Name | mteb JSON |
Version |
1.38.37
JSON |
| download |
home_page | None |
Summary | Massive Text Embedding Benchmark |
upload_time | 2025-07-21 11:43:51 |
maintainer | None |
docs_url | None |
author | None |
requires_python | <3.13,>=3.9 |
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.
|
keywords |
deep learning
text embeddings
benchmark
|
VCS |
 |
bugtrack_url |
|
requirements |
No requirements were recorded.
|
Travis-CI |
No Travis.
|
coveralls test coverage |
No coveralls.
|
<h1 align="center">Massive Text Embedding Benchmark</h1>
<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://arxiv.org/abs/2210.07316">
<img alt="GitHub release" src="https://img.shields.io/badge/arXiv-2305.14251-b31b1b.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="#installation">Installation</a> |
<a href="#usage-documentation">Usage</a> |
<a href="https://huggingface.co/spaces/mteb/leaderboard">Leaderboard</a> |
<a href="#documentation">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/hf_logo.png" /></a>
</h3>
## Installation
```bash
pip install mteb
```
## Example Usage
### Using a script
```python
import mteb
from sentence_transformers import SentenceTransformer
# Define the sentence-transformers model name
model_name = "average_word_embeddings_komninos"
model = mteb.get_model(model_name) # if the model is not implemented in MTEB it will be eq. to SentenceTransformer(model_name)
tasks = mteb.get_tasks(tasks=["Banking77Classification"])
evaluation = mteb.MTEB(tasks=tasks)
results = evaluation.run(model, output_folder=f"results/{model_name}")
```
### Using the CLI
```bash
mteb available_tasks # list _all_ available tasks
mteb run -m sentence-transformers/all-MiniLM-L6-v2 \
-t Banking77Classification \
--verbosity 3
# if nothing is specified default to saving the results in the results/{model_name} folder
```
Note that using multiple GPUs in parallel can be done by just having a custom encode function that distributes the inputs to multiple GPUs like e.g. [here](https://github.com/microsoft/unilm/blob/b60c741f746877293bb85eed6806736fc8fa0ffd/e5/mteb_eval.py#L60) or [here](https://github.com/ContextualAI/gritlm/blob/09d8630f0c95ac6a456354bcb6f964d7b9b6a609/gritlm/gritlm.py#L75). See [custom models](docs/usage/usage.md#using-a-custom-model) for more information.
## Usage Documentation
The following links to the main sections in the usage documentation.
| Section | |
| ------- |- |
| **General** | |
| [Evaluating a Model](docs/usage/usage.md#evaluating-a-model) | How to evaluate a model |
| [Evaluating on different Modalities](docs/usage/usage.md#evaluating-on-different-modalities) | How to evaluate image and image-text tasks |
| [MIEB](docs/mieb/readme.md) | How to run the Massive Image Embedding Benchmark |
| **Selecting Tasks** | |
| [Selecting a benchmark](docs/usage/usage.md#selecting-a-benchmark) | How to select benchmarks |
| [Task selection](docs/usage/usage.md#task-selection) | How to select and filter tasks |
| [Selecting Split and Subsets](docs/usage/usage.md#selecting-evaluation-split-or-subsets) | How to select evaluation splits or subsets |
| [Using a Custom Task](docs/usage/usage.md#using-a-custom-task) | How to evaluate on a custom task |
| **Selecting a Model** | |
| [Using a Pre-defined Model](docs/usage/usage.md#using-a-pre-defined-model) | How to run a pre-defined model |
| [Using a SentenceTransformer Model](docs/usage/usage.md#using-a-sentence-transformer-model) | How to run a model loaded using sentence-transformers |
| [Using a Custom Model](docs/usage/usage.md#using-a-custom-model) | How to run and implement a custom model |
| **Running Evaluation** | |
| [Passing Arguments to the model](docs/usage/usage.md#passing-in-encode-arguments) | How to pass `encode` arguments to the model |
