Google clearly recognized that “mobile phone” and “cell phone” were a good match. This was about a year before the launch of the Hummingbird update and text embeds in Google, and a decade before publicly available Large Language Models (LLMs).
Along with Google’s capabilities, researchers themselves have evolved and are more likely to use natural language. In 2026, you’re less likely to search for “smartphone” and more likely to search for something like “What’s the best cheap Android phone with a good camera?” You expect Google to correctly interpret that more complex question.
So, how much has Google improved, and can we measure that improvement?
1,000 long-tail queries / 8,703 results
We chose to use a search corpus of 1,000 “long-tail” queries created specifically for prompt tracking and spanning 20 industry categories. Here are some example queries:
- “What metrics should I track for e-commerce success?”
- “Is it better to train in the morning?”
- “Do streaming services track what I watch offline?”
We ran these as Google/US/desktop searches and looked specifically at the first page organic results. This resulted in 8,703 organic results and titles displayed (note that, due to SERP features, the first page may contain fewer than ten organic results).
