Benchmark
TutorBench (Scale AI)
Judge explanations, feedback, and hints tailored to a learner.
Published leaderboard
Explore scores and evaluation settings on the publisher’s leaderboard.
Open leaderboardCoverage
1,490 expert-curated high-school/AP prompts across six STEM subjects, including 828 examples with images and 15,220 rubric criteria.
Methodology
Expert-written, weighted criteria assess adaptive explanations, feedback, and active-learning support. A Claude-4-Sonnet judge grades each criterion; the publisher validates it against human ratings.