research
An AI Tutor Matched Human GRE Learning Gains
A 2,383-person comparison found statistical equivalence for one system—and sharply lower reported cost.
Summary
A 2,383-person comparison found statistical equivalence for one system—and sharply lower reported cost.
StudentBench compared AI tutoring, expert human tutoring and no tutoring on quantitative and verbal GRE questions with 2,383 participants. The authors report that one AI tutor produced learning gains statistically equivalent to expert human tutoring; across five of seven domains, the best-performing AI tutor exceeded the human tutor on average. Their cost analysis put that tutor at $0.0052 per percentage point gained versus $4.81 for the human tutor, a 918-fold difference. The result concerns this platform, task set and study design; it does not establish that AI tutoring is equivalent for every learner, subject or educational goal.
Why it matters
A 2,383-person comparison found statistical equivalence for one system—and sharply lower reported cost.
Limits and context
- The result concerns this platform, task set and study design; it does not establish that AI tutoring is equivalent for every learner, subject or educational goal.
Key claims
A 2,383-person comparison found statistical equivalence for one system—and sharply lower reported cost.
Qualification: The result concerns this platform, task set and study design; it does not establish that AI tutoring is equivalent for every learner, subject or educational goal.
Evidence: source-2026-09-24-002
Sources
- arXiv preprint 2609.28470arXiv · primary research
Corrections
No corrections have been recorded for this story.