| [Running Cross Encoders](docs/usage/usage.md#running-cross-encoders-on-reranking) | How to run cross encoders for reranking |
| [Running Late Interaction (ColBERT)](docs/usage/usage.md#using-late-interaction-models) | How to run late interaction models |
| [Saving Retrieval Predictions](docs/usage/usage.md#saving-retrieval-task-predictions) | How to save prediction for later analysis |
| [Caching Embeddings](docs/usage/usage.md#caching-embeddings-to-re-use-them) | How to cache and re-use embeddings |
| **Leaderboard** | |
| [Running the Leaderboard Locally](docs/usage/usage.md#running-the-leaderboard-locally) | How to run the leaderboard locally |
| [Report Data Contamination](docs/usage/usage.md#annotate-contamination) | How to report data contamination for a model |
| [Loading and working with Results](docs/usage/results.md) | How to load and working with the raw results from the leaderboard, including making result dataframes |
## Overview
| Overview | |
|--------------------------------|-------------------------------------------------------------------------------------|
| 📈 [Leaderboard] | The interactive leaderboard of the benchmark |
| 📋 [Tasks] | Overview of available tasks |
| 📐 [Benchmarks] | Overview of available benchmarks |
| **Contributing** | |
| 🤖 [Adding a model] | How to submit a model to MTEB and to the leaderboard |
| 👩🔬 [Reproducible workflows] | How to create reproducible workflows with MTEB |
| 👩💻 [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 |
[Tasks]: docs/tasks.md
[Benchmarks]: docs/benchmarks.md
[Contributing]: CONTRIBUTING.md
[Adding a model]: docs/adding_a_model.md
[Adding a dataset]: docs/adding_a_dataset.md
[Adding a benchmark]: docs/adding_a_benchmark.md
[Leaderboard]: https://huggingface.co/spaces/mteb/leaderboard
[Reproducible workflows]: docs/reproducible_workflow.md
## 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, Lo{\"\i}c 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.
```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()
```
Some of these amazing publications include (ordered chronologically):
- Shitao Xiao, Zheng Liu, Peitian Zhang, Niklas Muennighoff. "[C-Pack: Packaged Resources To Advance General Chinese Embedding](https://arxiv.org/abs/2309.07597)" arXiv 2023
- Michael Günther, Jackmin Ong, Isabelle Mohr, Alaeddine Abdessalem, Tanguy Abel, Mohammad Kalim Akram, Susana Guzman, Georgios Mastrapas, Saba Sturua, Bo Wang, Maximilian Werk, Nan Wang, Han Xiao. "[Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents](https://arxiv.org/abs/2310.19923)" arXiv 2023
- Silvan Wehrli, Bert Arnrich, Christopher Irrgang. "[German Text Embedding Clustering Benchmark](https://arxiv.org/abs/2401.02709)" arXiv 2024
- Orion Weller, Benjamin Chang, Sean MacAvaney, Kyle Lo, Arman Cohan, Benjamin Van Durme, Dawn Lawrie, Luca Soldaini. "[FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions](https://arxiv.org/abs/2403.15246)" arXiv 2024
- Dawei Zhu, Liang Wang, Nan Yang, Yifan Song, Wenhao Wu, Furu Wei, Sujian Li. "[LongEmbed: Extending Embedding Models for Long Context Retrieval](https://arxiv.org/abs/2404.12096)" arXiv 2024
- Kenneth Enevoldsen, Márton Kardos, Niklas Muennighoff, Kristoffer Laigaard Nielbo. "[The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding](https://arxiv.org/abs/2406.02396)" arXiv 2024
- Ali Shiraee Kasmaee, Mohammad Khodadad, Mohammad Arshi Saloot, Nick Sherck, Stephen Dokas, Hamidreza Mahyar, Soheila Samiee. "[ChemTEB: Chemical Text Embedding Benchmark, an Overview of Embedding Models Performance & Efficiency on a Specific Domain](https://arxiv.org/abs/2412.00532)" arXiv 2024
- Chenghao Xiao, Isaac Chung, Imene Kerboua, Jamie Stirling, Xin Zhang, Márton Kardos, Roman Solomatin, Noura Al Moubayed, Kenneth Enevoldsen, Niklas Muennighoff. "[MIEB: Massive Image Embedding Benchmark](https://arxiv.org/abs/2504.10471)" arXiv 2025
