Mieb: Massive Image Embedding Benchmark

By Chenghao Xiao, Isaac Chung, Imene Kerboua, J. Stirling, Xin Zhang, Márton Kardos, Roman Solomatin, N. A. Moubayed, Kenneth C. Enevoldsen, Niklas Muennighoff. 2025

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning, Evaluation & Benchmarks

Citations in the corpus

• jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers (2026, unknown): “We describe each evaluation suite by the types of tasks it covers: • Images: TheMassiveImageEmbeddingBenchmark(MIEB)[36] covers classification, clustering, visual semantic textual similarity (STS), retrieval, document retrieval, compositional reasoning, and vision-centric tasks.”