SEED-Bench-2-Plus

from https://huggingface.co/datasets/AILab-CVC/SEED-Bench-2-plus

SEED-Bench-2-Plus Card
Benchmark details
Benchmark type: SEED-Bench-2-Plus is a large-scale benchmark to evaluate Multimodal Large Language Models (MLLMs). It consists of 2.3K multiple-choice questions with precise human annotations, spanning three broad categories: Charts, Maps, and Webs, each of which covers a wide spectrum of text-rich scenarios in the real world.

Benchmark date: SEED-Bench-2-Plus was collected in April 2024.

Paper or resources for more information: https://github.com/AILab-CVC/SEED-Bench

License: Attribution-NonCommercial 4.0 International. It should abide by the policy of OpenAI: https://openai.com/policies/terms-of-use.

For the images of SEED-Bench-2-plus, we use data from the internet under CC-BY licenses. Please contact us if you believe any data infringes upon your rights, and we will remove it.

Where to send questions or comments about the benchmark: https://github.com/AILab-CVC/SEED-Bench/issues

Intended use
Primary intended uses: The primary use of SEED-Bench-2-Plus is evaluate Multimodal Large Language Models on text-rich visual understanding.

Primary intended users: The primary intended users of the Benchmark are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.

数据来源：https://huggingface.co/datasets/AILab-CVC/SEED-Bench-2-plus

SEED-Bench-2-Plus 基准测试集卡片

## 基准测试详情
基准类型：SEED-Bench-2-Plus 是一款用于评估多模态大语言模型（Multimodal Large Language Models，MLLMs）的大规模基准测试集。该数据集包含2300道经人工精准标注的多项选择题，涵盖图表（Charts）、地图（Maps）与网页（Webs）三大类别，每一类均覆盖现实世界中丰富的文本密集型视觉场景。

基准采集时间：SEED-Bench-2-Plus 于2024年4月完成数据采集。

更多信息参阅渠道：相关论文或资源链接：https://github.com/AILab-CVC/SEED-Bench

许可协议：采用署名-非商业性使用4.0国际许可协议（Attribution-NonCommercial 4.0 International），同时需遵循OpenAI的相关使用政策：https://openai.com/policies/terms-of-use。

数据集图像说明：SEED-Bench-2-Plus 所使用的图像数据均来自遵循CC-BY许可协议的互联网公开资源。若您认为任何数据侵犯了您的合法权益，请联系我们，我们将及时移除相关内容。

反馈渠道：若您对该基准测试集有任何疑问或建议，请提交至：https://github.com/AILab-CVC/SEED-Bench/issues

## 预期用途
核心用途：SEED-Bench-2-Plus 的核心用途为评估多模态大语言模型的富文本视觉理解能力。

目标用户：该基准测试集的目标用户为计算机视觉、自然语言处理、机器学习及人工智能领域的研究人员与爱好者。