MMTEB: Massive Multilingual Text Embedding Benchmark

@misc{yen2025mmtebmassivemultilingual,
      title={MMTEB: Massive Multilingual Text Embedding Benchmark}, 
      author={Howard Yen and Kranthi Kiran GV and Guangyu Song and Jay Gala and Federico Cassano and Michael Günther and Isabelle Mohr and Saba Sturua and Zheng Liu and Shitao Xiao and Jimmy Lin and Niklas Muennighoff and Mengzhou Xia and Siva Reddy and Sara Hooker and Hongjin Su and Weijia Shi and Manuel Faysse and Nandan Thakur and Alena Fenogenova and Maria Tikhonova and Akash Kundu and Genta Indra Winata and John Yang and Wen-Ding Li and Loïc Magne and Orion Weller and Bhavish Pahwa and David Stap and Manan Dey and Kenneth Enevoldsen and Jordan Clive and Roberta Rocca and Mariya Hendriksen and Diganta Misra and Mohammed Hamdy and Dawei Zhu and Silvan Wehrli and Simone Tedeschi and Chenghao Xiao and Konrad Wojtasik and Saiteja Utpala and Pranjal Chitale and Vaibhav Adlakha and Xing Han Lù and Artem Snegirev and Dominik Krzemiński and Lasse Hansen and Rafał Poświata and Malte Ostendorff and Lester James Miranda and Simon Clematide and Márton Kardos and Gayatri Krishnakumar and et al. (39 additional authors not shown) and Hippolyte Gisserot-Boukhlef and Andrianos Michail and Marek Šuppa and Anna Maksimova and Aleksandr Abramov and Tom Aarsen and Isaac Chung and Jan Kostkan and Wissam Siblini and Mathieu Ciancone and Marion Schaeffer and Imene Kerboua and Ashwin Mathur and Gabriel Sequeira and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağatan and Martin Bernstorff and Akshita Sukhlecha and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Taemin Lee and Crystina Zhang and Aleksei Vatolin and Dipam Vasani and Nguyen Tai and Henil Panchal and Ruqiya Bin Safi and Alessia Borghini},
      year={2025},
      eprint={2502.13595},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2502.13595}, 
}