GEO-bench

GEO-bench is the benchmark the Princeton and IIT Delhi GEO paper built to test and compare optimization tactics, consisting of 10,000 queries spanning 8 different domains, used as the standardized dataset every tactic in the study, from statistics addition to keyword stuffing, was measured against.

Why it matters

GEO-bench is what gives the paper's percentage improvements their credibility: every tactic was tested against the same 10,000-query, 8-domain benchmark rather than a cherry-picked or narrower dataset, which is what makes the comparisons between tactics meaningful rather than anecdotal.

Related terms

• Position-Adjusted Word Count (PAWC)

  Position-Adjusted Word Count, or PAWC, is the metric the Princeton and IIT Delhi GEO paper (arXiv 2311.09735) uses to score a source's visibility within an AI-generated answer, weighting how many of that source's words appear in the response and where they fall, with earlier-appearing content weighted more heavily.

• Statistics Addition

  Statistics addition is the Princeton GEO paper's tested tactic of replacing vague claims with specific numbers, sources, and dates, which the study measured as its single strongest-performing tactic, producing up to roughly a 41 percent improvement on the paper's PAWC visibility metric.

• Equalizer Effect

  The equalizer effect is the Princeton GEO paper's finding that citations let lower-ranked sources, such as a page sitting at position five in traditional search, achieve outsized visibility gains within an AI-generated answer relative to their organic rank, a genuinely counter-intuitive result given how strongly position predicts visibility in traditional search.