STS Spearman (Semantic Textual Similarity Spearman Rank Correlation) is an important evaluation metric for text embedding / vectorization tasks in natural language processing. STS Spearman measures the rank correlation between embedding vector similarity and human semantic similarity scores, and is a core metric for semantic similarity. It is typically reported as a percentage or a 0–1 score. This metric is widely used in relevant benchmarks and papers and can effectively reflect model performance on this dimension. Higher values are better.