amazon-agi/Amazon-Nova-1.0-Pro-evals

该数据集用于评估Amazon Nova Pro模型，涵盖了多个基准测试，包括MMLU、DROP、GPQA、MATH、GSM8K、IFEval、BBH、HumanEval、FinQA、FLORES、MMMU、ChartQA、DocVQA、TextVQA、VATEX、EgoSchema、VisualWebBench、MM-Mind2Web和GroundUI-1K。每个基准测试的评估方法、提示方式和评分标准都有详细说明。模型响应使用CC-BY-NC许可证发布。This dataset is used to evaluate the performance of the Amazon Nova Pro model on multiple tasks, including MMLU, DROP, GPQA, MATH, GSM8K, IFEval, BBH, HumanEval, FinQA, FLORES, MMMU, ChartQA, DocVQA, TextVQA, VATEX, EgoSchema, VisualWebBench, MM-Mind2Web, and GroundUI-1K. The evaluation methods and prompting techniques used for each task are detailed, and the corresponding performance metrics are reported.