open-compass / open-compass/VLMEvalKit
【OmniDocBench】Recommend updating the benchmark version
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 4.4k
- Forks
- 768
- Avg merge
- 1d 10h
- Merged PRs (30d)
- 17
Description
Hi, Thanks for the great work on this framework!
I noticed that the current OmniDocBench in VLMEvalKit is still v1.0 (981 images). However, the benchmark has been officially updated to v1.5 with 1,355 images. Will the benchmark update to v1.5 in the future?
Best regards!
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by locating the existing OmniDocBench v1.0 integration and confirming how its 981-image dataset is wired into VLMEvalKit. Compare the official v1.5 release with 1,355 images and identify the required benchmark update; done when the framework evaluates against the v1.5 image set.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, testing-qa
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 42/100