What is CodaBench?

Codabench is a platform allowing you to flexibly specify a benchmark. First you define tasks, e.g. datasets and metrics of success, then you specify the API for submissions of code (algorithms), add some documentation pages, and [CLICK] your benchmark is created, ready to accept submissions of new algorithms. Participant results get appended to an ever-growing leaderboard.

You may also create inverted benchmarks in which the role of datasets and algorithms are swapped. You specify reference algorithms and your participants submit datasets.

What is Codalab?

CodaLab Competitions is a powerful open source framework for running competitions that involve result or code submission. You can either participate in an existing competition or host a new competition.

Most competitions hosted on Codalab are machine learning (data science) competitions, but Codalab is NOT limited to this application domain. It can accommodate any problem for which a solution can be provided in the form of a zip archive containing a number of files to be evaluated quantitatively by a scoring program (provided by the organizers). The scoring program must return a numeric score, which is displayed on a leaderboard where the performances of participants are compared.

History of Codalab

Codalab was created in 2013 as a joint venture between Microsoft and Stanford University. Originally the vision was to create an ecosystem for conducting computational research in a more efficient, reproducible, and collaborative manner, combining worksheets and competitions. Worksheets capture complex research pipelines in a reproducible way and create "executable papers". Currently, we are developing the V2 of Codalab, which will be able to organize benchmarks.

Some competitions have been organized using worksheets, but the competition platform and the worksheet platform have both a large user base and can be used independently. In 2014, ChaLearn joined to co-develop Codalab competitions. Since 2015, University Paris-Saclay is community lead of Codalab competitions, under the direction of Isabelle Guyon, professor of big data. Codalab is administered by CKCollab and the LRI staff.

Codalab in Research

Codalab is used actively in research. In 2019/2020, 400 new challenges were launched. Recent popular challenges organized with Codalab include the COVID-19 retweet prediction challenge,  the ECCV 2020 ChaLearn LAP Fair face recognition challenge, the 2020 DriveML Huawei Autonomous Vehicle Challenge, and high profile challenges include the 2 million Euro prize of the EU, organized by the See.4C consortium, the CIKM AnalytiCup 2017, which attracted 493 participants, MSCOCO (633 participants) and the ChaLearn AutoML challenge 2017 (687 participants).

Since 2016, Codalab offers the possibility of organizing machine learning challenges with code submission. The simplest machine learning challenges require only the submission of results, which are compared to a solution (or key) by a scoring program. Result submission challenges are less computationally expensive than code submission challenges. However, they offer less possibilities. In particular, code submission allows conducting fair benchmarks by executing submitted code in the same condition for all participants.

Codalab has been providing free resources for challenge organizers who want to run high impact events, within a pre-approved agreed upon budget. New since version 1.5: organizers can hook up their own compute workers to the backend of Codalab to redirect the code submissions, enabling growth to big data competitions running at the expense of the organizers. For very special dedicated projects, Codalab can be customized since it is an open source project.