Give quick heads up about perf. relative to all-mpnet-base-v2

README.md

@@ -8467,7 +8467,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model trained on the [g
 * **0 Active Parameters:** This model does not use any active parameters, instead consisting exclusively of averaging pre-computed token embeddings.
 * **100x to 400x faster:** On CPU, this model is 100x to 400x faster than common options like [all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). On GPU, it's 10x to 25x faster.
 * **Matryoshka:** This model was trained with a [Matryoshka loss](https://huggingface.co/blog/matryoshka), allowing you to truncate the embeddings for faster retrieval at minimal performance costs.
-* **Evaluations:** See [Evaluations](#evaluation) for details on performance on NanoBEIR, embedding speed, and Matryoshka dimensionality truncation.
+* **Evaluations:** See [Evaluations](#evaluation) for details on performance on NanoBEIR, embedding speed, and Matryoshka dimensionality truncation. In short, this model is **87.4%** as performant as the commonly used [`all-mpnet-base-v2`](https://huggingface.co/sentence-transformers/all-mpnet-base-v2).
 * **Training Script:** See [train.py](train.py) for the training script used to train this model from scratch.
 
 ## Model Details