Raw data
{
"_id": null,
"home_page": null,
"name": "mteb",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.13,>=3.9",
"maintainer_email": null,
"keywords": "deep learning, text embeddings, benchmark",
"author": null,
"author_email": "MTEB Contributors <niklas@huggingface.co>, nouamane@huggingface.co, info@nils-reimers.de",
"download_url": "https://files.pythonhosted.org/packages/3e/34/bb03dccb94093df846d5b137c20f0916126d9f7e8c13abf7cfdc08c4d99b/mteb-1.38.37.tar.gz",
"platform": null,
"description": "<h1 align=\"center\">Massive Text Embedding Benchmark</h1>\n\n<p align=\"center\">\n <a href=\"https://github.com/embeddings-benchmark/mteb/releases\">\n <img alt=\"GitHub release\" src=\"https://img.shields.io/github/release/embeddings-benchmark/mteb.svg\">\n </a>\n <a href=\"https://arxiv.org/abs/2210.07316\">\n <img alt=\"GitHub release\" src=\"https://img.shields.io/badge/arXiv-2305.14251-b31b1b.svg\">\n </a>\n <a href=\"https://github.com/embeddings-benchmark/mteb/blob/master/LICENSE\">\n <img alt=\"License\" src=\"https://img.shields.io/github/license/embeddings-benchmark/mteb.svg?color=green\">\n </a>\n <a href=\"https://pepy.tech/project/mteb\">\n <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\">\n </a>\n</p>\n\n<h4 align=\"center\">\n <p>\n <a href=\"#installation\">Installation</a> |\n <a href=\"#usage-documentation\">Usage</a> |\n <a href=\"https://huggingface.co/spaces/mteb/leaderboard\">Leaderboard</a> |\n <a href=\"#documentation\">Documentation</a> |\n <a href=\"#citing\">Citing</a>\n <p>\n</h4>\n\n<h3 align=\"center\">\n <a href=\"https://huggingface.co/spaces/mteb/leaderboard\"><img style=\"float: middle; padding: 10px 10px 10px 10px;\" width=\"60\" height=\"55\" src=\"./docs/images/hf_logo.png\" /></a>\n</h3>\n\n\n## Installation\n\n```bash\npip install mteb\n```\n\n\n## Example Usage\n\n\n### Using a script\n\n```python\nimport mteb\nfrom sentence_transformers import SentenceTransformer\n\n# Define the sentence-transformers model name\nmodel_name = \"average_word_embeddings_komninos\"\n\nmodel = mteb.get_model(model_name) # if the model is not implemented in MTEB it will be eq. to SentenceTransformer(model_name)\ntasks = mteb.get_tasks(tasks=[\"Banking77Classification\"])\nevaluation = mteb.MTEB(tasks=tasks)\nresults = evaluation.run(model, output_folder=f\"results/{model_name}\")\n```\n\n### Using the CLI\n\n```bash\nmteb available_tasks # list _all_ available tasks\n\nmteb run -m sentence-transformers/all-MiniLM-L6-v2 \\\n -t Banking77Classification \\\n --verbosity 3\n\n# if nothing is specified default to saving the results in the results/{model_name} folder\n```\n\nNote that using multiple GPUs in parallel can be done by just having a custom encode function that distributes the inputs to multiple GPUs like e.g. [here](https://github.com/microsoft/unilm/blob/b60c741f746877293bb85eed6806736fc8fa0ffd/e5/mteb_eval.py#L60) or [here](https://github.com/ContextualAI/gritlm/blob/09d8630f0c95ac6a456354bcb6f964d7b9b6a609/gritlm/gritlm.py#L75). See [custom models](docs/usage/usage.md#using-a-custom-model) for more information.\n\n\n## Usage Documentation\nThe following links to the main sections in the usage documentation.\n\n| Section | |\n| ------- |- |\n| **General** | |\n| [Evaluating a Model](docs/usage/usage.md#evaluating-a-model) | How to evaluate a model |\n| [Evaluating on different Modalities](docs/usage/usage.md#evaluating-on-different-modalities) | How to evaluate image and image-text tasks |\n| [MIEB](docs/mieb/readme.md) | How to run the Massive Image Embedding Benchmark |\n| **Selecting Tasks** | |\n| [Selecting a benchmark](docs/usage/usage.md#selecting-a-benchmark) | How to select benchmarks |\n| [Task selection](docs/usage/usage.md#task-selection) | How to select and filter tasks |\n|\u00a0[Selecting Split and