SuperGPQA is a benchmark dataset for evaluating the performance of advanced question answering systems. It was developed by the Multimodal Art Projection team in 2025. The related paper results are "SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines". This dataset focuses on the field of natural language processing and machine learning evaluation, and aims to test the model's reasoning ability and knowledge level through complex interdisciplinary problems.

The dataset covers 285 graduate-level subject areas with diverse question types, including biology, physics, chemistry and other scientific fields.