To better understand Google’s current capabilities, we compared the queries to organic result titles (as displayed by Google, not <title> tags) using three metrics: (1) exact-match*, (2) partial match with Jaccard similarity, and (3) semantic match with cosine similarity.
1. Exact-match*
Exact-match is pretty self-explanatory, but we chose to be a bit forgiving, normalizing case and punctuation, removing plurals, and allowing any title that contained the full query.
2. Jaccard similarity
To analyze partial matches, we used Jaccard similarity, which measures the number of shared elements (in this case, words) across two sets vs. the unique elements of both sets. Put simply, it’s the proportion of shared words across the two strings to the total, unique words. This is measured on a 0.0-1.0 scale.
3. Cosine similarity
Finally, we calculated vector embeddings and cosine similarity between the two strings. This captures semantic relationships – in a word, “meaning.” Specifically, we used 768-dimensional Nomic embeddings. Cosine similarity also measures similarity on a 0.0-1.0 scale. Let’s look at the stats and some examples.
If you liked How Much Do Keywords Matter in 2026? by Dr. Peter J. Meyers Then you'll love Miami SEO Expert
Now, let's actually take a deep dive into what actually is the flow of AI…
8. Does Google search still exist as we know it in five years?I expect evolution,…
AI tools are everywhere, but most teams still use them as one-off assistants. The bigger opportunity…
So firstly, search volume, now this might be useful for Google. It's not actually that…
So how might you do this? Well, there are a couple of different ways. So…
Third-party sources play a major role in how AI systems understand and describe brands. For example, AirOps…