Gemini-3-flash achieved the highest rubric-item accuracy, ranging from 89% on Course 2 to over 99% on Course 1¶

Claim · All claims
Evidence · 1 study · design r2 · 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 all tested questions and models, Gemini-3-flash had the highest rubric-item accuracy, from 89% (Course 2) to over 99% (Course 1). → Jacob Levine 2026

Evidence¶

Jacob Levine 2026¶

Jacob Levine, Miguel Aenlle, Craig Zilles, Matthew West, and Mariana Silva. (2026). Automated Grading of Handwritten Mathematics Using Vision-Capable LLMs. https://arxiv.org/abs/2605.19043 doi:10.48550/arxiv.2605.19043

q2 · i? · design · r2

Evaluation of three vision-capable LLMs on authentic student submissions from two university STEM courses (Course 1 n=440, Course 2 n=245), comparing AI grading decisions against instructor-assigned ground truth at the rubric-item level. The article reports "the highest rubric-item accuracy, ranging from 89% on Course 2 to over 99% on Course 1" for Gemini-3-flash; no effect size is printed.

"In all cases, Gemini-3-flash had the highest rubric-item accuracy, ranging from 89% on Course 2 to over 99% on Course 1."

Discussion¶

Related Claims¶

• GPT models showed lower accuracy with more rubric-related errors (28% vs. 13% for Gemini 3 Flash) and near parity between false positives and negatives — related
• An LLM-based question-specificity classifier reached .830 knowledge and .829 scaffold accuracy without fine-tuning — related
• One student group compared outputs across three LLMs and judged Gemini more accurate overall, though it still failed fine-grained distinctions — related
• FATE benchmarks rank Gemini 2.5 Flash highest among commercial AI tutors, with actionability weakest for all models — related