embedding-benchmark/SWEbenchCodeRetrieval

Tasks

• text-retrieval

Citation text from the card

@misc{jimenez2024swebenchlanguagemodelsresolve,
  archiveprefix = {arXiv},
  author = {Carlos E. Jimenez and John Yang and Alexander Wettig and Shunyu Yao and Kexin Pei and Ofir Press and Karthik Narasimhan},
  eprint = {2310.06770},
  primaryclass = {cs.CL},
  title = {SWE-bench: Can Language Models Resolve Real-World GitHub Issues?},
  url = {https://arxiv.org/abs/2310.06770},
  year = {2024},
}

@article{enevoldsen2025mmtebmassivemultilingualtext,
  title={MMTEB: Massive Multilingual Text Embedding Benchmark},
  author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and M\'{a}rton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemi\'{n}ski 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 Rystr{\o}m and Roman Solomatin and \"{O}mer \c{C}a\u{g}atan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafa{\l} Po\'{s}wiata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Bj\"{o}rn Pl\"{u}ster and Jan Philipp Harries and Lo\"{i}c 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 \v{S}uppa 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 Mana

All datasets marked Permissive or share-alike | JSON