MEDAL Benchmark

What is MEDAL?

MEDAL is a framework for generating and evaluating multilingual open-domain chatbots and their evaluators. This framework supports various language models and…

Released

2025-05-28

Evaluates

其他, Other, 科学智能, AI for Science, 语言理解, Comprehension, 科学推理, Scientific Reasoning, 不支持, Unsupported

Openness

restricted

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

MEDAL paper, code and dataset

• Paper https://arxiv.org/pdf/2505.22777
• Code https://github.com/johndmendonca/medal
• Dataset https://huggingface.co/datasets/Johndfm/medal

Which sources cite MEDAL?

• MEDAL

Related 其他, Other, 科学智能, AI for Science, 语言理解, Comprehension, 科学推理, Scientific Reasoning, 不支持, Unsupported benchmarks

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