Metadata-Version: 2.1
Name: mteb
Version: 1.21.4
Summary: Massive Text Embedding Benchmark
Author-email: MTEB Contributors <niklas@huggingface.co>, nouamane@huggingface.co, info@nils-reimers.de
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: Huggingface Organization, https://huggingface.co/mteb
Project-URL: Source Code, https://github.com/embeddings-benchmark/mteb
Keywords: deep learning,text embeddings,benchmark
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: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: datasets<3.0.0,>=2.19.0
Requires-Dist: numpy<3.0.0,>=1.0.0
Requires-Dist: requests>=2.26.0
Requires-Dist: scikit_learn>=1.0.2
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: typing_extensions>=0.0.0
Requires-Dist: eval_type_backport>=0.0.0
Requires-Dist: polars>=0.20.22
Provides-Extra: dev
Requires-Dist: ruff==0.6.4; extra == "dev"
Requires-Dist: pytest; extra == "dev"
Requires-Dist: pytest-xdist; extra == "dev"
Requires-Dist: pytest-coverage; extra == "dev"
Provides-Extra: codecarbon
Requires-Dist: codecarbon; extra == "codecarbon"
Provides-Extra: speedtask
Requires-Dist: GPUtil>=1.4.0; extra == "speedtask"
Requires-Dist: psutil>=5.9.8; extra == "speedtask"
Provides-Extra: peft
Requires-Dist: peft>=0.11.0; extra == "peft"
Provides-Extra: leaderboard
Requires-Dist: gradio>=5.7.1; extra == "leaderboard"
Requires-Dist: gradio_rangeslider>=0.0.8; extra == "leaderboard"
Provides-Extra: flagembedding
Requires-Dist: FlagEmbedding; extra == "flagembedding"
Provides-Extra: jina
Requires-Dist: einops>=0.8.0; extra == "jina"
Provides-Extra: flash-attention
Requires-Dist: flash-attn>=2.6.3; extra == "flash-attention"

<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 Python 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}")
```

<details>
  <summary> Running SentenceTransformer model with prompts </summary>

Prompts can be passed to the SentenceTransformer model using the `prompts` parameter. The following code shows how to use prompts with SentenceTransformer:

```python
from sentence_transformers import SentenceTransformer


model = SentenceTransformer("average_word_embeddings_komninos", prompts={"query": "Query:", "passage": "Passage:"})
evaluation = mteb.MTEB(tasks=tasks)
```

In prompts the key can be:
1. Prompt types (`passage`, `query`) - they will be used in reranking and retrieval tasks 
2. Task type - these prompts will be used in all tasks of the given type
   1. `BitextMining`
   2. `Classification`
   3. `MultilabelClassification`
   4. `Clustering`
   5. `PairClassification`
   6. `Reranking`
   7. `Retrieval`
   8. `STS`
   9. `Summarization`
   10. `InstructionRetrieval`
3. Pair of task type and prompt type like `Retrival-query` - these prompts will be used in all classification tasks
4. Task name - these prompts will be used in the specific task
5. Pair of task name and prompt type like `NFCorpus-query` - these prompts will be used in the specific task
</details>

* Using CLI

```bash
mteb 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
```

* 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).



## Usage Documentation
Click on each section below to see the details.

<br /> 

<details>
  <summary>  Task selection </summary>

### Task selection

Tasks can be selected by providing the list of datasets, but also

* by their task (e.g. "Clustering" or "Classification")

```python
tasks = mteb.get_tasks(task_types=["Clustering", "Retrieval"]) # Only select clustering and retrieval tasks
```

* by their categories e.g. "s2s" (sentence to sentence) or "p2p" (paragraph to paragraph)

```python
tasks = mteb.get_tasks(categories=["s2s", "p2p"]) # Only select sentence2sentence and paragraph2paragraph datasets
```

* by their languages

```python
tasks = mteb.get_tasks(languages=["eng", "deu"]) # Only select datasets which contain "eng" or "deu" (iso 639-3 codes)
```

You can also specify which languages to load for multilingual/cross-lingual tasks like below:

```python
import mteb

tasks = [
    mteb.get_task("AmazonReviewsClassification", languages = ["eng", "fra"]),
    mteb.get_task("BUCCBitextMining", languages = ["deu"]), # all subsets containing "deu"
]

