November 2026 · same 50 inputs
Phrasly Ultra vs Solvely
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 | |
|---|---|---|---|---|---|---|
| 1 | Phrasly UltraModel: Ultra · Mode: Max | 87.60 | 91.30 | 94.80% | 70.80 | 0.93 |
| 12 | SolvelyModel: Not exposed · Mode: Humanize; Original result | 25.97 | 25.70 | 6.10% | 72.32 | 1.15 |
Phrasly Ultra: detector breakdown
| Detector | Model | Weight | Passes | Pass rate | Native human-score average |
|---|---|---|---|---|---|
| Pangram 4.1 | 4.1 | 40% | 50/50 | 100.00% | 100.00 |
| GPTZero 5.0b | 5.0b / 2026-11-04-base | 30% | 50/50 | 100.00% | 99.31 |
| Originality.ai 5.0 | model-5.0 | 20% | 37/50 | 74.00% | 75.20 |
| Winston AI 5.2 | 5.2 | 5% | 50/50 | 100.00% | 99.98 |
| ZeroGPT | Vendor-managed; no public version identifier | 5% | 50/50 | 100.00% | 99.10 |
Solvely: detector breakdown
| Detector | Model | Weight | Passes | Pass rate | Native human-score average |
|---|---|---|---|---|---|
| Pangram 4.1 | 4.1 | 40% | 1/50 | 2.00% | 7.09 |
| GPTZero 5.0b | 5.0b / 2026-11-04-base | 30% | 0/50 | 0.00% | 0.00 |
| Originality.ai 5.0 | model-5.0 | 20% | 0/50 | 0.00% | 3.98 |
| Winston AI 5.2 | 5.2 | 5% | 44/50 | 88.00% | 86.95 |
| ZeroGPT | Vendor-managed; no public version identifier | 5% | 9/50 | 18.00% | 38.09 |
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