ScratchEval: Are GPT-4o Smarter than My Child? Evaluating Large Multimodal Models with Visual Programming Challenges.

Rao Fu Ziyang Luo Hongzhan Lin 0001 Zhen Ye 0006 Jing Ma 0004 ScratchEval: Are GPT-4o Smarter than My Child? Evaluating Large Multimodal Models with Visual Programming Challenges. 2024 abs/2411.18932 CoRR https://doi.org/10.48550/arXiv.2411.18932 db/journals/corr/corr2411.html#abs-2411-18932 streams/journals/corr