Subsets](docs/usage/usage.md#selecting-evaluation-split-or-subsets) |\u00a0How to select evaluation splits or subsets |\n| [Using a Custom Task](docs/usage/usage.md#using-a-custom-task) | How to evaluate on a custom task |\n| **Selecting a Model** | |\n| [Using a Pre-defined Model](docs/usage/usage.md#using-a-pre-defined-model) |\u00a0How to run a pre-defined model |\n| [Using a SentenceTransformer Model](docs/usage/usage.md#using-a-sentence-transformer-model) |\u00a0How to run a model loaded using sentence-transformers |\n| [Using a Custom Model](docs/usage/usage.md#using-a-custom-model) |\u00a0How to run and implement a custom model |\n| **Running Evaluation** | |\n| [Passing Arguments to the model](docs/usage/usage.md#passing-in-encode-arguments) | How to pass `encode` arguments to the model |\n| [Running Cross Encoders](docs/usage/usage.md#running-cross-encoders-on-reranking) | How to run cross encoders for reranking |\n| [Running Late Interaction (ColBERT)](docs/usage/usage.md#using-late-interaction-models) | How to run late interaction models |\n| [Saving Retrieval Predictions](docs/usage/usage.md#saving-retrieval-task-predictions) | How to save prediction for later analysis |\n| [Caching Embeddings](docs/usage/usage.md#caching-embeddings-to-re-use-them) | How to cache and re-use embeddings |\n| **Leaderboard** | |\n| [Running the Leaderboard Locally](docs/usage/usage.md#running-the-leaderboard-locally) | How to run the leaderboard locally |\n| [Report Data Contamination](docs/usage/usage.md#annotate-contamination) | How to report data contamination for a model |\n| [Loading and working with Results](docs/usage/results.md) | How to load and working with the raw results from the leaderboard, including making result dataframes |\n\n\n\n## Overview\n\n| Overview | |\n|--------------------------------|-------------------------------------------------------------------------------------|\n| \ud83d\udcc8 [Leaderboard] | The interactive leaderboard of the benchmark |\n| \ud83d\udccb [Tasks] | Overview of available tasks |\n| \ud83d\udcd0 [Benchmarks] | Overview of available benchmarks |\n| **Contributing** | |\n| \ud83e\udd16 [Adding a model] | How to submit a model to MTEB and to the leaderboard |\n| \ud83d\udc69\u200d\ud83d\udd2c [Reproducible workflows] | How to create reproducible workflows with MTEB |\n| \ud83d\udc69\u200d\ud83d\udcbb [Adding a dataset] | How to add a new task/dataset to MTEB |\n| \ud83d\udc69\u200d\ud83d\udcbb [Adding a benchmark] | How to add a new benchmark to MTEB and to the leaderboard |\n| \ud83e\udd1d [Contributing] | How to contribute to MTEB and set it up for development |\n\n[Tasks]: docs/tasks.md\n[Benchmarks]: docs/benchmarks.md\n[Contributing]: CONTRIBUTING.md\n[Adding a model]: docs/adding_a_model.md\n[Adding a dataset]: docs/adding_a_dataset.md\n[Adding a benchmark]: docs/adding_a_benchmark.md\n[Leaderboard]: https://huggingface.co/spaces/mteb/leaderboard\n[Reproducible workflows]: docs/reproducible_workflow.md\n\n## Citing\n\nMTEB 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.\n\n<details>\n <summary> Bibtex Citation (click to unfold) </summary>\n\n\n```bibtex\n@article{muennighoff2022mteb,\n author = {Muennighoff, Niklas and Tazi, Nouamane and Magne, Lo{\\\"\\i}c and Reimers, Nils},\n title = {MTEB: Massive Text Embedding Benchmark},\n publisher = {arXiv},\n journal={arXiv preprint arXiv:2210.07316},\n year = {2022}\n url = {https://arxiv.org/abs/2210.07316},\n doi = {10.48550/ARXIV.2210.07316},\n}\n\n@article{enevoldsen2025mmtebmassivemultilingualtext,\n title={MMTEB: Massive Multilingual Text Embedding Benchmark},\n author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and M\u00e1rton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemi\u0144ski 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\u00f8m and Roman