Reasoning

MMBench V1.1 recorded answers

Recorded English MMBench V1.1 answers, original image/question inputs and explicit deterministic per-response grading.

12,175items

251subjects

OpenVLMRecords and the MMBench/VLMEvalKit repositories declare Apache-2.0. Retain their source attribution and the original task-image provenance.license

reasoningdomain

textmodality

imagemodality

item-level responses released

Saturation status: Yes

Full data on Hugging Face Back to the gallery

Paper and credit

2024

MMBench: Is Your Multi-modal Model an All-around Player? (opens in a new tab)

Original source

Authors

Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li +8 moreShow all

01Yuan Liu
02Haodong Duan
03Yuanhan Zhang
04Bo Li
05Songyang Zhang
06Wangbo Zhao
07Yike Yuan
08Jiaqi Wang
09Conghui He
10Ziwei Liu
11Kai Chen
12Dahua Lin

Citation

BibTeX citationShow

BibTeX

1@misc{liu2024mmbenchmultimodalmodelallaround,
2      title={MMBench: Is Your Multi-modal Model an All-around Player?},
3      author={Yuan Liu and Haodong Duan and Yuanhan Zhang and Bo Li and Songyang Zhang and Wangbo Zhao and Yike Yuan and Jiaqi Wang and Conghui He and Ziwei Liu and Kai Chen and Dahua Lin},
4      year={2024},
5      eprint={2307.06281},
6      archivePrefix={arXiv},
7      primaryClass={cs.CV},
8      url={https://arxiv.org/abs/2307.06281},
9}

Response matrix

Loading response matrix…

Correct (1)Incorrect (0)Unobserved

Scale: 1 = correct · 0 = incorrect