Metadata-Version: 2.4
Name: mteb
Version: 2.0.4
Summary: Massive Text Embedding Benchmark
Author-email: MTEB Contributors <niklas@huggingface.co>, Kenneth Enevoldsen <kenneth.enevoldsen@cas.au.dk>, Nouamane Tazi <nouamane@huggingface.co>, Nils Reimers <info@nils-reimers.de>
Maintainer-email: Kenneth Enevoldsen <kenneth.enevoldsen@cas.au.dk>, Roman Solomatin <risolomatin@gmail.com>, Isaac Chung <chungisaac1217@gmail.com>
License:                                  Apache License
                                   Version 2.0, January 2004
                                http://www.apache.org/licenses/
        
           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
        
           1. Definitions.
        
              "License" shall mean the terms and conditions for use, reproduction,
              and distribution as defined by Sections 1 through 9 of this document.
        
              "Licensor" shall mean the copyright owner or entity authorized by
              the copyright owner that is granting the License.
        
              "Legal Entity" shall mean the union of the acting entity and all
              other entities that control, are controlled by, or are under common
              control with that entity. For the purposes of this definition,
              "control" means (i) the power, direct or indirect, to cause the
              direction or management of such entity, whether by contract or
              otherwise, or (ii) ownership of fifty percent (50%) or more of the
              outstanding shares, or (iii) beneficial ownership of such entity.
        
              "You" (or "Your") shall mean an individual or Legal Entity
              exercising permissions granted by this License.
        
              "Source" form shall mean the preferred form for making modifications,
              including but not limited to software source code, documentation
              source, and configuration files.
        
              "Object" form shall mean any form resulting from mechanical
              transformation or translation of a Source form, including but
              not limited to compiled object code, generated documentation,
              and conversions to other media types.
        
              "Work" shall mean the work of authorship, whether in Source or
              Object form, made available under the License, as indicated by a
              copyright notice that is included in or attached to the work
              (an example is provided in the Appendix below).
        
              "Derivative Works" shall mean any work, whether in Source or Object
              form, that is based on (or derived from) the Work and for which the
              editorial revisions, annotations, elaborations, or other modifications
              represent, as a whole, an original work of authorship. For the purposes
              of this License, Derivative Works shall not include works that remain
              separable from, or merely link (or bind by name) to the interfaces of,
              the Work and Derivative Works thereof.
        
              "Contribution" shall mean any work of authorship, including
              the original version of the Work and any modifications or additions
              to that Work or Derivative Works thereof, that is intentionally
              submitted to Licensor for inclusion in the Work by the copyright owner
              or by an individual or Legal Entity authorized to submit on behalf of
              the copyright owner. For the purposes of this definition, "submitted"
              means any form of electronic, verbal, or written communication sent
              to the Licensor or its representatives, including but not limited to
              communication on electronic mailing lists, source code control systems,
              and issue tracking systems that are managed by, or on behalf of, the
              Licensor for the purpose of discussing and improving the Work, but
              excluding communication that is conspicuously marked or otherwise
              designated in writing by the copyright owner as "Not a Contribution."
        
              "Contributor" shall mean Licensor and any individual or Legal Entity
              on behalf of whom a Contribution has been received by Licensor and
              subsequently incorporated within the Work.
        
           2. Grant of Copyright License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              copyright license to reproduce, prepare Derivative Works of,
              publicly display, publicly perform, sublicense, and distribute the
              Work and such Derivative Works in Source or Object form.
        
           3. Grant of Patent License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              (except as stated in this section) patent license to make, have made,
              use, offer to sell, sell, import, and otherwise transfer the Work,
              where such license applies only to those patent claims licensable
              by such Contributor that are necessarily infringed by their
              Contribution(s) alone or by combination of their Contribution(s)
              with the Work to which such Contribution(s) was submitted. If You
              institute patent litigation against any entity (including a
              cross-claim or counterclaim in a lawsuit) alleging that the Work
              or a Contribution incorporated within the Work constitutes direct
              or contributory patent infringement, then any patent licenses
              granted to You under this License for that Work shall terminate
              as of the date such litigation is filed.
        
