swo-bench
swo-bench measures inference-endpoint performance with recorded and catalog
agentic workloads. Start with:
swo-bench replay --help
For agentic recordings whose prompts approach the model's context window, pass
--tokenizer <model> to swo-bench replay so prompts are sized with the model's
own tokenizer. Without it, a character estimate is used and some requests near the
limit can be rejected by the endpoint. --tokenizer needs the optional extra:
pip install 'swo-bench[tokenizer]'
Product documentation, examples, and support information are available at https://swarmone.ai/docs/swo-bench.
1 maintainer
Metadata
1 maintainer
Release files for swo-bench 4.0.2
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 |
|---|---|---|---|---|
| swo_bench-4.0.2.tar.gz | 318.6 kB | Without provenance | Details for swo_bench-4.0.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| swo_bench-4.0.2-py3-none-any.whl | Python 3 | none | any | Details for swo_bench-4.0.2-py3-none-any.whl |
Total release size: 722.4 kB
Release files / swo_bench-4.0.2.tar.gz
| Download URL | swo_bench-4.0.2.tar.gz |
|---|---|
| Size | 318.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c956f63cb72ca1b374eebb05be692c976e3567afd146417964fd9854bb77112c
|
|
BLAKE2b-256 checksum How to use checksums |
acb4ed08132378188924338ae9117ae1e17e4667460ccd212f24e2ae1930aab1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Release files / swo_bench-4.0.2-py3-none-any.whl
| Download URL | swo_bench-4.0.2-py3-none-any.whl |
|---|---|
| Size | 403.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2fc38229a2899358f4ec0a457907e8591b912d32dd5f18465e42a96cd936f8e4
|
|
BLAKE2b-256 checksum How to use checksums |
b98c24658df83365b3ade387580d82db0f9ba88b56b03e4f518a04dc7af3c8cc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Security for swo-bench 4.0.2
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A 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.
