UniFinEval

UniFinEval UniFinEval is a unified multimodal benchmark for high-information-density financial environments, covering text, images, and videos. It evaluates multimodal large language models (MLLMs) on fine-grained financial reasoning tasks grounded in real-world financial systems. Paper: UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and VideosCode: github.com/aifinlab/UniFinEval Dataset Summary Item Value… See the full description on the dataset page:

Source: Hugging Face Hub (AIFin-Lab/UniFinEval). Metadata imported from the dataset’s Hub tags.