ConvBench

What is ConvBench?

ConvBench is a novel multi-turn conversation evaluation benchmark tailored for Large Vision-Language Models (LVLMs). It comprises 577 meticulously curated…

Released

2024-03-29

Evaluates

推理, Reasoning, NeurIPS 2024, 大语言模型, LLM, 逻辑推理, 不支持, Unsupported

Openness

open

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

ConvBench paper, code and dataset

• Paper https://arxiv.org/abs/2403.20194
• Code https://github.com/shirlyliu64/ConvBench
• Dataset https://huggingface.co/datasets/liushuo12345/ConvBench

Which sources cite ConvBench?

• ConvBench

Related 推理, Reasoning, NeurIPS 2024, 大语言模型, LLM, 逻辑推理, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• ActiveFly-Bench
• Ada-LEval
• AdvancedMathBench
• AECBench