MT-Bench-101

What is MT-Bench-101?

MT-Bench-101 is specifically designed to evaluate the finegrained abilities of LLMs in multi-turn dialogues. Benchmark Radar tracks MT-Bench-101, cited by 1…

Released

2024-06-25

Evaluates

理解, Understanding, ACL 2024, 大语言模型, LLM, 语言理解, Comprehension, 开源收录, Open-Source, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/MT-Bench-101

MT-Bench-101 paper and code

• Paper https://arxiv.org/pdf/2402.14762
• Code https://github.com/mtbench101/mt-bench-101

Which sources cite MT-Bench-101?

• MT-Bench-101

Related 理解, Understanding, ACL 2024, 大语言模型, LLM, 语言理解, Comprehension, 开源收录, Open-Source, 不支持, Unsupported benchmarks

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