Available Benchmarks¶

@inproceedings{thakur2021beir,
  archiveprefix = {arXiv},
  author = {Nandan Thakur and Nils Reimers and Andreas R{\"u}ckl{\'e} and Abhishek Srivastava and Iryna Gurevych},
  booktitle = {Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)},
  eprint = {2104.08663},
  title = {{BEIR}: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models},
  url = {https://openreview.net/forum?id=wCu6T5xFjeJ},
  year = {2021},
}

@inproceedings{banar2024beirnlzeroshotinformationretrieval,
  address = {Abu Dhabi, UAE},
  archiveprefix = {arXiv},
  author = {Lotfi, Ehsan and Banar, Nikolay and Daelemans, Walter},
  booktitle = {Proceedings of the 18th Workshop on Building and Using Comparable Corpora ({BUCC})},
  editor = {Sharoff, Serge and Terryn, Ayla Rigouts and Zweigenbaum, Pierre and Rapp, Reinhard},
  eprint = {2412.08329},
  month = {jan},
  pages = {36--45},
  publisher = {Association for Computational Linguistics},
  title = {{BEIR}-{NL}: Zero-shot Information Retrieval Benchmark for the {D}utch Language},
  url = {https://aclanthology.org/2025.bucc-1.5/},
  year = {2025},
}

@misc{wojtasik2024beirpl,
  archiveprefix = {arXiv},
  author = {Konrad Wojtasik and Vadim Shishkin and Kacper Wołowiec and Arkadiusz Janz and Maciej Piasecki},
  eprint = {2305.19840},
  primaryclass = {cs.IR},
  title = {BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language},
  url = {https://arxiv.org/abs/2305.19840},
  year = {2024},
}

@inproceedings{su2024bright,
  archiveprefix = {arXiv},
  author = {Hongjin SU and Howard Yen and Mengzhou Xia and Weijia Shi and Niklas Muennighoff and Han-yu Wang and Liu Haisu and Quan Shi and Zachary S Siegel and Michael Tang and Ruoxi Sun and Jinsung Yoon and Sercan O Arik and Danqi Chen and Tao Yu},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.12883},
  title = {{BRIGHT}: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval},
  url = {https://openreview.net/forum?id=ykuc5q381b},
  year = {2025},
}

@inproceedings{su2024bright,
  archiveprefix = {arXiv},
  author = {Hongjin SU and Howard Yen and Mengzhou Xia and Weijia Shi and Niklas Muennighoff and Han-yu Wang and Liu Haisu and Quan Shi and Zachary S Siegel and Michael Tang and Ruoxi Sun and Jinsung Yoon and Sercan O Arik and Danqi Chen and Tao Yu},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.12883},
  title = {{BRIGHT}: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval},
  url = {https://openreview.net/forum?id=ykuc5q381b},
  year = {2025},
}

@inproceedings{su2024bright,
  archiveprefix = {arXiv},
  author = {Hongjin SU and Howard Yen and Mengzhou Xia and Weijia Shi and Niklas Muennighoff and Han-yu Wang and Liu Haisu and Quan Shi and Zachary S Siegel and Michael Tang and Ruoxi Sun and Jinsung Yoon and Sercan O Arik and Danqi Chen and Tao Yu},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  eprint = {2407.12883},
  title = {{BRIGHT}: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval},
  url = {https://openreview.net/forum?id=ykuc5q381b},
  year = {2025},
}

@inproceedings{Zhao2026RethinkingRR,
  address = {San Diego, California, United States},
  author = {Zhao, Yilun and Wei, Jinbiao and Song, Tingyu and Zhang, Siyue and Zhao, Chen and Cohan, Arman},
  booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2026.acl-long.1705},
  editor = {Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David},
  isbn = {979-8-89176-390-6},
  month = {jul},
  pages = {36776--36806},
  publisher = {Association for Computational Linguistics},
  title = {Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems},
  url = {https://aclanthology.org/2026.acl-long.1705/},
  year = {2026},
}

