Liquid AI
MKQA-11 multilingual retrieval
A display-only multilingual QA retrieval benchmark reported by Liquid AI for LFM2.5 retriever models, using Recall@20 across 11 languages.
ModelsModels with a result.1
Top resultBest result on this test.N/A
Top-3 spreadPoints from first to third.N/A
YearYear of release.2026
Results
1 result#ModelResultThe score from the source.