Solomatin and \u00d6mer \u00c7a\u011fatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafa\u0142 Po\u015bwiata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Bj\u00f6rn Pl\u00fcster and Jan Philipp Harries and Lo\u00efc 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 \u0160uppa 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 G\u00fcnther and Mengzhou Xia and Weijia Shi and Xing Han L\u00f9 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},\n publisher = {arXiv},\n journal={arXiv preprint arXiv:2502.13595},\n year={2025},\n url={https://arxiv.org/abs/2502.13595},\n doi = {10.48550/arXiv.2502.13595},\n}\n```\n</details>\n\n\nIf you use any of the specific benchmarks, we also recommend that you cite the authors.\n\n```py\nbenchmark = mteb.get_benchmark(\"MTEB(eng, v2)\")\nbenchmark.citation # get citation for a specific benchmark\n\n# you can also create a table of the task for the appendix using:\nbenchmark.tasks.to_latex()\n```\n\nSome of these amazing publications include (ordered chronologically):\n- Shitao Xiao, Zheng Liu, Peitian Zhang, Niklas Muennighoff. \"[C-Pack: Packaged Resources To Advance General Chinese Embedding](https://arxiv.org/abs/2309.07597)\" arXiv 2023\n- Michael G\u00fcnther, Jackmin Ong, Isabelle Mohr, Alaeddine Abdessalem, Tanguy Abel, Mohammad Kalim Akram, Susana Guzman, Georgios Mastrapas, Saba Sturua, Bo Wang, Maximilian Werk, Nan Wang, Han Xiao. \"[Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents](https://arxiv.org/abs/2310.19923)\" arXiv 2023\n- Silvan Wehrli, Bert Arnrich, Christopher Irrgang. \"[German Text Embedding Clustering Benchmark](https://arxiv.org/abs/2401.02709)\" arXiv 2024\n- Orion Weller, Benjamin Chang, Sean MacAvaney, Kyle Lo, Arman Cohan, Benjamin Van Durme, Dawn Lawrie, Luca Soldaini. \"[FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions](https://arxiv.org/abs/2403.15246)\" arXiv 2024\n- Dawei Zhu, Liang Wang, Nan Yang, Yifan Song, Wenhao Wu, Furu Wei, Sujian Li. \"[LongEmbed: Extending Embedding Models for Long Context Retrieval](https://arxiv.org/abs/2404.12096)\" arXiv 2024\n- Kenneth Enevoldsen, M\u00e1rton Kardos, Niklas Muennighoff, Kristoffer Laigaard Nielbo. \"[The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding](https://arxiv.org/abs/2406.02396)\" arXiv 2024\n- Ali Shiraee Kasmaee, Mohammad Khodadad, Mohammad Arshi Saloot, Nick Sherck, Stephen Dokas, Hamidreza Mahyar, Soheila Samiee. \"[ChemTEB: Chemical Text Embedding Benchmark, an Overview of Embedding Models Performance & Efficiency on a Specific Domain](https://arxiv.org/abs/2412.00532)\" arXiv 2024\n- Chenghao Xiao, Isaac Chung, Imene Kerboua, Jamie Stirling, Xin Zhang, M\u00e1rton Kardos, Roman Solomatin, Noura Al Moubayed, Kenneth Enevoldsen, Niklas Muennighoff. \"[MIEB: Massive Image Embedding Benchmark](https://arxiv.org/abs/2504.10471)\" arXiv 2025\n\n",
"bugtrack_url": null,
"license": "Apache License\n Version 2.0, January 2004\n http://www.apache.org/licenses/\n \n TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION\n \n 1. Definitions.\n \n \"License\" shall mean the terms and conditions for use, reproduction,\n and distribution as defined by Sections 1 through 9 of this document.\n \n \"Licensor\" shall mean the copyright owner or entity authorized by\n the copyright owner that is granting the License.\n \n \"Legal Entity\" shall mean the union of the acting entity and all\n other entities that control, are controlled by, or are under common\n control with that entity. For the purposes of this definition,\n \"control\" means (i) the power, direct or indirect, to cause the\n direction or management of such entity, whether by contract or\n otherwise, or (ii) ownership of fifty percent (50%) or more of the\n outstanding shares, or (iii) beneficial ownership of such entity.