WildBench

What is WildBench?

Weintroduce WildBench, an automated evaluation framework designed to bench-mark large language models (LLMs) using challenging, real-world user queries, which…

Released

2024-06-07

Evaluates

理解, Understanding, 大语言模型, LLM, 语言生成, Generation, 指令遵循, Instruction Following, 不支持, Unsupported

Openness

restricted

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

WildBench paper, code and dataset

• Paper https://arxiv.org/abs/2406.04770
• Code https://github.com/allenai/WildBench
• Dataset https://huggingface.co/datasets/allenai/WildChat

Which sources cite WildBench?

• WildBench

Related 理解, Understanding, 大语言模型, LLM, 语言生成, Generation, 指令遵循, Instruction Following, 不支持, Unsupported benchmarks

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