mteb and mleb
MLEB is a specialized legal-domain benchmark that extends the evaluation methodology of MTEB to a specific corpus, making them complementary tools where MLEB users would typically also use MTEB for cross-domain baseline comparisons.
About mteb
embeddings-benchmark/mteb
MTEB: Massive Text Embedding Benchmark
Provides standardized evaluation across 100+ tasks spanning classification, clustering, retrieval, and semantic textual similarity for both text and multimodal embeddings. Integrates with Hugging Face ecosystem (SentenceTransformers, transformers) and offers a unified Python API plus CLI for benchmarking custom or pretrained models against a curated leaderboard. Supports multilingual evaluation with automatic caching, batch processing, and reproducible result tracking across embedding model implementations.
About mleb
isaacus-dev/mleb
The code used to evaluate embedding models on the Massive Legal Embedding Benchmark (MLEB).
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work