\n \n \"You\" (or \"Your\") shall mean an individual or Legal Entity\n exercising permissions granted by this License.\n \n \"Source\" form shall mean the preferred form for making modifications,\n including but not limited to software source code, documentation\n source, and configuration files.\n \n \"Object\" form shall mean any form resulting from mechanical\n transformation or translation of a Source form, including but\n not limited to compiled object code, generated documentation,\n and conversions to other media types.\n \n \"Work\" shall mean the work of authorship, whether in Source or\n Object form, made available under the License, as indicated by a\n copyright notice that is included in or attached to the work\n (an example is provided in the Appendix below).\n \n \"Derivative Works\" shall mean any work, whether in Source or Object\n form, that is based on (or derived from) the Work and for which the\n editorial revisions, annotations, elaborations, or other modifications\n represent, as a whole, an original work of authorship. For the purposes\n of this License, Derivative Works shall not include works that remain\n separable from, or merely link (or bind by name) to the interfaces of,\n the Work and Derivative Works thereof.\n \n \"Contribution\" shall mean any work of authorship, including\n the original version of the Work and any modifications or additions\n to that Work or Derivative Works thereof, that is intentionally\n submitted to Licensor for inclusion in the Work by the copyright owner\n or by an individual or Legal Entity authorized to submit on behalf of\n the copyright owner. For the purposes of this definition, \"submitted\"\n means any form of electronic, verbal, or written communication sent\n to the Licensor or its representatives, including but not limited to\n communication on electronic mailing lists, source code control systems,\n and issue tracking systems that are managed by, or on behalf of, the\n Licensor for the purpose of discussing and improving the Work, but\n excluding communication that is conspicuously marked or otherwise\n designated in writing by the copyright owner as \"Not a Contribution.\"\n \n \"Contributor\" shall mean Licensor and any individual or Legal Entity\n on behalf of whom a Contribution has been received by Licensor and\n subsequently incorporated within the Work.\n \n 2. Grant of Copyright License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n copyright license to reproduce, prepare Derivative Works of,\n publicly display, publicly perform, sublicense, and distribute the\n Work and such Derivative Works in Source or Object form.\n \n 3. Grant of Patent License. Subject to the terms and conditions of\n this License, each Contributor hereby grants to You a perpetual,\n worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n (except as stated in this section) patent license to make, have made,\n use, offer to sell, sell, import, and otherwise transfer the Work,\n where such license applies only to those patent claims licensable\n by such Contributor that are necessarily infringed by their\n Contribution(s) alone or by combination of their Contribution(s)\n with the Work to which such Contribution(s) was submitted. If You\n institute patent litigation against any entity (including a\n cross-claim or counterclaim in a lawsuit) alleging that the Work\n or a Contribution incorporated within the Work constitutes direct\n or contributory patent infringement, then any patent licenses\n granted to You under this License for that Work shall terminate\n as of the date such litigation is filed.