CoDA-Bench
Enrichment pendingCoDA-Bench is a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?
GraphCanon updated today · GitHub synced today
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Active (28d since push)
- As of today
- Provenance
- Not a fork · Organization account
- As of today
- Security (OSV)
- No lockfile
- As of today
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install CoDA-BenchSimilar 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 a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?
Capability facts
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Jul 15, 2026
- Languages
- python
Source: github.language+pyproject.toml · Jul 15, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Jul 15, 2026)
export LLM_BASE_URL="https://api.openai.com/v1" # OptionalSource link
Tags
README
🚀 Quick Start
Installation
git clone https://github.com/ruc-datalab/CoDA-Bench.git
cd CoDA-Bench
pip install -e .
Run Evaluation (Docker Mode)
Step 1: Build Docker Image
cd docker
./build_all.sh
cd ..
Step 2: Set API Credentials
export LLM_API_KEY="your-api-key"
export LLM_BASE_URL="https://api.openai.com/v1" # Optional
Step 3: Run Evaluation
---
### Why Docker?
Docker mode provides **secure isolation**:
- ✅ Agents cannot access benchmark answers
- ✅ Network-restricted environment (only LLM API accessible)
- ✅ Resource limits (memory, CPU, timeout)
- ✅ Reproducible across different machines
See [docker/README.md](docker/README.md) for detailed Docker documentation.
---
## 📄 License
MIT License. See [LICENSE](LICENSE) for details.
Individual Kaggle datasets may have their own licenses.
For agents
This page has a .md twin and JSON over the API.