A prompt-engineered Custom GPT scored 82-86% on first-year statics exams, matching or beating average students, while image-based prompts and base models lagged.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Assessment of ChatGPT for Engineering Statics Analysis
A prompt-engineered Custom GPT scored 82-86% on first-year statics exams, matching or beating average students, while image-based prompts and base models lagged.