Claims

GPT-3.5 performed worst on open one-point exam questions, while GPT-4 improved mainly on multiple-choice items

Claim · All claims
Evidence · 1 study · design r2 · q3
Currency · newest study 2024 · not yet checked against its sources · not reviewed by a person · recheck by 2027: tool and model accuracy changes quickly

Subclaims

Reading the evidence codes

q is the design tier, i the impact, n the sample, and the kind with its r the rigour judged within that kind: what each code means.

This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.

q3 i? Across the three exams GPT-3.5 earned 79%, 68%, and 77% of points on open one-point questions, its weakest category, while GPT-4 improved on multiple-choice questions (92%, 84%, 80% for GPT-4-0314). → Joost C. F. de Winter 2024

Evidence

Joost C. F. de Winter 2024

Joost C. F. de Winter. (2024). Can ChatGPT Pass High School Exams on English Language Comprehension? International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-023-00372-z

q3 · i? · design · r2

Results analysis categorizing the 124 exam items into multiple-choice, open one-point, and multi-part open questions. GPT-3.5 "faced some challenges with the second category" (open one-point questions); GPT-4's gains concentrated in multiple-choice items.

"it became evident that GPT-3.5 faced some challenges with the second category (79%, 68%, and 77% of the points earned). Compared to GPT-3.5, GPT-4 showed improvement in the multiple-choice questions (GPT-4-0314: 92%, 84%, 80%; GPT-4-0613: 92%, 63%, 83%)."

Discussion

Page metadata
Field Value
status review
generated by process:wiki-ingest on 2026-10-28
trust unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.