November 2026 · same 50 inputs
WriteHuman vs Rephrasy
November 2026 · methodology v2 · provisional automated quality. 15 humanizers, 50 identical inputs each, five detectors and eight quality metrics. Read the scoring rules and post-run changes.
| Overall rank | Humanizer | Overall average | Overall median | Weighted bypass | Quality | |
|---|---|---|---|---|---|---|
| 3 | WriteHumanModel: Enhanced | 56.21 | 68.15 | 60.00% | 47.38 | 1.04 |
| 4 | RephrasyModel: Superstealth | 37.49 | 26.95 | 27.60% | 60.56 | 1.11 |
WriteHuman: detector breakdown
| Detector | Model | Weight | Passes | Pass rate | Native human-score average |
|---|---|---|---|---|---|
| Pangram 4.1 | 4.1 | 40% | 33/50 | 66.00% | 76.92 |
| GPTZero 5.0b | 5.0b / 2026-11-04-base | 30% | 40/50 | 80.00% | 75.52 |
| Originality.ai 5.0 | model-5.0 | 20% | 0/50 | 0.00% | 13.42 |
| Winston AI 5.2 | 5.2 | 5% | 50/50 | 100.00% | 99.93 |
| ZeroGPT | Vendor-managed; no public version identifier | 5% | 46/50 | 92.00% | 93.78 |
Rephrasy: detector breakdown
| Detector | Model | Weight | Passes | Pass rate | Native human-score average |
|---|---|---|---|---|---|
| Pangram 4.1 | 4.1 | 40% | 10/50 | 20.00% | 47.93 |
| GPTZero 5.0b | 5.0b / 2026-11-04-base | 30% | 22/50 | 44.00% | 38.24 |
| Originality.ai 5.0 | model-5.0 | 20% | 0/50 | 0.00% | 24.94 |
| Winston AI 5.2 | 5.2 | 5% | 44/50 | 88.00% | 90.67 |
| ZeroGPT | Vendor-managed; no public version identifier | 5% | 20/50 | 40.00% | 66.05 |
Overall weights humanization 70% and quality 30%. Rankings use automated quality scores with unresolved evidence flags; neither a detector pass nor a small score gap proves a universal advantage.
Per-output scores CSV · Frozen inputs and prompts CSV · Scoring manifest · Verification bundle · GitHub report · Earlier editions