Benchmark
MIEB Benchmark
What is MIEB?
Massive Image Embedding Benchmark (MIEB) is to evaluate the performance of image and image-text embedding models across the broadest spectrum to date.
- Released
- 2025-04-14
- Modality
- multimodal
- Evaluates
- 多模态, Multimodal, 多模态模型, VLM, 检索能力, Retrieval, 图像理解, Image Understanding, 不支持, Unsupported
- Openness
- unknown
- Importer
- OpenCompass Hub
- Reported scores
- 0
Source provenance
- Original evidence https://hub.opencompass.org.cn/dataset-detail/MIEB
MIEB paper and code
- Paper https://arxiv.org/abs/2210.07316
- Paper https://arxiv.org/abs/2309.07597
- Paper https://arxiv.org/abs/2310.19923
- Paper https://arxiv.org/abs/2401.02709
- Paper https://arxiv.org/abs/2403.15246
- Paper https://arxiv.org/abs/2404.12096
- Paper https://arxiv.org/abs/2406.02396
- Paper https://arxiv.org/abs/2412.00532
- Paper https://arxiv.org/abs/2502.13595
- Paper https://arxiv.org/abs/2504.10471
- Code https://github.com/embeddings-benchmark/mteb
No reported scores are on record for this benchmark yet.