Update README.md

README.md

@@ -50,7 +50,7 @@ For more information, please read our [blogpost](https://huggingface.co/blog/lig
 
 **DenseOn** is a dense (single-vector) retrieval model built on ModernBERT (149M parameters), trained by [LightOn](https://lighton.ai). It encodes queries and documents independently using cosine similarity with `query:`/`document:` prefixes and CLS pooling.
 
-DenseOn achieves **56.75** average NDCG@10 on BEIR (14 datasets) and **57.71** on decontaminated BEIR (12 datasets), topping all base-size dense models and outperforming models up to 4x larger. 
+DenseOn achieves **56.75** average NDCG@10 on BEIR (15 datasets) and **57.71** on decontaminated BEIR (12 datasets), topping all base-size dense models and outperforming models up to 4x larger. 
 Notably it:
 - **Tops all base-size dense models on BEIR**, ahead of GTE-ModernBERT (55.19) and on par with much larger Snowflake Arctic Embed L v2 (55.22, 568M) and Qwen3-Embedding-0.6B (55.52).
 - **Holds up under decontamination**: when training-overlap samples are stripped from the BEIR corpora, DenseOn improves to **57.71 nDCG@10** on the 12-dataset decontaminated split.
@@ -61,7 +61,7 @@ See our [blog post](https://huggingface.co/blog/lightonai/denseon-lateon) for fu
 
 ## Results
 
-### BEIR (14 datasets, NDCG@10)
+### BEIR (15 datasets, NDCG@10)
 
 | Model | Average | Size | Emb dim | ArguAna | CQADupstackRetrieval | ClimateFEVER | DBPedia | FEVER | FiQA2018 | HotpotQA | MSMARCO | NFCorpus | NQ | QuoraRetrieval | SCIDOCS | SciFact | TRECCOVID | Touche2020 |
 |---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|