Multilingual benchmark
NanoBEIR Multilingual leaderboard
NanoBEIR Multilingual Extended. Every model the catalog carries a published NanoBEIR Multilingual value for, ranked by that value.
A display-only multilingual retrieval benchmark reported by Liquid AI for LFM2.5 retriever models, using NDCG@10 across 11 languages.
NanoBEIR Multilingual ranking
2 models with a published NanoBEIR Multilingual value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | NDCG@10 average |
|---|---|---|---|
| 1 |  LFM2.5-ColBERT-350M | LiquidAI | 60.5 |
| 2 | LFM2.5-Embedding-350M | LiquidAI | 57.7 |
Evidence key: Observed
Rows are ordered by the value LFM2.5 Retrievers: Bi-directional LFMs for Fast Multilingual Search published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.