OpenCompass
OpenCompass CommunityEvaluation platform covering more than a hundred datasets across open and API models, with both objective scoring and subjective arena-style comparison. Backed by Shanghai AI Lab, it has notably deeper Chinese-language and multimodal coverage than the English-first harnesses.
Verified 2026-08-13 via the open-compass/opencompass repository and its license endpoint.
Openness
5 high confidence- license
- Apache-2.0(OSI)
- source
- public(GitHub)
- core-gated
- ungated
Apache-2.0 and fully public, and Apache-2.0 is an OSI license, so this is open source.
- https://github.com/open-compass/opencompass recorded 2026-06-04
Apache-2.0 license, public source, v0.5.2 (Feb 2026)
- https://api.github.com/repos/open-compass/opencompass/license recorded 2026-08-13
GitHub's license endpoint reports spdx_id Apache-2.0 for open-compass/opencompass and returns the Apache-2.0 text as the LICENSE body.
- https://raw.githubusercontent.com/open-compass/opencompass/main/README.md recorded 2026-08-13
README installs the platform with `pip install -U opencompass` or editable from a clone and runs evaluations locally against local weights or model APIs; all dataset and model configs ship inside the package. CompassRank and CompassHub are free public leaderboard and dataset sites beside it. No pricing, enterprise edition, paid tier or license key appears in the README.
Adoption
3 medium confidenceA widely used eval framework, especially in the China and Hugging Face ecosystems, with 7.1k GitHub stars and broad dataset and backend coverage. No clean download headline is available, so the level rests on reported traction - framework distribution plus the star footprint - rather than on stars alone, which would cap it lower. A PyPI package named opencompass does exist and is genuinely this project's, but it is not the measure used: it sees 5,728 downloads a month against a project whose documented path is a git clone and a config tree, so banding on it would read a minority channel rather than the project.
- https://github.com/open-compass/opencompass recorded 2026-06-04
7.1k stars; 100+ datasets, multi-backend eval framework
- https://api.github.com/repos/open-compass/opencompass recorded 2026-08-13
stargazers_count = 7,299, forks 837, pushed_at 2026-08-12, license Apache-2.0
- https://raw.githubusercontent.com/open-compass/opencompass/main/README.md recorded 2026-08-13
README still describes 100+ supported datasets and the CompassRank public leaderboards that carry the project's reported traction.
Capability
4 medium confidenceVery broad multi-benchmark coverage and backend breadth, sitting just below lm-eval as the standardization reference - strong, but not the single de-facto global standard. The README claims 100+ datasets and lists Hugging Face, LMDeploy, vLLM and API backends as install extras.
- https://github.com/open-compass/opencompass recorded 2026-06-04
100+ datasets, 20+ HF + API model backends
- https://raw.githubusercontent.com/open-compass/opencompass/main/README.md recorded 2026-08-13
100+ supported datasets; model backends offered as install extras (`opencompass[full]`, `[lmdeploy]`, `[vllm]`, `[api]`); subjective and objective scoring modes documented.
Verified 2026-08-13