@article{shahinmoghadam2024benchmarking,
  author = {Shahinmoghadam, Mehrzad and Motamedi, Ali},
  doi = {10.1038/s41598-025-09052-5},
  issn = {2045-2322},
  journal = {Scientific Reports},
  month = {July},
  number = {1},
  publisher = {Springer Science and Business Media LLC},
  title = {Benchmarking pre-trained text embedding models in aligning built asset information},
  url = {https://doi.org/10.1038/s41598-025-09052-5},
  volume = {15},
  year = {2025},
}

@inproceedings{kasmaee2024chemteb,
  archiveprefix = {arXiv},
  author = {Ali Shiraee Kasmaee and Mohammad Khodadad and Mohammad Arshi Saloot and Nick Sherck and Stephen Dokas and Hamidreza Mahyar and Soheila Samiee},
  booktitle = {ENLSP},
  eprint = {2412.00532},
  pages = {512-531},
  title = {ChemTEB: Chemical Text Embedding Benchmark, an Overview of Embedding Models Performance & Efficiency on a Specific Domain},
  url = {https://proceedings.mlr.press/v262/shiraee-kasmaee24a.html},
  year = {2024},
}

@inproceedings{kasmaee2024chemteb,
  archiveprefix = {arXiv},
  author = {Ali Shiraee Kasmaee and Mohammad Khodadad and Mohammad Arshi Saloot and Nick Sherck and Stephen Dokas and Hamidreza Mahyar and Soheila Samiee},
  booktitle = {ENLSP},
  eprint = {2412.00532},
  pages = {512-531},
  title = {ChemTEB: Chemical Text Embedding Benchmark, an Overview of Embedding Models Performance & Efficiency on a Specific Domain},
  url = {https://proceedings.mlr.press/v262/shiraee-kasmaee24a.html},
  year = {2024},
}

@article{kasmaee2025chembed,
  author = {Kasmaee, Ali Shiraee and Khodadad, Mohammad and Astaraki, Mahdi and Saloot, Mohammad Arshi and Sherck, Nicholas and Mahyar, Hamidreza and Samiee, Soheila},
  journal = {arXiv preprint arXiv:2508.01643},
  title = {Chembed: Enhancing chemical literature search through domain-specific text embeddings},
  year = {2025},
}

@inproceedings{li2024coircomprehensivebenchmarkcode,
  address = {Vienna, Austria},
  author = {Li, Xiangyang and Dong, Kuicai and Lee, Yi Quan and Xia, Wei and Zhang, Hao and Dai, Xinyi and Wang, Yasheng and Tang, Ruiming},
  booktitle = {Proceedings of the 63rd Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2025.acl-long.1072},
  editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher},
  isbn = {979-8-89176-251-0},
  month = {jul},
  pages = {22074--22091},
  publisher = {Association for Computational Linguistics},
  title = {{C}o{IR}: A Comprehensive Benchmark for Code Information Retrieval Models},
  url = {https://aclanthology.org/2025.acl-long.1072/},
  year = {2025},
}

@article{xue2026coreb,
  author = {Xue, Siqiao and Liao, Zihan and Qin, Jin and Zhang, Ziyin and Mu, Yixiang and Zhou, Fan and Yu, Hang},
  journal = {arXiv preprint arXiv:2605.04615},
  title = {Beyond Retrieval: A Multitask Benchmark and Model for Code Search},
  url = {https://arxiv.org/abs/2605.04615},
  year = {2026},
}

@inproceedings{wang2024coderagbenchretrievalaugmentcode,
  address = {Albuquerque, New Mexico},
  author = {Wang, Zora Zhiruo and Asai, Akari and Yu, Xinyan Velocity and Xu, Frank F. and Xie, Yiqing and Neubig, Graham and Fried, Daniel},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {NAACL} 2025},
  doi = {10.18653/v1/2025.findings-naacl.176},
  editor = {Chiruzzo, Luis and Ritter, Alan and Wang, Lu},
  isbn = {979-8-89176-195-7},
  month = {apr},
  pages = {3199--3214},
  publisher = {Association for Computational Linguistics},
  title = {{C}ode{RAG}-Bench: Can Retrieval Augment Code Generation?},
  url = {https://aclanthology.org/2025.findings-naacl.176/},
  year = {2025},
}

