HumanEval-V/HumanEval-V-Benchmark
收藏官方服务：
资源简介：
HumanEval-V是一个评估大型多模态模型在编程环境中对复杂图表理解和推理能力的基准数据集，包含253个带有复杂图表的Python编码任务。
HumanEval-V is a benchmark for evaluating the diagram understanding and reasoning capabilities of Large Multimodal Models (LMMs) in programming contexts, containing 253 Python coding tasks with complex diagrams.
提供机构：
HumanEval-V
