NanoBEIR Multilingual Extended (NanoBEIR Multilingual)
We show this table for reference; we do not rank on it.
A display-only multilingual retrieval benchmark reported by Liquid AI for LFM2.5 retriever models, using NDCG@10 across 11 languages.
Benchmark score on NanoBEIR Multilingual — November 13, 2026
We compile the NanoBEIR Multilingual rows from provider self-reports. LFM2.5-ColBERT-350M leads the table at 60.5%, followed by LFM2.5-Embedding-350M (57.7%). We do not use these results to rank models overall.
LFM2.5-ColBERT-350M
LiquidAI
Reported by LiquidAILFM2.5-Embedding-350M
LiquidAI
Reported by LiquidAI2 modelsMultilingualCurrentDisplay onlyUpdated November 13, 2026
Benchmark score table (2 models)
All 2 results on this page were reported by the labs that built the models.
| Rank | Model / configuration | Score | Who ran it | Parameters (B) | Open / closed |
|---|---|---|---|---|---|
| 1 | LFM2.5-ColBERT-350MLiquidAIReported by LiquidAI | 60.5% | Reported by LiquidAI | Not reported | Open |
| 2 | LFM2.5-Embedding-350MLiquidAIReported by LiquidAI | 57.7% | Reported by LiquidAI | Not reported | Open |
- Lab-reported
- Benchmark-run
- Independent
About NanoBEIR Multilingual
Year
2026
Tasks
Multilingual document retrieval
Format
NDCG@10 average
Difficulty
Multilingual retrieval
Liquid reports average NanoBEIR Multilingual Extended NDCG@10 across Arabic, German, English, Spanish, French, Italian, Japanese, Korean, Norwegian, Portuguese, and Swedish. BenchLM stores the average as a display-only retrieval signal.
Freshness and provenance
Version
NanoBEIR Multilingual 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does NanoBEIR Multilingual measure?
A display-only multilingual retrieval benchmark reported by Liquid AI for LFM2.5 retriever models, using NDCG@10 across 11 languages.
Which model scores highest on NanoBEIR Multilingual?
LFM2.5-ColBERT-350M by LiquidAI currently leads with a score of 60.5% on NanoBEIR Multilingual.
How many models are evaluated on NanoBEIR Multilingual?
2 AI models have published results on NanoBEIR Multilingual in the BenchLM catalog.
Compare top models on NanoBEIR Multilingual
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.