November 2026 · Independent humanizer benchmarks. Explore the evidence

NOVEMBER 2026 / SHARED EVALUATION

AI humanizer leaderboard

Thirteen open-weight entries and ten published services. Every entry uses the same 33 source texts and the same scoring framework.

Measurement coverage5,252 / 5,313
Current scores

Scores are provisional while 58 detector checks remain unresolved. Rankings update as measurements arrive. Provider exclusions: 3. Excluded checks have no numeric score. Readability and meaning: 759/759 recorded.

Inspect coverage and recorded evidence →
Rank ⓘHumanizerOverall ⓘ ↓Bypass ⓘMeaning ⓘReadability ⓘPenalties ⓘCoverageEvidence
133 examples
Rephrasyrephrasy.ai
55.3478.035.773.4△ −12.0
231/231
233 examples
CleverHumanizercleverhumanizer.ai
54.8177.325.475.8△ −10.0
231/231
333 examples
UndetectedGPTundetectedgpt.ai
50.6561.346.879.8△ −10.0
231/231
433 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
45.2330.265.978.0△ −3.0
231/231
533 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
45.1925.569.680.0△ −2.0
231/231
633 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
45.1925.569.680.0△ −2.0
231/231
733 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
44.1818.576.581.3△ −1.0
231/231
833 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
43.1336.360.977.1△ −7.0
231/231
933 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
43.1266.221.178.1△ −15.0
230/231
1033 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
41.9325.366.579.0△ −4.0
230/231
1133 examples
Superhumanizersuperhumanizer.ai
41.1246.543.274.6△ −10.0
231/231
1233 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
40.3424.665.978.8△ −5.0
229/231
1333 examples
StealthGPTstealthgpt.ai
36.4438.646.479.9△ −12.0
231/231
1433 examples
GPTinfgptinf.com
35.6337.741.471.7△ −10.0
231/231
1533 examples
SmartHumanizersmarthumanizer.ai
34.0529.050.277.6△ −10.0
231/231
1633 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
32.900.292.085.1△ −7.0
231/231
1733 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
30.910.096.685.1△ −10.0
231/231
1833 examples
HIX Bypasshixbypass.com
30.7045.441.376.9△ −20.0
231/231
1933 examples
Rehumanizerehumanize.io
26.210.860.282.2△ −6.0
231/231
2033 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
17.810.677.171.2△ −17.0
229/231
2133 examples
Undetectable AIundetectable.ai
12.610.555.679.6△ −18.0
231/231
2233 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
12.111.075.982.6△ −24.0
199/231
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
0.001.312.372.1△ −20.0
208/231

Gold, silver and bronze highlight the current top three overall values. All values use our measurements. Scores use available detector measurements. Coverage and methodology are available above.

How scores are computed

Full methodology
56.5%24%12%7.5%

Bypass

Median detector human scores per output, averaged across the entry.

Meaning

Embedding cosine similarity, rescaled by the original scorer.

Readability

Clarity, fluency, and naturalness under one frozen NVIDIA rubric.

Consistency

How evenly detector results hold up across writing categories.

Penalties

Fixed deductions for output issues. Each rule is capped at 10 points; final scores stay between 0 and 100.

Identical output−2

Whitespace-normalized output matches its source.

Refusal−1

The fixed text rule identifies a refusal.

Meaning drift−1

Raw embedding cosine is below 0.85.

Length inflation−1

The output exceeds 1.4× the source word count.

Length deflation−1

The output is below 0.6× the source word count.