datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Natural-Language-Processing-with-Disaster-Tweets-0.84033natural-language-to-atlas-search
Natural Language to Atlas Search Benchmark
By Ben Perlmutter, Oct 16, 2025
This README contains a report of benchmarking various large language models (LLMs) on converting natural language (NL) queries into executable Atlas Search code.
Summary of Results
There is a correlation between model performance on generally available benchmarks and this NL to Atlas Search benchmark for frontier LLMs.
There was not a clearly discernible optimal prompting strategy.
Results at a… See the full description on the dataset page: https://huggingface.co/datasets/mongodb-eai/natural-language-to-atlas-search.