Update README.md

README.md

@@ -50,7 +50,12 @@ BTW embedder is only a part of a good RAG<br>
 <li>bge-m3 (up to 8192t context length)</li>
 </ul>
 Working well, all other its up to you! Some models are very similar! (jina and qwen based not yet supported by LM-Studio)<br>
-With the same setting, these embedders found same 6-7 snippets out of 10 from a book. This means that only 3-4 snippets were different, but I didn't test it extensively.
+With the same setting, these embedders found same 6-7 snippets out of 10 from a book. This means that only 3-4 snippets were different, but I didn't test it extensively.<br>
+Further tests have shown that the following models are suitable for complex tasks (German-text, but should be similar in English). Jina-DE, nomic was not that good.
+<ul style="line-height: 1.05;">
+<li>GTE large</li> 
+<li>cross-en-de-es-roberta</li>
+  
 <br>
 <br>
 ...
@@ -212,11 +217,12 @@ docfetcher - https://docfetcher.sourceforge.io/en/index.html (yes old but very u
 <li>Snowflake/snowflake-arctic-embed-l-v2.0 (English, multi)</li>
 <li>intfloat/multilingual-e5-large-instruct (100 languages)</li>
 <li>T-Systems-onsite/german-roberta-sentence-transformer-v2</li>
+<li>T-Systems-onsite/cross-en-de-es-roberta-sentence-transformer (English, German, Spanish)</li>
 <li>mixedbread-ai/mxbai-embed-2d-large-v1</li>
 <li>jinaai/jina-embeddings-v2-base-en</li>
 <li>Qwen/Qwen3-Embedding-0.6B</li>
 <li>HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5</li>
-  
+<li>thenlper/gte-large</li> 
 </ul>