\n \n 4. Redistribution. You may reproduce and distribute copies of the\n Work or Derivative Works thereof in any medium, with or without\n modifications, and in Source or Object form, provided that You\n meet the following conditions:\n \n (a) You must give any other recipients of the Work or\n Derivative Works a copy of this License; and\n \n (b) You must cause any modified files to carry prominent notices\n stating that You changed the files; and\n \n (c) You must retain, in the Source form of any Derivative Works\n that You distribute, all copyright, patent, trademark, and\n attribution notices from the Source form of the Work,\n excluding those notices that do not pertain to any part of\n the Derivative Works; and\n \n (d) If the Work includes a \"NOTICE\" text file as part of its\n distribution, then any Derivative Works that You distribute must\n include a readable copy of the attribution notices contained\n within such NOTICE file, excluding those notices that do not\n pertain to any part of the Derivative Works, in at least one\n of the following places: within a NOTICE text file distributed\n as part of the Derivative Works; within the Source form or\n documentation, if provided along with the Derivative Works; or,\n within a display generated by the Derivative Works, if and\n wherever such third-party notices normally appear. The contents\n of the NOTICE file are for informational purposes only and\n do not modify the License. You may add Your own attribution\n notices within Derivative Works that You distribute, alongside\n or as an addendum to the NOTICE text from the Work, provided\n that such additional attribution notices cannot be construed\n as modifying the License.\n \n You may add Your own copyright statement to Your modifications and\n may provide additional or different license terms and conditions\n for use, reproduction, or distribution of Your modifications, or\n for any such Derivative Works as a whole, provided Your use,\n reproduction, and distribution of the Work otherwise complies with\n the conditions stated in this License.\n \n 5. Submission of Contributions. Unless You explicitly state otherwise,\n any Contribution intentionally submitted for inclusion in the Work\n by You to the Licensor shall be under the terms and conditions of\n this License, without any additional terms or conditions.\n Notwithstanding the above, nothing herein shall supersede or modify\n the terms of any separate license agreement you may have executed\n with Licensor regarding such Contributions.\n \n 6. Trademarks. This License does not grant permission to use the trade\n names, trademarks, service marks, or product names of the Licensor,\n except as required for reasonable and customary use in describing the\n origin of the Work and reproducing the content of the NOTICE file.\n \n 7. Disclaimer of Warranty. Unless required by applicable law or\n agreed to in writing, Licensor provides the Work (and each\n Contributor provides its Contributions) on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or\n implied, including, without limitation, any warranties or conditions\n of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A\n PARTICULAR PURPOSE. You are solely responsible for determining the\n appropriateness of using or redistributing the Work and assume any\n risks associated with Your exercise of permissions under this License.\n \n 8. Limitation of Liability. In no event and under no legal theory,\n whether in tort (including negligence), contract, or otherwise,\n unless required by applicable law (such as deliberate and grossly\n negligent acts) or agreed to in writing, shall any Contributor be\n liable to You for damages, including any direct, indirect, special,\n incidental, or consequential damages of any character arising as a\n result of this License or out of the use or inability to use the\n Work (including but not limited to damages for loss of goodwill,\n work stoppage, computer failure or malfunction, or any and all\n other commercial damages or losses), even if such Contributor\n has been advised of the possibility of such damages.