GAOKAO-MM: A Chinese Human-Level Benchmark for Multimodal Models Evaluation

The Large Vision-Language Models (LVLMs) have demonstrated great abilities in image perception and language understanding. However, existing multimodal benchmarks focus on primary perception abilities and commonsense knowledge which are insufficient to reflect the comprehensive capabilities of LVLMs. We propose GAOKAO-MM, a multimodal benchmark based on the Chinese College Entrance Examination (GAOKAO), comprising of 8 subjects and 12 types of images, such as diagrams, function graphs, maps and photos. GAOKAO-MM derives from native Chinese context and sets human-level requirements for the model's abilities, including perception, understanding, knowledge and reasoning. We evaluate 10 LVLMs and find that the accuracies of all of them are lower than 50%, with GPT-4-Vison (48.1%), Qwen-VL-Plus (41.2%) and Gemini-Pro-Vision (35.1%) ranking in the top three positions. The results of our multi-dimension analysis indicate that LVLMs have moderate distance towards Artificial General Intelligence (AGI) and provide insights facilitating the development of multilingual LVLMs.

Evaluating the Performance of Large Language Models on GAOKAO Benchmark

Large language models have demonstrated remarkable performance across various natural language processing tasks; however, their efficacy in more challenging and domain-specific tasks remains less explored. This paper introduces the GAOKAO-Benchmark (GAOKAO-Bench), an intuitive benchmark that employs questions from the Chinese Gaokao examination as test samples for evaluating large language models.In order to align the evaluation results with humans as much as possible, we designed a method based on zero-shot prompts to analyze the accuracy and scoring rate of the model by dividing the questions into subjective and objective types. We evaluated the ChatGPT model on GAOKAO-Benchmark performance.Our findings reveal that the ChatGPT model excels in tackling objective questions, while also shedding light on its shortcomings and areas for improvement. To further scrutinize the model's responses, we incorporate human evaluations.In conclusion, this research contributes a robust evaluation benchmark for future large-scale language models and offers valuable insights into the limitations of such models.