November 2026 · Independent humanizer benchmarks. Explore the evidence

Originality.ai detector results

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

756/759Measurements collected
23Entries in the shared panel
33Sources per entry
PolygraphActive collection route
Rank ⓘHumanizerOriginality.ai ⓘ ↓Bypass ⓘMeaning ⓘReadability ⓘPenalties ⓘCoverageEvidence
133 examples
Rephrasyrephrasy.ai
34.8878.035.773.4△ −12.0
231/231
233 examples
CleverHumanizercleverhumanizer.ai
33.4277.325.475.8△ −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
23.0666.221.178.1△ −15.0
230/231
433 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
11.2436.360.977.1△ −7.0
231/231
533 examples
Superhumanizersuperhumanizer.ai
10.4846.543.274.6△ −10.0
231/231
633 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
9.7930.265.978.0△ −3.0
231/231
733 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
9.6725.569.680.0△ −2.0
231/231
833 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
9.6725.569.680.0△ −2.0
231/231
933 examples
StealthGPTstealthgpt.ai
9.3338.646.479.9△ −12.0
231/231
1033 examples
UndetectedGPTundetectedgpt.ai
8.2161.346.879.8△ −10.0
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
6.8224.665.978.8△ −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
6.6425.366.579.0△ −4.0
230/231
1333 examples
GPTinfgptinf.com
6.4237.741.471.7△ −10.0
231/231
1433 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
5.5218.576.581.3△ −1.0
231/231
1533 examples
HIX Bypasshixbypass.com
4.6145.441.376.9△ −20.0
231/231
1633 examples
SmartHumanizersmarthumanizer.ai
4.3629.050.277.6△ −10.0
231/231
1733 examples
Rehumanizerehumanize.io
4.300.860.282.2△ −6.0
231/231
1833 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
3.741.075.982.6△ −24.0
199/231
1933 examples
Undetectable AIundetectable.ai
3.360.555.679.6△ −18.0
231/231
2033 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
3.330.292.085.1△ −7.0
231/231
2133 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
3.300.677.171.2△ −17.0
229/231
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
3.060.096.685.1△ −10.0
231/231
2333 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
0.031.312.372.1△ −20.0
208/231

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