Papers
Community platform that links ML papers with open source implementations benchmarks and leaderboards to make research more reproducible and accessible.
Overview
Papers with Code helps researchers and engineers find methods datasets and results with direct links between papers and implementations. Each task page aggregates SOTA leaderboards methods and datasets while paper pages list official code repos versions and licenses. Users can filter by tasks frameworks and evaluation metrics compare submissions and see how results evolved over time.
The platform also curates trending topics tutorials and starter resources for new areas. Because entries are crowd maintained with moderation the community can propose fixes and add missing repos quickly. APIs and bulk data dumps support meta research and education.
For practitioners the site shortens the path from reading to running while reinforcing licensing awareness and reproducibility so teams avoid dead ends and can benchmark baselines before deeper investment.
Key features
- Task pages: Browse leaderboards datasets methods and metrics for a clear view of the SOTA landscape
- Paper pages: See official code repos versions and licenses linked directly from publications
- Filters and compare: Slice by dataset metric task or framework to evaluate methods quickly
- Community edits: Propose changes and add repos with moderation to keep entries accurate
- APIs and dumps: Pull structured task and result data for meta analysis and education at scale
- Trends and guides: Explore curated topics tutorials and learning paths for emerging areas
- Repro focus: Emphasize licensing versions and seeds so results are comparable and responsible
- Search and alerts: Track new papers methods and tasks to stay current with your domain
Best for
- Find baseline code for a new task and run it quickly
- Compare methods across datasets and metrics before experiments
- Build teaching labs with real repos and tasks for students
- Extract benchmark data for reviews and meta analysis
- Track trending tasks and papers in a research area
- Check licenses and versions before reuse in products
- Identify gaps where a method lacks an implementation
- Automate weekly digests of new results in your field
Capabilities
Task leaderboards
See ranked results datasets and metrics for each task so you can assess progress and pick baselines quickly.
Official repos
Open linked implementations and instructions for methods to reduce trial setup time and friction.
Filters and metrics
Filter by dataset framework or metric to compare approaches fairly and decide what to test first.
APIs and dumps
Fetch structured data for classes reviews and meta research so findings are transparent and reproducible.
Frequently Asked Questions
Is Papers with Code free?
Yes the site is free to use and encourages open contributions with clear licenses and moderation to keep entries reliable.
Can I access data programmatically?
Yes APIs and periodic dumps provide task paper and result data for analysis and education.
How current are leaderboards?
They update as maintainers and the community add results with moderation to keep standards consistent.
Does it only cover deep learning?
Coverage spans a wide range of ML tasks methods and datasets not only neural networks.
Are repos vetted for licenses?
Paper pages surface repository licenses and versions so users can evaluate reuse obligations before adoption.
