retomaton VS beir

The source code for these experiments is open-source and utilizes beir-qdrant, an integration of Qdrant with the BeIR library. While this package is not officially maintained by the Qdrant team, it may prove useful for those interested in experimenting with various Qdrant configurations to see how they impact retrieval quality. All experiments were conducted using Qdrant in exact search mode, ensuring the results are not influenced by approximate search.

The BEIR project might be what you're looking for: https://github.com/beir-cellar/beir/wiki/Leaderboard

Custom datasets can also be evaluated using this method as specified in this link. This article and the associated benchmarks script can be reused to evaluate what method works best on your data.

> Meilisearch focuses on simplicity, relevancy, and performance.

> excellent relevance out of the box

> if ease of use, performance, and relevancy are important to you, Meilisearch was made for you

Is there a benchmark that shows Meilisearch outperforming Elasticsearch in terms of relevance score? I couldn't find Meilisearch listed on https://github.com/beir-cellar/beir.

There are actually benchmarks that allow measuring search relevancy objectively, e.g. BEIR[1]. Manticore Search team did an effort to make a PR to include it to the list. The results are here [2]. Unfortunately the BEIR team seems to be too busy to review a whole pile of PRs including about Vespa. Nevertheless it would be nice to have both Meilisearch and Typesense there too since it's interesting what performance those non-tf-idf based search engines would show compared to BM25-based and vector search engines.

[1] https://github.com/beir-cellar/beir

True! Here's a pull request to BEIR to compare Manticore with Elasticsearch in terms of relevance https://github.com/beir-cellar/beir/pull/92. Spoiler: in this test Manticore provides better relevance than Elasticsearch in average. Of course you can tune both further and Elasticsearch now has KNN which when combined with BM25 can give even better relevance. In general I would say for most users the results quality in terms of full-text relevance is about the same in Elasticseach and Manticore.

But there's for example BEIR that compared BM25 vs state of the art ML language models and it turned out BM25 is in average better than all of them unless you rerank top 100 results from Elasticsearch using the language models. With Manticore you can get even better relevance than with Elasticsearch. We made a pull-request to BEIR to demonstrate that https://docs.google.com/spreadsheets/d/1_ZyYkPJ_K0st9FJBrjbZqX14nmCCPVlE_y3a_y5KkYI/edit#gid=0