Get a weekly rundown of the latest AI models and research... subscribe!

Bge Reranker Base


The bge-reranker-base is a text-to-text model that is designed to rerank given pairs of text based on their relevance or correlation. The input schema takes in arrays of text pairs in the format { "pairs_json":"[[\"a\", \"b\"], [\"c\", \"d\"]]" }. In response, the model returns an output schema that includes scores for each text pair, the time taken for the process, and the model name. The score indicates the level of relevance between the paired texts: a higher score signifies greater relevance.

Use cases

The bge-reranker-base artificial intelligence model, indicated by its input-output schema, is capable of ranking or reordering pairs of text-based elements according to a computed score. Accordingly, it allows for an array of advantageous applications. For example, in the field of search engine optimization, this model could be employed to re-rank search results for better relevance. Similarly, in digital advertising, it could rerank advertisements to better match user preferences and behavioral patterns. As it involves text-to-text transformation, it could be utilized in news aggregation platforms to prioritize news articles according to users' interests, or in e-commerce environments and recommendation engines to rerank products based on their likeliness to be purchased. Additonally, this technology could be instrumental in the development of customized educational software that reranks learning materials based on their relevance to the learner. Furthermore, this model could find application in customer service chatbots, where it could rerank FAQs or responses to more accurately assist user inquiries. The practical utility of this AI model, therefore, rests in its ability to enhance the personalization and relevancy of various digital services.



Cost per run
Avg run time

Creator Models

Bge Reranker Large$?60

Similar Models

Try it!

You can use this area to play around with demo applications that incorporate the Bge Reranker Base model. These demos are maintained and hosted externally by third-party creators. If you see an error, message me on Twitter.

Currently, there are no demos available for this model.


Summary of this model and related resources.

Model NameBge Reranker Base
BAAI/bge-reranker-base Model with fp16
Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkNo paper link provided


How popular is this model, by number of runs? How popular is the creator, by the sum of all their runs?

Model Rank
Creator Rank


How much does it cost to run this model? How long, on average, does it take to complete a run?

Cost per Run$-
Prediction Hardware-
Average Completion Time-