# or you can select specific huggingface subsets like this:
from mteb.tasks import AmazonReviewsClassification, BUCCBitextMining

evaluation = mteb.MTEB(tasks=[
        AmazonReviewsClassification(hf_subsets=["en", "fr"]) # Only load "en" and "fr" subsets of Amazon Reviews
        BUCCBitextMining(hf_subsets=["de-en"]), # Only load "de-en" subset of BUCC
])
# for an example of a HF subset see "Subset" in the dataset viewer at: https://huggingface.co/datasets/mteb/bucc-bitext-mining
```

</details>

<details>
  <summary>  Running a benchmark </summary>

### Running a Benchmark

`mteb` comes with a set of predefined benchmarks. These can be fetched using `get_benchmark` and run in a similar fashion to other sets of tasks. 
For instance to select the 56 English datasets that form the "Overall MTEB English leaderboard":

```python
import mteb
benchmark = mteb.get_benchmark("MTEB(eng, classic)")
evaluation = mteb.MTEB(tasks=benchmark)
```

The benchmark specified not only a list of tasks, but also what splits and language to run on. To get an overview of all available benchmarks simply run:

```python
import mteb
benchmarks = mteb.get_benchmarks()
```

Generally we use the naming scheme for benchmarks `MTEB(*)`, where the "*" denotes the target of the benchmark. In the case of a language, we use the three-letter language code. For large groups of languages, we use the group notation, e.g., `MTEB(Scandinavian)` for Scandinavian languages. External benchmarks implemented in MTEB like `CoIR` use their original name. When using a benchmark from MTEB please cite `mteb` along with the citations of the benchmark which you can access using:

```python
benchmark.citation
```

</details>

<details>
  <summary>  Passing in `encode` arguments </summary>


### Passing in `encode` arguments

To pass in arguments to the model's `encode` function, you can use the encode keyword arguments (`encode_kwargs`):

```python
evaluation.run(model, encode_kwargs={"batch_size": 32})
```
</details>


<details>
  <summary>  Selecting evaluation split </summary>

### Selecting evaluation split
You can evaluate only on `test` splits of all tasks by doing the following:

```python
evaluation.run(model, eval_splits=["test"])
```

Note that the public leaderboard uses the test splits for all datasets except MSMARCO, where the "dev" split is used.

</details>

<details>
  <summary>  Using a custom model </summary>


### Using a custom model

Models should implement the following interface, implementing an `encode` function taking as inputs a list of sentences, and returning a list of embeddings (embeddings can be `np.array`, `torch.tensor`, etc.). For inspiration, you can look at the [mteb/mtebscripts repo](https://github.com/embeddings-benchmark/mtebscripts) used for running diverse models via SLURM scripts for the paper.

```python
import mteb
from mteb.encoder_interface import PromptType
import numpy as np


class CustomModel:
    def encode(
        self,
        sentences: list[str],
        task_name: str,
        prompt_type: PromptType | None = None,
        **kwargs,
    ) -> np.ndarray:
        """Encodes the given sentences using the encoder.
        
        Args:
            sentences: The sentences to encode.
            task_name: The name of the task.
            prompt_type: The prompt type to use.
            **kwargs: Additional arguments to pass to the encoder.
            
        Returns:
            The encoded sentences.
        """
        pass

model = CustomModel()
tasks = mteb.get_tasks(tasks=["Banking77Classification"])
evaluation = MTEB(tasks=tasks)
evaluation.run(model)
```

</details>

<details>
  <summary>  Evaluating on a custom dataset </summary>


### Evaluating on a custom dataset

To evaluate on a custom task, you can run the following code on your custom task. See [how to add a new task](docs/adding_a_dataset.md), for how to create a new task in MTEB.

```python
from mteb import MTEB
from mteb.abstasks.AbsTaskReranking import AbsTaskReranking
from sentence_transformers import SentenceTransformer


class MyCustomTask(AbsTaskReranking):
    ...

model = SentenceTransformer("average_word_embeddings_komninos")
evaluation = MTEB(tasks=[MyCustomTask()])
evaluation.run(model)
```

</details>

<details>
  <summary>  Using a cross encoder for reranking</summary>


### Using a cross encoder for reranking

To use a cross encoder for reranking, you can directly use a CrossEncoder from SentenceTransformers. The following code shows a two-stage run with the second stage reading results saved from the first stage. 

