November 2026 · Independent humanizer benchmarks. Explore the evidence

Grammarly detector results

Mean reported human-likelihood scores for each entry on available Grammarly measurements. Higher values mean the detector assigned more human likelihood, not that authorship was established.

759/759Measurements collected
23Entries in the shared panel
33Sources per entry
PolygraphActive collection route
Rank ⓘHumanizerGrammarly ⓘ ↓Bypass ⓘMeaning ⓘReadability ⓘPenalties ⓘCoverageEvidence
133 examples
CleverHumanizercleverhumanizer.ai
96.8577.325.475.8△ −10.0
231/231
233 examples
UndetectedGPTundetectedgpt.ai
93.0661.346.879.8△ −10.0
231/231
333 examples
Qwen 2.5 14B HumanizerVerified 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.arunsingh80475/qwen2.5-14b-humanizer-v4-lora
88.5866.221.178.1△ −15.0
230/231
433 examples
GPTinfgptinf.com
87.4837.741.471.7△ −10.0
231/231
533 examples
HIX Bypasshixbypass.com
86.6145.441.376.9△ −20.0
231/231
633 examples
Rephrasyrephrasy.ai
86.4578.035.773.4△ −12.0
231/231
733 examples
Superhumanizersuperhumanizer.ai
85.8246.543.274.6△ −10.0
231/231
833 examples
SmartHumanizersmarthumanizer.ai
76.4829.050.277.6△ −10.0
231/231
933 examples
Humanizer 12B · OptiQ 4-bitVerified 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.mlx-community/humanizer-12b-OptiQ-4bit
73.4236.360.977.1△ −7.0
231/231
1033 examples
Humanizer · CMFVerified 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.infosave/humanizer-cmf
69.4530.265.978.0△ −3.0
231/231
1133 examples
Humanizer 12B · MLX 8-bit (npario)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.npario/humanizer-12b-mlx-8bit
67.6124.665.978.8△ −5.0
229/231
1233 examples
Humanizer 12B · MLX 8-bit (cowWhySo)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.cowWhySo/humanizer-12b-mlx-8bit
66.5225.366.579.0△ −4.0
230/231
1333 examples
Humanizer 12B · GGUFVerified 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.jialinyyzz/humanizer-GGUF
65.9125.569.680.0△ −2.0
231/231
1433 examples
Humanizer 12BVerified 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.jialinyyzz/humanizer
65.9125.569.680.0△ −2.0
231/231
1533 examples
StealthGPTstealthgpt.ai
65.1238.646.479.9△ −12.0
231/231
1633 examples
Rehumanizerehumanize.io
58.820.860.282.2△ −6.0
231/231
1733 examples
Smaug HumanizerVerified 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.abacusai/Smaug-Humanizer
50.7018.576.581.3△ −1.0
231/231
1833 examples
Humanizer 1B · OptiQ 4-bitVerified 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.mlx-community/humanizer-1B-OptiQ-4bit
28.180.677.171.2△ −17.0
229/231
1933 examples
Undetectable AIundetectable.ai
27.120.555.679.6△ −18.0
231/231
2033 examples
Humanizer 3BVerified 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.mondk/Humanizer-3B-Safetensors
19.671.312.372.1△ −20.0
208/231
2133 examples
GoHumanizeVerified 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.gohumanize/gohumanize-open-humanizer
17.180.292.085.1△ −7.0
231/231
2233 examples
Open Humanizer 4BVerified 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.akhaliq/open-humanizer-4b
11.000.096.685.1△ −10.0
231/231
2333 examples
HumanizerAI · GGUFVerified 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.mradermacher/humanizerAI-GGUF
8.941.075.982.6△ −24.0
199/231

Detector values are mean reported human-likelihood scores; 100 is highest. Scores use available detector measurements. Coverage and methodology are available above.