November 2026 · Independent humanizer benchmarks. Explore the evidence
← All humanizers

Humanizer · CMF

Verified by HumanizeBenchWe ran this model ourselves on the benchmark source examples and checked its execution records. Verification confirms the tested model’s provenance; it does not guarantee performance or imply that every detector returned a result.
Open weights33 saved rewrites

Humanizer · CMF has a current composite of 45.23/100 in our shared November evaluation. Readability is 78.0 and rescaled meaning preservation is 65.9. 231 of 231 detector measurements are available.

This entry is the requested cmf artifact from infosave/humanizer-cmf. Related formats are separate roster entries, not necessarily independent underlying models.

Overall score45.23/100
Panel bypass score30.2%
Readability78.0%
Prompts tested33

Detector human-likelihood scores

Mean reported human score on measured outputs. Missing results stay missing. Coverage is shown beside each detector.

GPTZero
1.533/33
ZeroGPT
15.633/33
Copyleaks
42.433/33
Pangram
30.833/33
Grammarly
69.533/33
QuillBot
99.633/33

Performance by category

HumanizeBench v2 per-category values.

Academic essay43.3Application essay35.5Blog post54.6Business email35.3Marketing copy60.6Discussion board60.1News article47.0

Quality and penalties

0.9147Raw meaning cosine
0/33Identical outputs
0/33Refusals
3.0Penalty points
RuleOccurrencesDeduction
Meaning drift2−2
Length inflation1−1

Artifact & evaluation record

Entry
infosave/humanizer-cmf
Source
Recorded GPU generation
Family
jialinyyzz-humanizer
Pinned revision
8a0f116f0d6b0b1868b24ed3535e36f5378e02dd
Scoring
56.5% bypass · 24% meaning · 12% readability · 7.5% consistency, minus fixed penalties.
Measurement notes
NVIDIA quality substitutes; current Polygraph routes; no historical-score fallback.

Inspect the recorded text

The source and rewritten text are available for every sample.

SampleCategorySource modelInput wordsReadabilityDetector scores
S01 Academic essayAcademic essaygpt-5.6-terra31580.07/7
S02 Academic essayAcademic essayclaude-sonnet-529681.37/7
S03 Application essayApplication essaygemini-3.5-flash29178.07/7
S04 Application essayApplication essaygpt-5.6-luna27178.07/7
S05 Blog postBlog postclaude-haiku-4-5-2025100128083.37/7
S06 Blog postBlog postgemini-2.5-flash32976.07/7
S07 Business emailBusiness emailgpt-5.6-terra26282.07/7
S08 Marketing copyMarketing copyclaude-sonnet-529970.07/7
S09 Marketing copyMarketing copygemini-3.5-flash19175.37/7
S10 Discussion boardDiscussion boardgpt-5.6-luna26876.07/7
S11 News articleNews articleclaude-haiku-4-5-2025100130078.07/7
S12 Academic essayAcademic essaygemini-2.5-flash25981.77/7
S13 Academic essayAcademic essaygpt-5.6-terra34981.37/7
S14 Application essayApplication essayclaude-sonnet-531480.07/7
S15 Application essayApplication essaygemini-3.5-flash29278.07/7
S16 Blog postBlog postgpt-5.6-luna31380.07/7
S17 Blog postBlog postclaude-haiku-4-5-2025100128180.07/7
S18 Business emailBusiness emailgemini-2.5-flash18881.77/7
S19 Marketing copyMarketing copygpt-5.6-terra25773.37/7
S20 Marketing copyMarketing copyclaude-sonnet-519178.07/7
S21 Discussion boardDiscussion boardgemini-3.5-flash25173.37/7
S22 News articleNews articlegpt-5.6-luna29882.37/7
S23 Academic essayAcademic essayclaude-haiku-4-5-2025100131276.07/7
S24 Academic essayAcademic essaygemini-2.5-flash25870.07/7
S25 Application essayApplication essaygpt-5.6-terra30076.07/7
S26 Application essayApplication essayclaude-sonnet-532980.07/7
S27 Blog postBlog postgemini-3.5-flash29873.37/7
S28 Blog postBlog postgpt-5.6-luna32376.07/7
S29 Business emailBusiness emailclaude-haiku-4-5-2025100122880.07/7
S30 Marketing copyMarketing copygemini-2.5-flash27771.77/7
S31 Marketing copyMarketing copygpt-5.6-terra19580.07/7
S32 Discussion boardDiscussion boardclaude-sonnet-525280.07/7
S33 News articleNews articlegemini-3.5-flash29582.07/7