Brain-Score Language is a platform to evaluate computational models of language on their match to behavioral and neural
measurements in the domain of language processing. The intent of Brain-Score is to adopt many (ideally all) the
experimental benchmarks in the field for the purpose of model testing, falsification, and comparison. To that end,
Brain-Score operationalizes experimental data into quantitative benchmarks that any model candidate following
the BrainModel interface can be scored on.
See the Documentation for more details.
Brain-Score is made by and for the community. To contribute, please send in a pull request.
Alpha status
This repository is under active development, and should be considered to be in an alpha status. Code is likely to change substantially, without backwards compatibility. Please let us know of any problems by creating an issue.
Setup
python -m pip install -e "." # change "." to ".[test]" to include testing dependencies
Please note that plugins (models, benchmarks, data, and metrics) may require additional dependencies beyond those installed here. Default behavior will install these dependencies directly into the runtime environment.
To avoid conflicts, we encourage either using an environment manager or setting the BS_INSTALL_DEPENDENCIES environment variable to either no or newenv (e.g. export BS_INSTALL_DEPENDENCIES=newenv).
no will leave all dependency installation up to the user, whereas newenv will create a new conda environment for the duration of the run. If you would like to use the newenv option and do not already have conda installed, you can follow the installation instructions here.
Usage
Score an existing model on an existing benchmark:
python brainscore_language score --model_identifier='distilgpt2' --benchmark_identifier='Futrell2018-pearsonr'
License
MIT license
1 maintainer
Metadata
1 maintainer
Release files for brainscore-language 2.3.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| brainscore_language-2.3.0.tar.gz | 687.7 kB | With provenance | Details for brainscore_language-2.3.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| brainscore_language-2.3.0-py3-none-any.whl | Python 3 | none | any | Details for brainscore_language-2.3.0-py3-none-any.whl |
Total release size: 1.5 MB
Release files / brainscore_language-2.3.0.tar.gz
| Download URL | brainscore_language-2.3.0.tar.gz |
|---|---|
| Size | 687.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4b71bf4908a2c27f67575a69118e479ba6b931dfca0f94635a317771b43f25d4
|
|
BLAKE2b-256 checksum How to use checksums |
2274d23111477ea61e9209498b94603c0c1e1069a6756e6bff1e32f3526c705b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 9, 2026.
Transparency logRelease files / brainscore_language-2.3.0-py3-none-any.whl
| Download URL | brainscore_language-2.3.0-py3-none-any.whl |
|---|---|
| Size | 781.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ebaa5c5b9742429a6b84dd89d0ef1db3b41372f4b862dc55631afc3fd10bf57d
|
|
BLAKE2b-256 checksum How to use checksums |
e883888c51a821d2195f6f501e1fca2a8ea41c61f07fd0c0ce79a9c161ee1256
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 9, 2026.
Transparency logSecurity for brainscore-language 2.3.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for brainscore_language-2.3.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 9, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
