Leaderboard Leaderboards / OpenVLM Leaderboard (OpenCompass)
OpenVLM Leaderboard (OpenCompass)
Vision-language model results produced with VLMEvalKit.
- Operator
- OpenCompass (Shanghai AI Lab)
- Leaderboard
- huggingface.co
- Category
- Multimodal
- How results are made
- Operator runs the evals
- Checked
- 2026-10-31
Raw data
| Format | Where |
|---|---|
| JSON download | opencompass.openxlab.space/assets/OpenVLM.json All detailed results as one JSON file. “The performance numbers on our official multi-modal leaderboards can be downloaded from here!” (raw.githubusercontent.com) |
Licence / reuse: Unclear
Apache-2.0 (licence of the repository that holds the result files). A licence exists, but it covers the code or website rather than clearly the results.
“Apache License Version 2.0, January 2004”
Source: raw.githubusercontent.com/open-compass/VLMEvalKit/main/LICENSE
Apache-2.0 covers VLMEvalKit; the JSON download has no licence statement.
Submissions: Not stated
We found no statement about outside submissions.
Last updated: 2026-03-11 234 days old
- 2026-03-11: Hugging Face lastModified of Space opencompass/open_vlm_leaderboard · huggingface.co
This page lists where the data lives and what the licence says. It does not copy any scores; open the leaderboard for those. Not legal advice. Something wrong? Use the bug link in the footer. Back to all leaderboards.