           4. Redistribution. You may reproduce and distribute copies of the
              Work or Derivative Works thereof in any medium, with or without
              modifications, and in Source or Object form, provided that You
              meet the following conditions:
        
              (a) You must give any other recipients of the Work or
                  Derivative Works a copy of this License; and
        
              (b) You must cause any modified files to carry prominent notices
                  stating that You changed the files; and
        
              (c) You must retain, in the Source form of any Derivative Works
                  that You distribute, all copyright, patent, trademark, and
                  attribution notices from the Source form of the Work,
                  excluding those notices that do not pertain to any part of
                  the Derivative Works; and
        
              (d) If the Work includes a "NOTICE" text file as part of its
                  distribution, then any Derivative Works that You distribute must
                  include a readable copy of the attribution notices contained
                  within such NOTICE file, excluding those notices that do not
                  pertain to any part of the Derivative Works, in at least one
                  of the following places: within a NOTICE text file distributed
                  as part of the Derivative Works; within the Source form or
                  documentation, if provided along with the Derivative Works; or,
                  within a display generated by the Derivative Works, if and
                  wherever such third-party notices normally appear. The contents
                  of the NOTICE file are for informational purposes only and
                  do not modify the License. You may add Your own attribution
                  notices within Derivative Works that You distribute, alongside
                  or as an addendum to the NOTICE text from the Work, provided
                  that such additional attribution notices cannot be construed
                  as modifying the License.
        
              You may add Your own copyright statement to Your modifications and
              may provide additional or different license terms and conditions
              for use, reproduction, or distribution of Your modifications, or
              for any such Derivative Works as a whole, provided Your use,
              reproduction, and distribution of the Work otherwise complies with
              the conditions stated in this License.
        
           5. Submission of Contributions. Unless You explicitly state otherwise,
              any Contribution intentionally submitted for inclusion in the Work
              by You to the Licensor shall be under the terms and conditions of
              this License, without any additional terms or conditions.
              Notwithstanding the above, nothing herein shall supersede or modify
              the terms of any separate license agreement you may have executed
              with Licensor regarding such Contributions.
        
           6. Trademarks. This License does not grant permission to use the trade
              names, trademarks, service marks, or product names of the Licensor,
              except as required for reasonable and customary use in describing the
              origin of the Work and reproducing the content of the NOTICE file.
        
           7. Disclaimer of Warranty. Unless required by applicable law or
              agreed to in writing, Licensor provides the Work (and each
              Contributor provides its Contributions) on an "AS IS" BASIS,
              WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
              implied, including, without limitation, any warranties or conditions
              of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
              PARTICULAR PURPOSE. You are solely responsible for determining the
              appropriateness of using or redistributing the Work and assume any
              risks associated with Your exercise of permissions under this License.
        
           8. Limitation of Liability. In no event and under no legal theory,
              whether in tort (including negligence), contract, or otherwise,
              unless required by applicable law (such as deliberate and grossly
              negligent acts) or agreed to in writing, shall any Contributor be
              liable to You for damages, including any direct, indirect, special,
              incidental, or consequential damages of any character arising as a
              result of this License or out of the use or inability to use the
              Work (including but not limited to damages for loss of goodwill,
              work stoppage, computer failure or malfunction, or any and all
              other commercial damages or losses), even if such Contributor
              has been advised of the possibility of such damages.
        
           9. Accepting Warranty or Additional Liability. While redistributing
              the Work or Derivative Works thereof, You may choose to offer,
              and charge a fee for, acceptance of support, warranty, indemnity,
              or other liability obligations and/or rights consistent with this
              License. However, in accepting such obligations, You may act only
              on Your own behalf and on Your sole responsibility, not on behalf
              of any other Contributor, and only if You agree to indemnify,
              defend, and hold each Contributor harmless for any liability
              incurred by, or claims asserted against, such Contributor by reason
              of your accepting any such warranty or additional liability.
        
           END OF TERMS AND CONDITIONS
        
           APPENDIX: How to apply the Apache License to your work.
        
              To apply the Apache License to your work, attach the following
              boilerplate notice, with the fields enclosed by brackets "[]"
              replaced with your own identifying information. (Don't include
              the brackets!)  The text should be enclosed in the appropriate
              comment syntax for the file format. We also recommend that a
              file or class name and description of purpose be included on the
              same "printed page" as the copyright notice for easier
              identification within third-party archives.
        
