Rephrasy vs. CleverHumanizer
Where do the two highest November composite scores differ on matched texts scored by GPTZero?
Across 33 matched rewrites with numeric gptzero scores, Rephrasy scored higher on 16, CleverHumanizer on 7, and 10 tied. Their November composite scores were 55.34 and 54.81 out of 100, respectively.
Results on the same source texts
Each row compares both entries on the same source and includes pairs with two numeric scores. Meaning uses recorded embedding cosine. Detector scores reflect reported human-likelihood.
| Metric | Rephrasy higher | CleverHumanizer higher | Tied | Measured pairs |
|---|---|---|---|---|
| Readability | 14 | 14 | 5 | 33 / 33 |
| Meaning preservation | 22 | 11 | 0 | 33 / 33 |
| GPTZero | 16 | 7 | 10 | 33 / 33 |
| ZeroGPT | 14 | 8 | 11 | 33 / 33 |
| Copyleaks | 2 | 2 | 29 | 33 / 33 |
| Originality.ai | 16 | 14 | 3 | 33 / 33 |
| Pangram | 15 | 14 | 4 | 33 / 33 |
| Grammarly | 3 | 12 | 18 | 33 / 33 |
| QuillBot | 4 | 11 | 18 | 33 / 33 |
Read the matched rewrites
These examples show the largest measured gaps in gptzero, with one example per writing category.
- Academic essay ? S02
Rephrasy rewrite (100.0%) ? CleverHumanizer rewrite (0.0%) - Marketing copy ? S09
Rephrasy rewrite (100.0%) ? CleverHumanizer rewrite (0.0%) - Blog post ? S17
Rephrasy rewrite (99.9%) ? CleverHumanizer rewrite (0.0%)
Scope and source
Both entries use historical published commercial rewrites. The comparison uses the recorded outputs in the November 2026 dataset, version 2026-11-v1. See the methodology for metric definitions and limitations.
Model profiles: Rephrasy and CleverHumanizer.