A growing body of evidence links gut microbiota changes with inflammatory bowel disease (IBD), raising the question of the potential benefit of exploiting metagenomics data for non-invasive IBD diagnostics. Open between September 2019 and March 2020, the sbv IMPROVER Metagenomics Diagnosis for Inflammatory Bowel Disease Challenge (MEDIC) investigated computational metagenomics methods for discriminating IBD and non-IBD subjects. For developing and applying models for classifying metagenomics fecal samples, participants were offered the option to start with raw (sub-challenge 1, SC1) or taxonomy- and pathway-based processed (sub-challenge 2, SC2) independent training and test metagenomics data from IBD and non-IBD subjects. We have received and scored a total of 81 anonymized submissions. The results show that many participants’ predictions performed better than random predictions for classifying IBD vs. non-IBD, ulcerative colitis (UC) vs. non-IBD, and Crohn’s disease (CD) vs. non-IBD. However, discrimination of UC and CD remains challenging, with very few submissions reaching the level of significance. Following the challenge, we are conducting an analysis of class predictions and metagenomics features across the teams, including evaluation of the computational methods used to solve the problem. These results will be openly shared with the scientific community to help advance research in the field of IBD.