Original aggregate data
AI-Assisted Manuscript Review Quality Snapshot 2026
Published: 18 July 2026 · Version 2026-07-18-v1
Executive summary
Across 68 completed quality-judge runs, the average generated-review quality score was 7.21/10. This measures the quality of the generated review, not manuscript quality or acceptance probability.
Sample size
n=68
Average score
7.21/10
Strong band
8
Period
2026
Score distribution
| Band | n |
|---|---|
| 0–6 | 10 |
| >6–8 | 50 |
| >8–10 | 8 |
Quality dimensions
citationAccuracy
3.88/10
n=68
specificity
4.66/10
n=68
comprehensiveness
3.39/10
n=68
actionability
4.43/10
n=68
tone
5/10
n=68
Methodology and privacy
Aggregate quality-judge scores for completed AI-assisted manuscript reviews. No manuscript text, title, author, institution, DOI, email, file name, or user identifier is exported.
Groups smaller than n=20 are suppressed. The snapshot is versioned and does not update live.
Limitations
- This is operational quality-assurance data, not peer-reviewed research.
- Scores evaluate generated review quality, not manuscript acceptance probability.
- The submitted-manuscript population is self-selected.
Suggested citation
Börcek AO. AI-Assisted Manuscript Review Quality Snapshot 2026. Review My Manuscript; 2026. Version 2026-07-18-v1.