← Back to the wire

Introducing the Ettin Reranker Family

AchievementModelMay 19, 2026

Tom Aarsen released six new CrossEncoder reranker models built on Ettin ModernBERT encoders, achieving state-of-the-art performance at their respective sizes. The models were trained using a distillation recipe based on Mixedbread AI's mxbai-rerank-large-v2 scores over the cross-encoder/ettin-reranker-v1-data dataset, which combines subsets from Lighton's embedding datasets. Evaluated on MTEB(eng, v2) Retrieval paired with Google's google/embeddinggemma-300m, the rerankers are available on Hugging Face with full training data and recipes.

Receipt № 4931 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

01highPRIMARY
Mixedbread AICompanyEttin ModernBERTModelgoogle/embeddinggemma-300mModelTom AarsenPersonLightonCompanymxbai-rerank-large-v2Modelcross-encoder/ettin-reranker-v1-dataModelGoogleCompanyHugging FaceCompany
Canonical: https://huggingface.co/blog/ettin-reranker