           Copyright [yyyy] [name of copyright owner]
        
           Licensed under the Apache License, Version 2.0 (the "License");
           you may not use this file except in compliance with the License.
           You may obtain a copy of the License at
        
               http://www.apache.org/licenses/LICENSE-2.0
        
           Unless required by applicable law or agreed to in writing, software
           distributed under the License is distributed on an "AS IS" BASIS,
           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
           See the License for the specific language governing permissions and
           limitations under the License.
        
Project-URL: Homepage, https://github.com/embeddings-benchmark/mteb
Project-URL: Documentation, https://embeddings-benchmark.github.io/mteb/
Project-URL: Repository, https://github.com/embeddings-benchmark/mteb
Project-URL: Hugging Face Organization, https://huggingface.co/mteb
Keywords: deep learning,text embeddings,embeddings,multimodal,benchmark,retrieval,information retrieval
Classifier: Development Status :: 5 - Production/Stable
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Information Technology
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Requires-Python: <3.14,>=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: datasets>=2.19.0
Requires-Dist: numpy<3.0.0,>=1.0.0
Requires-Dist: requests>=2.26.0
Requires-Dist: scikit-learn>=1.4.0
Requires-Dist: scipy>=0.0.0
Requires-Dist: sentence_transformers>=3.0.0
Requires-Dist: typing-extensions>=4.5.0
Requires-Dist: torch>1.0.0
Requires-Dist: tqdm>1.0.0
Requires-Dist: rich>=0.0.0
Requires-Dist: pytrec-eval-terrier>=0.5.6
Requires-Dist: pydantic>=2.0.0
Requires-Dist: polars>=0.20.22
Provides-Extra: image
Requires-Dist: torchvision>0.2.1; extra == "image"
Provides-Extra: codecarbon
Requires-Dist: codecarbon<3.0.0,>=2.0.0; extra == "codecarbon"
Provides-Extra: leaderboard
Requires-Dist: gradio==5.35.0; extra == "leaderboard"
Requires-Dist: plotly<6.0.0,>=5.24.0; extra == "leaderboard"
Requires-Dist: cachetools>=5.2.0; extra == "leaderboard"
Requires-Dist: matplotlib>=3.9.4; extra == "leaderboard"
Provides-Extra: peft
Requires-Dist: peft>=0.11.0; extra == "peft"
Provides-Extra: flagembedding
Requires-Dist: FlagEmbedding==1.3.4; extra == "flagembedding"
Provides-Extra: jina
Requires-Dist: einops>=0.8.0; extra == "jina"
Provides-Extra: jina-v4
Requires-Dist: peft>=0.15.2; extra == "jina-v4"
Requires-Dist: transformers>=4.52.0; extra == "jina-v4"
Requires-Dist: torchvision>=0.22.1; extra == "jina-v4"
Provides-Extra: flash-attention
Requires-Dist: flash-attn>=2.6.3; extra == "flash-attention"
Provides-Extra: openai
Requires-Dist: openai>=1.41.0; extra == "openai"
Requires-Dist: tiktoken>=0.8.0; extra == "openai"
Provides-Extra: model2vec
Requires-Dist: model2vec>=0.3.0; extra == "model2vec"
Provides-Extra: pylate
Requires-Dist: pylate>=1.3.1; python_version < "3.13" and extra == "pylate"
Provides-Extra: bm25s
Requires-Dist: bm25s>=0.2.6; extra == "bm25s"
Requires-Dist: PyStemmer>=2.2.0.3; extra == "bm25s"
Provides-Extra: gritlm
Requires-Dist: gritlm>=1.0.2; extra == "gritlm"
Provides-Extra: xformers
Requires-Dist: xformers>=0.0.29; extra == "xformers"
Provides-Extra: blip2
Requires-Dist: salesforce-lavis>=1.0.2; extra == "blip2"
Provides-Extra: voyageai
Requires-Dist: voyageai<2.0.0,>0.3.0; extra == "voyageai"
Provides-Extra: voyage-v
Requires-Dist: voyageai<2.0.0,>0.3.0; extra == "voyage-v"
Requires-Dist: tenacity>9.0.0; extra == "voyage-v"
Provides-Extra: cohere
Requires-Dist: cohere==5.14.0; extra == "cohere"
Provides-Extra: vertexai
Requires-Dist: vertexai==1.71.1; extra == "vertexai"
Provides-Extra: llm2vec
Requires-Dist: llm2vec<0.3.0,>=0.2.3; extra == "llm2vec"
Provides-Extra: timm
Requires-Dist: timm<1.1.0,>=1.0.15; extra == "timm"
Provides-Extra: open-clip-torch
Requires-Dist: open_clip_torch==2.31.0; extra == "open-clip-torch"
Provides-Extra: nomic
Requires-Dist: einops>=0.8.1; extra == "nomic"
Provides-Extra: ark
Requires-Dist: volcengine-python-sdk[ark]==3.0.2; extra == "ark"
Requires-Dist: tiktoken>=0.8.0; extra == "ark"
Provides-Extra: colpali-engine
Requires-Dist: colpali_engine>=0.3.12; extra == "colpali-engine"
Provides-Extra: xet
Requires-Dist: huggingface_hub>=0.32.0; extra == "xet"
Provides-Extra: youtu
Requires-Dist: tencentcloud-sdk-python-common>=3.0.1454; extra == "youtu"
Requires-Dist: tencentcloud-sdk-python-lkeap>=3.0.1451; extra == "youtu"
Provides-Extra: llama-embed-nemotron
Requires-Dist: transformers==4.51.0; extra == "llama-embed-nemotron"
Provides-Extra: faiss-cpu
Requires-Dist: faiss-cpu>=1.12.0; extra == "faiss-cpu"
Dynamic: license-file

