FinMTEB: Finance Massive Text Embedding Benchmark

Finance Massive Text Embedding Benchmark (FinMTEB), an embedding benchmark consists of 64 financial domain-specific text datasets, across English and Chinese, spanning seven different tasks. All datasets in FinMTEB are finance-domain specific, either previously used in financial NLP research or newly developed by the authors.

• Paper: Do We Need Domain-Specific Embedding Models? An Empirical Investigation
• GitHub: FinMTEB