Ai2 reports that Claude Sonnet 5.5 (low effort) was best at asking students to work through more of a math problem themselves when teachers recommended it. With explicit tutoring instructions, GPT-6 Sol (no reasoning) outscored Claude Opus 4.8 overall.
Part of a thread · earlier post
When asked to “tutor well,” Claude Sonnet 5.5 (low effort) was best at asking students to work through more of a math problem themselves when teachers recommended it.
With explicit tutoring instructions, GPT-6 Sol (no reasoning) outscored Claude Opus 4.8 overall.
Source: Ai2 · x.comPublished · added here
