OpenCompassLanguage-model evaluation across knowledge, reasoning, coding, and other tasks.Apache-2.0
Language-model evaluation across knowledge, reasoning, coding, and other tasks.
OpenCompass organizes model evaluation into dataset and model configuration, inference, scoring and result summaries. Researchers can compare locally hosted and API-accessible models using backends such as Hugging Face, LMDeploy and vLLM, with rule-based or model-assisted judging. Its Python tooling supports distributed evaluation, while integration with VLMEvalKit extends the workflow to vision-language models as well as text models.
OpenCompass official README · Reviewed 2026-10-29
- 01 / Feature noteEvaluation pipeline
Configure datasets and models, run inference and evaluation, then summarize the results.
Feature source ↗ - 02 / Feature noteMultiple judging methods
Evaluate outputs using rule-based scoring or a language model acting as judge.
Feature source ↗
GitHub stars
7,563
Detected license
Apache-2.0
Repository created
2023-06-15
Repository push
2026-11-03
2023-06-15GitHub release
2026-08-26 · 0.5.4Repository push
2026-11-03
GitHub stars
Unknown
i
Cached history uses a different month window; chart withheld until aligned.
Latest attempt: ok · Checked 2026-10-15T19:40:39.600225+00:00 · Last successful fetch 2026-10-15T19:40:39.600225+00:00 · Provider source
Hacker News stories
Unknown
i
OpenSSF Scorecard
Unknown
i
No result returned.
Checked 2026-10-26T23:54:49Z · Latest attempt: not found · Provider source
GitHub release
Published 2026-08-26
i
Checked 2026-11-04T04:04:05Z · Last successful fetch 2026-11-04T04:04:05Z · Value fetched 2026-11-04T04:04:05Z · Provider source
Unknown