@inproceedings{weller2024followir,
  address = {Albuquerque, New Mexico},
  author = {Weller, Orion and Chang, Benjamin and MacAvaney, Sean and Lo, Kyle and Cohan, Arman and Van Durme, Benjamin and Lawrie, Dawn and Soldaini, Luca},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the {A}mericas Chapter of the {A}ssociation for {C}omputational {L}inguistics: Human Language Technologies (Volume 1: Long Papers)},
  doi = {10.18653/v1/2025.naacl-long.597},
  editor = {Chiruzzo, Luis and Ritter, Alan and Wang, Lu},
  isbn = {979-8-89176-189-6},
  month = {apr},
  pages = {11926--11942},
  publisher = {Association for Computational Linguistics},
  title = {{F}ollow{IR}: Evaluating and Teaching Information Retrieval Models to Follow Instructions},
  url = {https://aclanthology.org/2025.naacl-long.597/},
  year = {2025},
}

@inproceedings{song2025ifir,
  author = {Song, Tingyu and Gan, Guo and Shang, Mingsheng and Zhao, Yilun},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)},
  pages = {10186--10204},
  title = {IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval},
  year = {2025},
}

@inproceedings{li-etal-2026-jmteb,
  address = {Palma de Mallorca, Spain},
  author = {Li, Shengzhe and Ohagi, Masaya and Ri, Ryokan and Fukuchi, Akihiko and Shibata, Tomohide and Kawahara, Daisuke},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  doi = {10.63317/5ouzpv2f2f6k},
  month = may,
  pages = {7423--7434},
  publisher = {ELRA Language Resource Association},
  title = {{JMTEB} and {JMTEB}-lite: {J}apanese Massive Text Embedding Benchmark and Its Lightweight Version},
  url = {https://aclanthology.org/2026.lrec-1.588/},
  year = {2026},
}

@inproceedings{li-etal-2026-jmteb,
  address = {Palma de Mallorca, Spain},
  author = {Li, Shengzhe and Ohagi, Masaya and Ri, Ryokan and Fukuchi, Akihiko and Shibata, Tomohide and Kawahara, Daisuke},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  doi = {10.63317/5ouzpv2f2f6k},
  month = may,
  pages = {7423--7434},
  publisher = {ELRA Language Resource Association},
  title = {{JMTEB} and {JMTEB}-lite: {J}apanese Massive Text Embedding Benchmark and Its Lightweight Version},
  url = {https://aclanthology.org/2026.lrec-1.588/},
  year = {2026},
}

@inproceedings{günther2025jinaembeddingsv4universalembeddingsmultimodal,
  address = {Suzhuo, China},
  author = {G{\"u}nther, Michael and Sturua, Saba and Akram, Mohammad Kalim and Mohr, Isabelle and Ungureanu, Andrei and Wang, Bo and Eslami, Sedigheh and Martens, Scott and Werk, Maximilian and Wang, Nan and Xiao, Han},
  booktitle = {Proceedings of the 5th Workshop on Multilingual Representation Learning ({MRL} 2025)},
  doi = {10.18653/v1/2025.mrl-main.36},
  editor = {Adelani, David Ifeoluwa and Arnett, Catherine and Ataman, Duygu and Chang, Tyler A. and Gonen, Hila and Raja, Rahul and Schmidt, Fabian and Stap, David and Wang, Jiayi},
  isbn = {979-8-89176-345-6},
  month = {nov},
  pages = {531--550},
  publisher = {Association for Computational Linguistics},
  title = {jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval},
  url = {https://aclanthology.org/2025.mrl-main.36/},
  year = {2025},
}

