SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.15745 · 2024

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

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.15745")
get_code_for_paper("2402.15745")
have("2402.15745")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.15745.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.15745.svg)](https://syntology.ai/paper/2402.15745)

Connect an agent — have() is free.