```python
from mteb import MTEB
import mteb
from sentence_transformers import CrossEncoder, SentenceTransformer

cross_encoder = CrossEncoder("cross-encoder/ms-marco-TinyBERT-L-2-v2")
dual_encoder = SentenceTransformer("all-MiniLM-L6-v2")

tasks = mteb.get_tasks(tasks=["NFCorpus"], languages=["eng"])

subset = "default" # subset name used in the NFCorpus dataset
eval_splits = ["test"]

evaluation = MTEB(tasks=tasks)
evaluation.run(
    dual_encoder,
    eval_splits=eval_splits,
    save_predictions=True,
    output_folder="results/stage1",
)
evaluation.run(
    cross_encoder,
    eval_splits=eval_splits,
    top_k=5,
    save_predictions=True,
    output_folder="results/stage2",
    previous_results=f"results/stage1/NFCorpus_{subset}_predictions.json",
)
```

</details>

<details>
  <summary>  Saving retrieval task predictions </summary>

### Saving retrieval task predictions

To save the predictions from a retrieval task, add the `--save_predictions` flag in the CLI or set `save_predictions=True` in the run method. The filename will be in the "{task_name}_{subset}_predictions.json" format.

Python:
```python
from mteb import MTEB
import mteb
from sentence_transformers import SentenceTransformer

model = SentenceTransformer("all-MiniLM-L6-v2")

tasks = mteb.get_tasks(tasks=["NFCorpus"], languages=["eng"])

evaluation = MTEB(tasks=tasks)
evaluation.run(
    model,
    eval_splits=["test"],
    save_predictions=True,
    output_folder="results",
)
```

CLI:
```bash
mteb run -t NFCorpus -m all-MiniLM-L6-v2 --output_folder results --save_predictions
```

</details>

<details>
  <summary> Fetching result from the results repository </summary>

### Fetching results from the results repository

Multiple models have already been run on tasks available within MTEB. These results are available results [repository](https://github.com/embeddings-benchmark/results).

To make the results more easily accessible, we have designed custom functionality for retrieving from the repository. For instance, if you are selecting the best model for your French and English retrieval task on legal documents you could fetch the relevant tasks and create a dataframe of the results using the following code:

```python
import mteb
from mteb.task_selection import results_to_dataframe

tasks = mteb.get_tasks(
    task_types=["Retrieval"], languages=["eng", "fra"], domains=["Legal"]
)

model_names = [
    "GritLM/GritLM-7B",
    "intfloat/multilingual-e5-small",
    "intfloat/multilingual-e5-base",
    "intfloat/multilingual-e5-large",
]
models = [mteb.get_model_meta(name) for name in model_names]

results = mteb.load_results(models=models, tasks=tasks)

df = results_to_dataframe(results)
```

</details>

<details>
  <summary>  Caching Embeddings To Re-Use Them </summary>


### Caching Embeddings To Re-Use Them

There are times you may want to cache the embeddings so you can re-use them. This may be true if you have multiple query sets for the same corpus (e.g. Wikipedia) or are doing some optimization over the queries (e.g. prompting, other experiments). You can setup a cache by using a simple wrapper, which will save the cache per task in the `cache_embeddings/{task_name}` folder:

```python
# define your task and model above as normal
...
# wrap the model with the cache wrapper
from mteb.models.cache_wrapper import CachedEmbeddingWrapper
model_with_cached_emb = CachedEmbeddingWrapper(model, cache_path='path_to_cache_dir')
# run as normal
evaluation.run(model, ...) 
```

</details>

<br /> 



## Documentation

| Documentation                  |                        |
| ------------------------------ | ---------------------- |
| 📋 [Tasks] | Overview of available tasks |
| 📐 [Benchmarks] | Overview of available benchmarks |
| 📈 [Leaderboard] | The interactive leaderboard of the benchmark |
| 🤖 [Adding a model] | Information related to how to submit a model to the leaderboard |
| 👩‍🔬 [Reproducible workflows] | Information related to how to reproduce and create reproducible workflows with MTEB |
| 👩‍💻 [Adding a dataset] | How to add a new task/dataset to MTEB | 
| 👩‍💻 [Adding a leaderboard tab] | How to add a new leaderboard tab to MTEB | 
| 🤝 [Contributing] | How to contribute to MTEB and set it up for development |
| 🌐 [MMTEB] | An open-source effort to extend MTEB to cover a broad set of languages |  

[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 leaderboard tab]: docs/adding_a_leaderboard_tab.md
[Leaderboard]: https://huggingface.co/spaces/mteb/leaderboard
[MMTEB]: docs/mmteb/readme.md
[Reproducible workflows]: docs/reproducible_workflow.md

## Citing

MTEB was introduced in "[MTEB: Massive Text Embedding Benchmark](https://arxiv.org/abs/2210.07316)", feel free to cite:

```bibtex
@article{muennighoff2022mteb,
  doi = {10.48550/ARXIV.2210.07316},
  url = {https://arxiv.org/abs/2210.07316},
  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}
}
```

You may also want to read and cite the amazing work that has extended MTEB & integrated new datasets:
- 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

For works that have used MTEB for benchmarking, you can find them on the [leaderboard](https://huggingface.co/spaces/mteb/leaderboard).
