Skip to content

StudentBench

Product or Programme · All products and programmes
Evidence · 2 claims (2 for) · 1 study (1 causal), q2 · 0 of 1 report an effect size · 2 claims rest on one study

Description

StudentBench is a public platform and associated open dataset developed by Curtis Northcutt et al. for large-scale evaluation of AI tutors using randomized studies with real students, expert ratings, and post-test learning gains.

Components

  • StudentBench platform and open dataset for evaluating AI tutoring by real student learning gains: StudentBench is "a suite of AI teaching evaluations and a public platform that enables large-scale data collection with over 175,000 student–AI messages". It runs randomized pre/post learning-gain studies comparing AI tutors, human tutors, and control, and produces five leaderboards covering lesson planning, practice-problem creation, conversational pedagogy, cost, and engagement. Unlike prior LLM tutoring benchmarks judged by LLM evaluators or simulated students, it measures real students' unaided post-test gains after live tutoring. The de-identified data and reproduction code are open-sourced. (Curtis Northcutt et al. (2026))

Claims

-

Key Sources

  • Curtis Northcutt, Inaara Hasmani, Kevin Feng, Trevor Khangi, Andreas Plesner, Jonas Mueller. (2026). StudentBench: AI and human tutoring yield equivalent GRE learning gains. https://arxiv.org/abs/2609.28470
Page metadata
Field Value
type product
id studentbench
title StudentBench
description StudentBench is a public platform and associated open dataset developed by Curtis Northcutt et al.
status review
product_kind software
generated by process:settle-candidates on 2026-10-11
trust unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.