@inproceedings{choi-etal-2026-kovidore,
  address = {San Diego, USA},
  author = {Choi, Yongbin  and
Song, Yongwoo  and
Sung, Mujeen},
  booktitle = {Proceedings of the 2nd Workshop on Multimodal Augmented Generation via Multimodal Retrieval ({MAGM}a{R} 2026)},
  doi = {10.18653/v1/2026.magmar-main.11},
  editor = {Murray, Kenton  and
Kriz, Reno},
  isbn = {979-8-89176-425-5},
  month = jul,
  pages = {54--80},
  publisher = {Association for Computational Linguistics},
  title = {{K}o{V}i{D}o{R}e: A Benchmark for {K}orean Visual Document Retrieval},
  url = {https://aclanthology.org/2026.magmar-main.11/},
  year = {2026},
}

@misc{zhao2026lmeb,
  archiveprefix = {arXiv},
  author = {Zhao, Xinping and Hu, Xinshuo and Xu, Jiaxin and Tang, Danyu and Zhang, Xin and Zhou, Mengjia and Zhong, Yan and Zhou, Yao and Shan, Zifei and Zhang, Meishan and Hu, Baotian and Zhang, Min},
  eprint = {2603.12572},
  primaryclass = {cs.CL},
  title = {LMEB: Long-horizon Memory Embedding Benchmark},
  url = {https://arxiv.org/abs/2603.12572},
  year = {2026},
}

@inproceedings{zhu2024longembed,
  address = {Miami, Florida, USA},
  author = {Zhu, Dawei and Wang, Liang and Yang, Nan and Song, Yifan and Wu, Wenhao and Wei, Furu and Li, Sujian},
  booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},
  doi = {10.18653/v1/2024.emnlp-main.47},
  editor = {Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung},
  month = {nov},
  pages = {802--816},
  publisher = {Association for Computational Linguistics},
  title = {{L}ong{E}mbed: Extending Embedding Models for Long Context Retrieval},
  url = {https://aclanthology.org/2024.emnlp-main.47/},
  year = {2024},
}

@misc{assadi2026maebmassiveaudioembedding,
  archiveprefix = {arXiv},
  author = {Adnan El Assadi and Isaac Chung and Chenghao Xiao and Roman Solomatin and Animesh Jha and Rahul Chand and Silky Singh and Kaitlyn Wang and Ali Sartaz Khan and Marc Moussa Nasser and Sufen Fong and Pengfei He and Alan Xiao and Ayush Sunil Munot and Aditya Shrivastava and Artem Gazizov and Niklas Muennighoff and Kenneth Enevoldsen},
  eprint = {2602.16008},
  primaryclass = {cs.SD},
  title = {MAEB: Massive Audio Embedding Benchmark},
  url = {https://arxiv.org/abs/2602.16008},
  year = {2026},
}

@misc{assadi2026maebmassiveaudioembedding,
  archiveprefix = {arXiv},
  author = {Adnan El Assadi and Isaac Chung and Chenghao Xiao and Roman Solomatin and Animesh Jha and Rahul Chand and Silky Singh and Kaitlyn Wang and Ali Sartaz Khan and Marc Moussa Nasser and Sufen Fong and Pengfei He and Alan Xiao and Ayush Sunil Munot and Aditya Shrivastava and Artem Gazizov and Niklas Muennighoff and Kenneth Enevoldsen},
  eprint = {2602.16008},
  primaryclass = {cs.SD},
  title = {MAEB: Massive Audio Embedding Benchmark},
  url = {https://arxiv.org/abs/2602.16008},
  year = {2026},
}

@inproceedings{xiao2025mieb,
  author = {Xiao, Chenghao and Chung, Isaac and Kerboua, Imene and Stirling, Jamie and Zhang, Xin and Kardos, M\'arton and Solomatin, Roman and Al Moubayed, Noura and Enevoldsen, Kenneth and Muennighoff, Niklas},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month = {October},
  pages = {22187-22198},
  title = {MIEB: Massive Image Embedding Benchmark},
  year = {2025},
}

