Research report
Does Turnitin Detect Essays Generated by GPT-5.6-Sol?
A Large-Scale Benchmark Experiment on GPT-5.6-Sol Essay Detection
Cite this research
In a benchmark of 180 GPT-5.6-Sol essays across 30 majors, Turnitin achieved 97.88% word-level accuracy, correctly flagging 153,620 of 156,955 words as AI-generated.
According to Turnitin0 Research, the tool correctly identified 97.88% of words in 180 GPT-5.6-Sol essays as AI-generated, with accuracy ranging from 88.81% in Physics to 99.67% in Business Administration.
- 180 articles tested
- Checker: Turnitin
- LLM: gpt-5.6-sol
- 1 linked dataset
- Detection screenshots available
- Published July 29, 2026
Peng, J. (2026). Does Turnitin Detect Essays Generated by GPT-5.6-Sol?. Turnitin0 Research. https://www.turnitin0.com/research/reports/does-turnitin-detect-essays-generated-by-gpt-5-6-sol
Licensed under CC0 1.0 Universal. You may copy, modify, distribute, and cite this research—including text, figures, tables, and datasets—without asking permission.
Overview
This benchmark evaluates Turnitin's ability to detect AI-generated essays produced by the GPT-5.6-Sol model. The dataset comprises 180 essays across 30 majors, totaling 156,955 words. We report word-level accuracy, comparing Turnitin's flagged words against the total word count.
- Overall word accuracy: 97.88% — Turnitin correctly flagged 153,620 out of 156,955 words as AI-generated.
- Domain performance:
- Education: 99.50% accuracy (5,003 correct / 5,028 words)
- Business: 99.32% accuracy (26,029 / 26,206)
- Humanities: 99.00% accuracy (41,865 / 42,288)
- Psychology: 96.48% accuracy (5,294 / 5,487)
- STEM: 96.77% accuracy (75,429 / 77,946)
- Major-level highlights:
- Highest accuracy: Business Administration (99.67%), Nursing (99.55%), Economics (99.54%)
- Lowest accuracy: Physics (88.81%), Mathematics (89.57%), Computer Science (94.95%)
- Level breakdown:
- Graduate: 98.74% accuracy (77,902 / 78,899)
- Undergraduate: 97.00% accuracy (75,718 / 78,056)
- Word count buckets:
- 400-word essays: 98.31% accuracy (23,849 / 24,259)
- 800-word essays: 98.42% accuracy (49,680 / 50,478)
- 1,200-word essays: 97.41% accuracy (80,091 / 82,218)
- Dataset: 180 GPT-5.6-Sol essays across 30 majors, 5 domains (Business, Education, Humanities, Psychology, STEM).
- Word counts: 400, 800, and 1,200 words per essay; total 156,955 words.
- Levels: 90 graduate and 90 undergraduate essays.
- No humanizer applied — essays are raw AI output.
- Evaluation metric: Word-level accuracy = (correctly flagged words / total words) × 100.
- Reference/bibliography sections excluded from word counts.
- Scoring unit: accuracy is measured in words. First identify correct paragraphs under the expectation below, then sum the words in those paragraphs for the correct-word count; total words are summed over all counted paragraphs.
- Correct paragraph: a counted paragraph that was flagged as AI. Correct words are the words in those paragraphs.
- References excluded: from a References/Bibliography-style heading onward, those paragraphs are left out of word counts.
- Domain imbalance: STEM has 90 essays, while Education and Psychology have only 6 each.
- Total articles: 180
- Correct words: 153,620
- Total words: 156,955
- Word accuracy: 97.88%
- Business: 99.32% (26,029 / 26,206)
- Education: 99.50% (5,003 / 5,028)
- Humanities: 99.00% (41,865 / 42,288)
- Psychology: 96.48% (5,294 / 5,487)
- STEM: 96.77% (75,429 / 77,946)
- Top 3 majors: Business Administration (99.67%), Nursing (99.55%), Economics (99.54%)
- Bottom 3 majors: Physics (88.81%), Mathematics (89.57%), Computer Science (94.95%)
- All 30 majors show accuracy above 88%.
- Graduate: 98.74% (77,902 / 78,899)
- Undergraduate: 97.00% (75,718 / 78,056)
- 400 words: 98.31% (23,849 / 24,259)
- 800 words: 98.42% (49,680 / 50,478)
- 1,200 words: 97.41% (80,091 / 82,218)
Detection report screenshots
Turnitin marks suspected AIGC text in cyan.