🎊 News

• [2026/07] 🔥Peking University and Kuaishou Kling Team evaluate their agentic visual reasoning method Beacon on our GameQA benchmark. Beacon learns when tools are truly needed (Mode Adaptiveness) and how tool use extends capability on hard problems (Tool Effect), and achieves the highest accuracy on GameQA among open-source models of the same scale, significantly outperforming its Qwen3-VL-8B-Instruct base.
• [2026/07] 🔥Peking University and WeChat AI use our Game-RL data synthesis code in the ICML 2026 paper ReaForest for 2D Maze, 3D Maze, and Sokoban spatial-planning tasks.
• [2026/06] 🔥Shanghai AI Lab uses our Game-RL codebase in MoTiF, building 15K+ Sokoban and Maze interleaved-thinking samples.
• [2026/04] 🔥Princeton University uses our GameQA dataset in their Vero project.
• [2026/03] 🔥National University of Singapore uses our games in the Gym-V platform.
• [2026/02] 🔥Alibaba Group and Shanghai Jiao Tong University use our GameQA-140K dataset at scale in the DeepVision-103K dataset, which accounts for around 50% of its "visual logic problems".
• [2026/01] 🔥Shanghai AI Lab uses our GameQA-140K dataset at scale in the MMFineReason dataset, which accounts for 87.65% of its "Puzzle/Game" samples.
• [2026/01] 🔥THUML and ByteDance Seed use our Sokoban code for the synthesis of the Sokoban task samples in VisWorld-Eval (and the training data).
• [2026/01] 🔥🔥Our work has been accepted by ICLR 2026! 🎉🎉🎉
• [2025/11] 🔥DeepWisdom and Tsinghua University use the maze-like games in our GameQA dataset in the VR-Bench benchmark, which evaluates video models' reasoning.
• [2025/11] 🔥Shanghai Innovation Institute uses the games in our GameQA dataset for image editing reasoning tasks ("game-world scenarios"), developing the UniREditBench benchmark and the UniREdit-Data-100K training data.

1. Overview

GameQA is a large-scale, diverse, and challenging multimodal reasoning dataset designed to enhance the general reasoning capabilities of Vision Language Models (VLMs). Generated using the innovative Code2Logic framework, it leverages game code to synthesize high-quality visual-language Chain-of-Thought (CoT) data. The dataset addresses the scarcity of multimodal reasoning data, critical for advancing complex multi-step reasoning in VLMs. Each sample includes visual game state, targeted question, original analysis, augmented step-by-step reasoning (refinement) and final answer, derived from the logical structures inherent in game code.

📖 Paper: Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs’ General Reasoning

🔗 Website: https://iclr26-game-rl.github.io

💻 Code: https://github.com/tongjingqi/Game-RL

2. Dataset Files

For a quick preview of the dataset, GameQA-data_studio-preview.parquet contains 300 sampled entries from the training set. This file is optimized for online viewing in tools like Data Studio and includes embedded image data.

For the full training dataset, please download games_data.json.

For the full test dataset, please download games_data_test.json.

Associated image files are available in games_images.zip and games_images_test.zip respectively.

3. Dataset Description

🔎 Citation

If you find our work or dataset useful, we would appreciate it if you could cite our work:

@article{tong2025game,
  title={Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning},
  author={Tong, Jingqi and Tang, Jixin and Li, Hangcheng and Mou, Yurong and Zhang, Ming and Zhao, Jun and Wen, Yanbo and Song, Fan and Zhan, Jiahao and Lu, Yuyang and others},
  journal={arXiv preprint arXiv:2505.13886},
  year={2025}
}