@inproceedings{xiao2025mieb,
  author = {Xiao, Chenghao and Chung, Isaac and Kerboua, Imene and Stirling, Jamie and Zhang, Xin and Kardos, M\'arton and Solomatin, Roman and Al Moubayed, Noura and Enevoldsen, Kenneth and Muennighoff, Niklas},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month = {October},
  pages = {22187-22198},
  title = {MIEB: Massive Image Embedding Benchmark},
  year = {2025},
}

@inproceedings{xiao2025mieb,
  author = {Xiao, Chenghao and Chung, Isaac and Kerboua, Imene and Stirling, Jamie and Zhang, Xin and Kardos, M\'arton and Solomatin, Roman and Al Moubayed, Noura and Enevoldsen, Kenneth and Muennighoff, Niklas},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month = {October},
  pages = {22187-22198},
  title = {MIEB: Massive Image Embedding Benchmark},
  year = {2025},
}

@inproceedings{xiao2025mieb,
  author = {Xiao, Chenghao and Chung, Isaac and Kerboua, Imene and Stirling, Jamie and Zhang, Xin and Kardos, M\'arton and Solomatin, Roman and Al Moubayed, Noura and Enevoldsen, Kenneth and Muennighoff, Niklas},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month = {October},
  pages = {22187-22198},
  title = {MIEB: Massive Image Embedding Benchmark},
  year = {2025},
}

@inproceedings{winata2024miners,
  address = {Miami, Florida, USA},
  author = {Winata, Genta Indra and Zhang, Ruochen and Adelani, David Ifeoluwa},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2024},
  doi = {10.18653/v1/2024.findings-emnlp.155},
  editor = {Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung},
  month = {nov},
  pages = {2742--2766},
  publisher = {Association for Computational Linguistics},
  title = {{MINERS}: Multilingual Language Models as Semantic Retrievers},
  url = {https://aclanthology.org/2024.findings-emnlp.155/},
  year = {2024},
}

@article{enevoldsen2025mmtebmassivemultilingualtext,
  author = {Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisserot-Boukhlef and Tom Aarsen and Jan Kostkan and Konrad Wojtasik and Taemin Lee and Marek Šuppa and Crystina Zhang and Roberta Rocca and Mohammed Hamdy and Andrianos Michail and John Yang and Manuel Faysse and Aleksei Vatolin and Nandan Thakur and Manan Dey and Dipam Vasani and Pranjal Chitale and Simone Tedeschi and Nguyen Tai and Artem Snegirev and Michael Günther and Mengzhou Xia and Weijia Shi and Xing Han Lù and Jordan Clive and Gayatri Krishnakumar and Anna Maksimova and Silvan Wehrli and Maria Tikhonova and Henil Panchal and Aleksandr Abramov and Malte Ostendorff and Zheng Liu and Simon Clematide and Lester James Miranda and Alena Fenogenova and Guangyu Song and Ruqiya Bin Safi and Wen-Ding Li and Alessia Borghini and Federico Cassano and Hongjin Su and Jimmy Lin and Howard Yen and Lasse Hansen and Sara Hooker and Chenghao Xiao and Vaibhav Adlakha and Orion Weller and Siva Reddy and Niklas Muennighoff},
  doi = {10.48550/arXiv.2502.13595},
  journal = {arXiv preprint arXiv:2502.13595},
  publisher = {arXiv},
  title = {MMTEB: Massive Multilingual Text Embedding Benchmark},
  url = {https://arxiv.org/abs/2502.13595},
  year = {2025},
}