\n \n 9. Accepting Warranty or Additional Liability. While redistributing\n the Work or Derivative Works thereof, You may choose to offer,\n and charge a fee for, acceptance of support, warranty, indemnity,\n or other liability obligations and/or rights consistent with this\n License. However, in accepting such obligations, You may act only\n on Your own behalf and on Your sole responsibility, not on behalf\n of any other Contributor, and only if You agree to indemnify,\n defend, and hold each Contributor harmless for any liability\n incurred by, or claims asserted against, such Contributor by reason\n of your accepting any such warranty or additional liability.\n \n END OF TERMS AND CONDITIONS\n \n APPENDIX: How to apply the Apache License to your work.\n \n To apply the Apache License to your work, attach the following\n boilerplate notice, with the fields enclosed by brackets \"[]\"\n replaced with your own identifying information. (Don't include\n the brackets!) The text should be enclosed in the appropriate\n comment syntax for the file format. We also recommend that a\n file or class name and description of purpose be included on the\n same \"printed page\" as the copyright notice for easier\n identification within third-party archives.\n \n Copyright [yyyy] [name of copyright owner]\n \n Licensed under the Apache License, Version 2.0 (the \"License\");\n you may not use this file except in compliance with the License.\n You may obtain a copy of the License at\n \n http://www.apache.org/licenses/LICENSE-2.0\n \n Unless required by applicable law or agreed to in writing, software\n distributed under the License is distributed on an \"AS IS\" BASIS,\n WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n See the License for the specific language governing permissions and\n limitations under the License.\n ",
"summary": "Massive Text Embedding Benchmark",
"version": "1.38.37",
"project_urls": {
"Huggingface Organization": "https://huggingface.co/mteb",
"Source Code": "https://github.com/embeddings-benchmark/mteb",
"homepage": "https://github.com/embeddings-benchmark/mteb"
},
"split_keywords": [
"deep learning",
" text embeddings",
" benchmark"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "273eba856cb83dee24e7c40e69c6528205b002e1dd4c5e0375da804665b0dad2",
"md5": "3b9fda6c536cc5c5b9a7bf420490ed7b",
"sha256": "e693054e2b20a353848b0de6564e9b656aa32e1b79babe48d8db8edffc3db2d8"
},
"downloads": -1,
"filename": "mteb-1.38.37-py3-none-any.whl",
"has_sig": false,
"md5_digest": "3b9fda6c536cc5c5b9a7bf420490ed7b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.13,>=3.9",
"size": 1668934,
"upload_time": "2025-07-21T11:43:48",
"upload_time_iso_8601": "2025-07-21T11:43:48.967474Z",
"url": "https://files.pythonhosted.org/packages/27/3e/ba856cb83dee24e7c40e69c6528205b002e1dd4c5e0375da804665b0dad2/mteb-1.38.37-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "3e34bb03dccb94093df846d5b137c20f0916126d9f7e8c13abf7cfdc08c4d99b",
"md5": "7ec3c866fd5f2a4ce2b87e15373cc222",
"sha256": "145ad820565b634fcbf99f9e2ed573205b6a1611a083b999f8bedeca7b5bbb96"
},
"downloads": -1,
"filename": "mteb-1.38.37.tar.gz",
"has_sig": false,
"md5_digest": "7ec3c866fd5f2a4ce2b87e15373cc222",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.13,>=3.9",
"size": 1018042,
"upload_time": "2025-07-21T11:43:51",
"upload_time_iso_8601": "2025-07-21T11:43:51.567278Z",
"url": "https://files.pythonhosted.org/packages/3e/34/bb03dccb94093df846d5b137c20f0916126d9f7e8c13abf7cfdc08c4d99b/mteb-1.38.37.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-21 11:43:51",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "embeddings-benchmark",
"github_project": "mteb",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "mteb"
}