Hey Pablo, right now, most of our models are purposely trained to use mostly English (see here in our embeddings limitations: https://beta.openai.com/docs/guides/embeddings/english-only). Hopefully this will expand over time but for now, any good Spanish results are a bonus.
See the GPT-3 paper for more details (GPT-3 powers ChatGPT):
For GPT-2 a filter was used on a multilingual collection of documents to produce an English only dataset due to capacity concerns. Even with this filtering GPT-2 showed some evidence of multilingual capability and performed non-trivially when translating between French and English despite only training on 10 megabytes of remaining French text. Since we increase the capacity by over two orders of magnitude from GPT-2 to GPT-3, we also expand the scope of the training
dataset to include more representation of other languages, though this remains an area for further improvement. As discussed in 2.2 the majority of our data is derived from raw Common Crawl with only quality-based filtering. Although GPT-3’s training data is still primarily English (93% by word count), it also includes 7% of text in other languages. These languages are documented in the supplemental material.