Command Palette
Search for a command to run...
MTEB
Date
MTEB (Massive Text Embedding Benchmark) is a large-scale text embedding evaluation benchmark covering a variety of tasks such as retrieval, classification, clustering, reranking, and semantic similarity. The MTEB Score generally refers to the model's average performance across the benchmark's tasks and is currently the most commonly used benchmark-specific metric for evaluating general-purpose text embedding models. It is typically reported as a percentage or a score from 0 to 1, with higher values being better. Different papers may report average scores over different task subsets, so the task coverage should be checked for consistency when making comparisons.
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.