LetTokenBurn
Sign in
Auto71%Harbor: pendingMultimodalAbstract Reasoning

MM-CondChain

Haozhan Shen1,2, Shilin Yan1†, Hongwei Xue1‡, Shuaiqi Lu1, Xiaojun Tang1, Guannan Zhang1, Tiancheng Zhao3‡, Jianwei Yin2 †Project Leader ‡Corresponding Author 1Accio Team, Alibaba Group 2Zhejiang University 3ZJU-BJ [🏠 Project Page] [📖 Paper] [💻 GitHub] [🏆 Leaderboard] 🔥 News 2026.

PaperDataset

How to run

ltb · mm-condchain
$ npm i -g lettokenburn-cli
$ ltb bench info mm-condchain

External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.

Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs

Scores

0 sourced entries

No sourced scores recorded yet.

Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.

Reproduced by the community

All runs
Loading community runs…

About

MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning

Haozhan Shen1,2, Shilin Yan1†, Hongwei Xue1‡, Shuaiqi Lu1, Xiaojun Tang1, Guannan Zhang1, Tiancheng Zhao3‡, Jianwei Yin2

†Project Leader ‡Corresponding Author

1Accio Team, Alibaba Group 2Zhejiang University 3ZJU-BJ [🏠 Project Page] [📖 Paper] [💻 GitHub] [🏆 Leaderboard]

🔥 News

2026.03.13 🌟 We release MM-CondChain, the first benchmark for visually grounded deep…