Mind2Web Benchmark

What is Mind2Web?

MIND2WEB is the first dataset for developing and evaluating generalist agents for the web that can follow language instructions to complete complex tasks on…

Released

2023-12-09

Evaluates

其他, Other, 智能体, Agent, 任务执行, Task Execution, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/Mind2Web

Mind2Web paper, code and dataset

• Paper https://arxiv.org/pdf/2306.06070
• Code https://github.com/OSU-NLP-Group/Mind2Web
• Dataset https://huggingface.co/datasets/osunlp/Mind2Web

Which sources cite Mind2Web?

• Mind2Web

Related 其他, Other, 智能体, Agent, 任务执行, Task Execution, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• Ada-LEval
• AECBench
• AFQMC
• AgentBoard