open-compass / open-compass/VLMEvalKit

Qwen3-VL on ScreenSpot datasets

Open
#1,332 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
4.4k
Forks
768
Avg merge
1d 10h
Merged PRs (30d)
17

Description

Hi, I got very low score for Qwen3-VL on ScreenSpot datasets. According to Qwen3-VL's docs, it's grounding output is normed to a 0-1000 value. Should I change the normalization method in ScreenSpot datasets to click_point = (click_point[0] / 1000, click_point[1] / 1000) ?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No file or test is named. Start by locating the ScreenSpot dataset normalization and the Qwen3-VL evaluation entry point, then compare the documented 0-1000 grounding coordinates with the current conversion. Done means confirming the correct normalization and showing that ScreenSpot scores improve or remain correct for Qwen3-VL.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
42/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.