@article{enevoldsen2025mmtebmassivemultilingualtext,
  author = {Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisserot-Boukhlef and Tom Aarsen and Jan Kostkan and Konrad Wojtasik and Taemin Lee and Marek Šuppa and Crystina Zhang and Roberta Rocca and Mohammed Hamdy and Andrianos Michail and John Yang and Manuel Faysse and Aleksei Vatolin and Nandan Thakur and Manan Dey and Dipam Vasani and Pranjal Chitale and Simone Tedeschi and Nguyen Tai and Artem Snegirev and Michael Günther and Mengzhou Xia and Weijia Shi and Xing Han Lù and Jordan Clive and Gayatri Krishnakumar and Anna Maksimova and Silvan Wehrli and Maria Tikhonova and Henil Panchal and Aleksandr Abramov and Malte Ostendorff and Zheng Liu and Simon Clematide and Lester James Miranda and Alena Fenogenova and Guangyu Song and Ruqiya Bin Safi and Wen-Ding Li and Alessia Borghini and Federico Cassano and Hongjin Su and Jimmy Lin and Howard Yen and Lasse Hansen and Sara Hooker and Chenghao Xiao and Vaibhav Adlakha and Orion Weller and Siva Reddy and Niklas Muennighoff},
  doi = {10.48550/arXiv.2502.13595},
  journal = {arXiv preprint arXiv:2502.13595},
  publisher = {arXiv},
  title = {MMTEB: Massive Multilingual Text Embedding Benchmark},
  url = {https://arxiv.org/abs/2502.13595},
  year = {2025},
}

@article{enevoldsen2025mmtebmassivemultilingualtext,
  author = {Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisserot-Boukhlef and Tom Aarsen and Jan Kostkan and Konrad Wojtasik and Taemin Lee and Marek Šuppa and Crystina Zhang and Roberta Rocca and Mohammed Hamdy and Andrianos Michail and John Yang and Manuel Faysse and Aleksei Vatolin and Nandan Thakur and Manan Dey and Dipam Vasani and Pranjal Chitale and Simone Tedeschi and Nguyen Tai and Artem Snegirev and Michael Günther and Mengzhou Xia and Weijia Shi and Xing Han Lù and Jordan Clive and Gayatri Krishnakumar and Anna Maksimova and Silvan Wehrli and Maria Tikhonova and Henil Panchal and Aleksandr Abramov and Malte Ostendorff and Zheng Liu and Simon Clematide and Lester James Miranda and Alena Fenogenova and Guangyu Song and Ruqiya Bin Safi and Wen-Ding Li and Alessia Borghini and Federico Cassano and Hongjin Su and Jimmy Lin and Howard Yen and Lasse Hansen and Sara Hooker and Chenghao Xiao and Vaibhav Adlakha and Orion Weller and Siva Reddy and Niklas Muennighoff},
  doi = {10.48550/arXiv.2502.13595},
  journal = {arXiv preprint arXiv:2502.13595},
  publisher = {arXiv},
  title = {MMTEB: Massive Multilingual Text Embedding Benchmark},
  url = {https://arxiv.org/abs/2502.13595},
  year = {2025},
}

@article{enevoldsen2025mmtebmassivemultilingualtext,
  author = {Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisserot-Boukhlef and Tom Aarsen and Jan Kostkan and Konrad Wojtasik and Taemin Lee and Marek Šuppa and Crystina Zhang and Roberta Rocca and Mohammed Hamdy and Andrianos Michail and John Yang and Manuel Faysse and Aleksei Vatolin and Nandan Thakur and Manan Dey and Dipam Vasani and Pranjal Chitale and Simone Tedeschi and Nguyen Tai and Artem Snegirev and Michael Günther and Mengzhou Xia and Weijia Shi and Xing Han Lù and Jordan Clive and Gayatri Krishnakumar and Anna Maksimova and Silvan Wehrli and Maria Tikhonova and Henil Panchal and Aleksandr Abramov and Malte Ostendorff and Zheng Liu and Simon Clematide and Lester James Miranda and Alena Fenogenova and Guangyu Song and Ruqiya Bin Safi and Wen-Ding Li and Alessia Borghini and Federico Cassano and Hongjin Su and Jimmy Lin and Howard Yen and Lasse Hansen and Sara Hooker and Chenghao Xiao and Vaibhav Adlakha and Orion Weller and Siva Reddy and Niklas Muennighoff},
  doi = {10.48550/arXiv.2502.13595},
  journal = {arXiv preprint arXiv:2502.13595},
  publisher = {arXiv},
  title = {MMTEB: Massive Multilingual Text Embedding Benchmark},
  url = {https://arxiv.org/abs/2502.13595},
  year = {2025},
}