo_scan · Oct 18, 2026

Languages
python

Source: github.language+pyproject.toml · Oct 18, 2026

Categories

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Documented Python runtime (not runtime-tested)Python

Source: README excerpt (readme_declaration_v2, Oct 18, 2026)

pip install -e .
Source link

Tags

README

🚀 Quick Start <img src="./assets/overview.png" style="height: 20em" Installation Run Evaluation (Docker Mode) Step 1: Build Docker Image Step 2: Set API Credentials Step 3: Run Evaluation ```bash Why Docker? Docker mode provides secure isolation : ✅ Agents cannot access benchmar...

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.