The MTEB Leaderboard is available here. To submit:
- Run on MTEB: You can reference scripts/run_mteb_english.py for all MTEB English datasets used in the main ranking, or scripts/run_mteb_chinese.py for the Chinese ones. Advanced scripts with different models are available in the mteb/mtebscripts repo.
- Format the json files into metadata using the script at
scripts/mteb_meta.py
. For examplepython scripts/mteb_meta.py path_to_results_folder
, which will create amteb_metadata.md
file. If you ran CQADupstack retrieval, make sure to merge the results first withpython scripts/merge_cqadupstack.py path_to_results_folder
. - Copy the content of the
mteb_metadata.md
file to the top of aREADME.md
file of your model on the Hub. See here for an example. - Hit the Refresh button at the bottom of the leaderboard and you should see your scores 🥇
- To have the scores appear without refreshing, you can open an issue on the Community Tab of the LB and someone will restart the space to cache your average scores. The cache is updated anyways ~1x/week.