Add wbench eval framework#2200
Merged
Merged
Conversation
KainingYing
requested review from
NathanHB,
gary149,
julien-c,
krampstudio and
pcuenca
as code owners
NathanHB
approved these changes
Jun 1, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds
wbenchto the supported evaluation frameworks for benchmark dataseteval.yamlfiles.WBench is a comprehensive multi-turn benchmark for interactive video world model evaluation, assessing models across 5 dimensions (video quality, setting adherence, interaction adherence, consistency, physics compliance) and 22 metrics over 289 multi-turn interaction cases.
Dataset prepared for the Hub Evaluation Results feature:
https://huggingface.co/datasets/meituan-longcat/WBench
The dataset repo already includes an
eval.yaml.Note
Low Risk
Registry-only metadata change with no runtime logic, auth, or data path changes.
Overview
Registers
wbenchinEVALUATION_FRAMEWORKS(packages/tasks/src/eval.ts) so benchmark datasets can declare it ineval.yamland surface correctly on Hub Evaluation Results.The new entry includes display name, a short description of WBench (multi-turn interactive video world model evaluation), and a link to the upstream repo.
Reviewed by Cursor Bugbot for commit 30f6c1c. Bugbot is set up for automated code reviews on this repo. Configure here.