Saved in:
Bibliographic Details
Main Authors: Xu, Xiaojie, Lin, Zhengyuan, He, Kang, Feng, Yukang, Mao, Xiaofeng, Yin, Yuanyang, Zhang, Kaipeng, Ge, Yongtao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.21686
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908989707517952
author Xu, Xiaojie
Lin, Zhengyuan
He, Kang
Feng, Yukang
Mao, Xiaofeng
Yin, Yuanyang
Zhang, Kaipeng
Ge, Yongtao
author_facet Xu, Xiaojie
Lin, Zhengyuan
He, Kang
Feng, Yukang
Mao, Xiaofeng
Yin, Yuanyang
Zhang, Kaipeng
Ge, Yongtao
contents Interactive video generation models such as Genie, YUME, HY-World, and Matrix-Game are advancing rapidly, yet every model is evaluated on its own benchmark with private scenes and trajectories, making fair cross-model comparison impossible. Existing public benchmarks offer useful metrics such as trajectory error, aesthetic scores, and VLM-based judgments, but none supplies the standardized test conditions -- identical scenes, identical action sequences, and a unified control interface -- needed to make those metrics comparable across models with heterogeneous inputs. We introduce WorldMark, the first benchmark that provides such a common playing field for interactive Image-to-Video world models. WorldMark contributes: (1) a unified action-mapping layer that translates a shared WASD-style action vocabulary into each model's native control format, enabling apples-to-apples comparison across six major models on identical scenes and trajectories; (2) a hierarchical test suite of 500 evaluation cases covering first- and third-person viewpoints, photorealistic and stylized scenes, and three difficulty tiers from Easy to Hard spanning 20-60s; and (3) a modular evaluation toolkit for Visual Quality, Control Alignment, and World Consistency, designed so that researchers can reuse our standardized inputs while plugging in their own metrics as the field evolves. We will release all data, evaluation code, and model outputs to facilitate future research. Beyond offline metrics, we launch World Model Arena (warena.ai), an online platform where anyone can pit leading world models against each other in side-by-side battles and watch the live leaderboard.
format Preprint
id arxiv_https___arxiv_org_abs_2604_21686
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle WorldMark: A Unified Benchmark Suite for Interactive Video World Models
Xu, Xiaojie
Lin, Zhengyuan
He, Kang
Feng, Yukang
Mao, Xiaofeng
Yin, Yuanyang
Zhang, Kaipeng
Ge, Yongtao
Computer Vision and Pattern Recognition
Interactive video generation models such as Genie, YUME, HY-World, and Matrix-Game are advancing rapidly, yet every model is evaluated on its own benchmark with private scenes and trajectories, making fair cross-model comparison impossible. Existing public benchmarks offer useful metrics such as trajectory error, aesthetic scores, and VLM-based judgments, but none supplies the standardized test conditions -- identical scenes, identical action sequences, and a unified control interface -- needed to make those metrics comparable across models with heterogeneous inputs. We introduce WorldMark, the first benchmark that provides such a common playing field for interactive Image-to-Video world models. WorldMark contributes: (1) a unified action-mapping layer that translates a shared WASD-style action vocabulary into each model's native control format, enabling apples-to-apples comparison across six major models on identical scenes and trajectories; (2) a hierarchical test suite of 500 evaluation cases covering first- and third-person viewpoints, photorealistic and stylized scenes, and three difficulty tiers from Easy to Hard spanning 20-60s; and (3) a modular evaluation toolkit for Visual Quality, Control Alignment, and World Consistency, designed so that researchers can reuse our standardized inputs while plugging in their own metrics as the field evolves. We will release all data, evaluation code, and model outputs to facilitate future research. Beyond offline metrics, we launch World Model Arena (warena.ai), an online platform where anyone can pit leading world models against each other in side-by-side battles and watch the live leaderboard.
title WorldMark: A Unified Benchmark Suite for Interactive Video World Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.21686