According to the following preliminary comparison by Gensim:
fastText embeddings are significantly better than word2vec at encoding syntactic information. This is expected, since most syntactic analogies are morphology based, and the char n-gram approach of fastText takes such information into account. The original word2vec model seems to perform better on semantic tasks, since words in semantic analogies are unrelated to their char n-grams, and the added information from irrelevant char n-grams worsens the embeddings.
The source for this is: word2vec fasttext comparison notebook (https://github.com/RaRe-Technologies/gensim/blob/37e49971efa74310b300468a5b3cf531319c6536/docs/notebooks/Word2Vec_FastText_Comparison.ipynb ...