<h1 align="center">
  <img src="docs/images/logos/mteb_logo/dots-icon.png" alt="MTEB" width="28" style="vertical-align: middle; margin-right: 10px;"/> MTEB
</h1>

<h3 align="center" style="border-bottom: none;">Multimodal toolbox for evaluating embeddings and retrieval systems</h3>

<p align="center">
    <a href="https://github.com/embeddings-benchmark/mteb/releases">
        <img alt="GitHub release" src="https://img.shields.io/github/release/embeddings-benchmark/mteb.svg">
    </a>
    <a href="https://github.com/embeddings-benchmark/mteb/blob/master/LICENSE">
        <img alt="License" src="https://img.shields.io/github/license/embeddings-benchmark/mteb.svg?color=green">
    </a>
    <a href="https://pepy.tech/project/mteb">
        <img alt="Downloads" src="https://static.pepy.tech/personalized-badge/mteb?period=total&units=international_system&left_color=grey&right_color=orange&left_text=Downloads">
    </a>
</p>

<h4 align="center">
    <p>
        <a href="https://embeddings-benchmark.github.io/mteb/installation/">Installation</a> |
        <a href="https://embeddings-benchmark.github.io/mteb/">Usage</a> |
        <a href="https://huggingface.co/spaces/mteb/leaderboard">Leaderboard</a> |
        <a href="https://embeddings-benchmark.github.io/mteb/">Documentation</a> |
        <a href="#citing">Citing</a>
    </p>
</h4>


<h3 align="center">
    <a href="https://huggingface.co/spaces/mteb/leaderboard"><img style="float: middle; padding: 10px 10px 10px 10px;" width="60" height="55" src="./docs/images/logos/hf_logo.png" /></a>
</h3>


## Installation

You can install mteb simply using pip. For more on installation please see the [documentation](https://embeddings-benchmark.github.io/mteb/installation/).

```bash
pip install mteb
```


## Example Usage

Below we present a simple use-case example. For more information, see the [documentation](https://embeddings-benchmark.github.io/mteb/).

```python
import mteb
from sentence_transformers import SentenceTransformer

# Select model
model_name = "sentence-transformers/all-MiniLM-L6-v2"
model = mteb.get_model(model_name) # if the model is not implemented in MTEB it will be eq. to SentenceTransformer(model_name)

# Select tasks
tasks = mteb.get_tasks(tasks=["Banking77Classification.v2"])

# evaluate
results = mteb.evaluate(model, tasks=tasks)
```

You can also run it using the CLI:

```bash
mteb run \
    -m sentence-transformers/all-MiniLM-L6-v2 \
    -t "Banking77Classification.v2" \
    --output-folder results
```

For more on how to use the CLI check out the [related documentation](https://embeddings-benchmark.github.io/mteb/usage/cli/).

