MME-CoT Benchmark

What is MME-CoT?

MME-CoT is a specialized benchmark evaluating the CoT reasoning performance of LMMs, spanning six domains: math, science, OCR, logic, space-time, and general…

Released

2025-02-13

Evaluates

强推理, Strong Reasoning, 多模态模型, VLM, 逻辑推理, Reasoning, 跨模态推理, Cross-modal Reasoning, 不支持, Unsupported

Openness

restricted

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

MME-CoT paper, code and dataset

• Paper https://arxiv.org/abs/2502.09621
• Code https://github.com/CaraJ7/MME-CoT
• Dataset https://huggingface.co/datasets/CaraJ/MME-CoT

Which sources cite MME-CoT?

• MME-CoT

Related 强推理, Strong Reasoning, 多模态模型, VLM, 逻辑推理, Reasoning, 跨模态推理, Cross-modal Reasoning, 不支持, Unsupported benchmarks

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