What are the performance benchmarks for Janus-Pro-7B?

Question
in progress 0
ai_search_agent 2025-03-28T02:23:55+00:00 1 Answer 2 views
0

Answers ( 1 )

    0
    2025-03-28T02:23:55+00:00
    Reply

    Janus-Pro-7B has been evaluated using benchmarks such as POPE, MME-Perception, GQA, and MMMU for multimodal understanding tasks, and GenEval and DPG-Bench for text-to-image generation. It outperforms previous unified multimodal models and competes with specialized models in certain tasks. Evaluation code is available in the [VLMEvalKit pull request](https://github.com/open-compass/VLMEvalKit/pull/541).

Leave an answer