## Overview

| Overview                       |                                                                                      |
|--------------------------------|--------------------------------------------------------------------------------------|
| 📈 [Leaderboard]               | The interactive leaderboard of the benchmark                                         |
| **Get Started**.               |                                                                                      |
| 🏃 [Get Started]               | Overview of how to use mteb                                                          |
| 🤖 [Defining Models]           | How to use existing model and define custom ones                                     |
| 📋 [Selecting tasks]           | How to select tasks, benchmarks, splits etc.                                         |
| 🏭 [Running Evaluation]        | How to run the evaluations, including cache management, speeding up evaluations etc. |
| 📊 [Loading Results]           | How to load and work with existing model results                                     |
| **Overview**.                  |                                                                                      |
| 📋 [Tasks]                     | Overview of available tasks                                                          |
| 📐 [Benchmarks]                | Overview of available benchmarks                                                     |
| 🤖 [Models]                    | Overview of available Models                                                         |
| **Contributing**               |                                                                                      |
| 🤖 [Adding a model]            | How to submit a model to MTEB and to the leaderboard                                 |
| 👩‍💻 [Adding a dataset]          | How to add a new task/dataset to MTEB                                                |
| 👩‍💻 [Adding a benchmark]        | How to add a new benchmark to MTEB and to the leaderboard                            |
| 🤝 [Contributing]              | How to contribute to MTEB and set it up for development                              |

[Get Started]: https://embeddings-benchmark.github.io/mteb/usage/get_started/
[Defining Models]: https://embeddings-benchmark.github.io/mteb/usage/defining_the_model/
[Selecting tasks]: https://embeddings-benchmark.github.io/mteb/usage/selecting_tasks/
[Running Evaluation]: https://embeddings-benchmark.github.io/mteb/usage/running_the_evaluation/
[Loading Results]: https://embeddings-benchmark.github.io/mteb/usage/loading_results/
[Tasks]: https://embeddings-benchmark.github.io/mteb/overview/available_tasks/any2anymultilingualretrieval/
[Benchmarks]: https://embeddings-benchmark.github.io/mteb/overview/available_benchmarks/
[Models]: https://embeddings-benchmark.github.io/mteb/overview/available_models/text/
[Contributing]: docs/CONTRIBUTING.md
[Adding a model]: docs/contributing/adding_a_model.md
[Adding a dataset]: docs/contributing/adding_a_dataset.md
[Adding a benchmark]: docs/contributing/adding_a_benchmark.md
[Leaderboard]: https://huggingface.co/spaces/mteb/leaderboard

## Citing

MTEB was introduced in "[MTEB: Massive Text Embedding Benchmark](https://arxiv.org/abs/2210.07316)", and heavily expanded in "[MMTEB: Massive Multilingual Text Embedding Benchmark](https://arxiv.org/abs/2502.13595)". When using `mteb`, we recommend that you cite both articles.

<details>
  <summary> Bibtex Citation (click to unfold) </summary>


```bibtex
@article{muennighoff2022mteb,
  author = {Muennighoff, Niklas and Tazi, Nouamane and Magne, Loïc and Reimers, Nils},
  title = {MTEB: Massive Text Embedding Benchmark},
  publisher = {arXiv},
  journal={arXiv preprint arXiv:2210.07316},
  year = {2022}
  url = {https://arxiv.org/abs/2210.07316},
  doi = {10.48550/ARXIV.2210.07316},
}

@article{enevoldsen2025mmtebmassivemultilingualtext,
  title={MMTEB: Massive Multilingual Text Embedding Benchmark},
  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},
  publisher = {arXiv},
  journal={arXiv preprint arXiv:2502.13595},
  year={2025},
  url={https://arxiv.org/abs/2502.13595},
  doi = {10.48550/arXiv.2502.13595},
}
```
</details>


If you use any of the specific benchmarks, we also recommend that you cite the authors of both the benchmark and its tasks:

```py
benchmark = mteb.get_benchmark("MTEB(eng, v2)")
benchmark.citation # get citation for a specific benchmark

# you can also create a table of the task for the appendix using:
benchmark.tasks.to_latex()
```
