GenEval-7B

Model Summary

GenEval-7b is the first open-source large multimodal model (LMM) designed as an evaluator across different tasks and modalities for assessing model performance. Built on the foundation of Qwen2-VL-7B-Instruct, it has been finetuned on FRABench dataset.

For further details, please refer to the following resources:

• 📰 Paper: https://arxiv.org/abs/2505.12795
• 🪐 Project Page: https://github.com/ALEX-nlp/FRABench-and-GenEval
• 📦 Datasets: https://huggingface.co/datasets/SPUH/FRABench