Solving-oriented and pedagogy-oriented composite scores on the public MathTutorBench leaderboard are only moderately correlated (Pearson 0.421, Spearman 0.690)¶

Claim · All claims
Evidence · 1 study · associational r? · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q2 i? Across eight publicly reported models, the Pearson correlation between solving and pedagogy composites is 0.421 and the Spearman correlation is 0.690, reported descriptively rather than as hypothesis tests. → Junyi Yao 2026

Evidence¶

Junyi Yao 2026¶

Junyi Yao, Zihao Zheng, and Baichuan Li. (2026). Beyond Helpfulness: A Teaching-over-Solving Diagnostic for Measuring Educational Impact in LLM Tutors. arXiv preprint. https://arxiv.org/abs/2606.16206 doi:10.48550/arxiv.2606.16206

q2 · i? · associational · r?

Reaggregation of public MathTutorBench leaderboard scores for eight tutoring models into solving-oriented and pedagogy-oriented composites; the article states the values are used "descriptively rather than as hypothesis tests" given the small number of models.

"Across the eight public MathTutorBench leaderboard models, the Pearson correlation between solving and pedagogy composites is 0.421, while the rank-based Spearman correlation is 0.690."

Discussion¶

Related Claims¶

• The solving–pedagogy correlation is statistically fragile: leave-one-out Pearson correlations range from 0.251 to 0.887, rising to 0.887 when Qwen2.5-Math-7B-Instruct is removed — related
• Human raters' preferences align with the LLM judge on TutorBench (Pearson r = 0.82 across metric-level win rates) — related