November 2026 · Independent humanizer benchmarks. Explore the evidence

Updated November 18, 2026 November edition

AI humanizers.
Put to the test.

Open weights and closed services, measured on the same texts. HumanizeBench compares 23 entries across seven detectors, with meaning preservation and readability scored under one shared framework. Explore every source, rewrite, and measured result.

November 2026 AI Humanizer Benchmark

23 entries · 33 shared source texts per entry · 7 detectors

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.

Go beyond the score

Read what the models actually wrote, then inspect the measurements behind it.

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.

Why compare open and closed humanizers?

A service name and a downloadable checkpoint tell you very little about the resulting text. We wanted to place their recorded outputs under one evaluation framework, with enough evidence to see where the numbers come from.

We keep source texts fixed, score the saved rewrites, and expose coverage gaps. Related quantizations remain visible as related entries. Approximate measurements remain labeled.

Why we built HumanizeBench

One test set.
One scoring framework.

The run starts with 33 published source texts, not newly generated answers to similar prompts. Thirteen open-weight repository entries each produce one saved rewrite per source, joining 330 existing rewrites from ten closed-source services.

All 759 outputs share seven detector routes, one readability rubric, and one meaning-preservation profile. HumanizeBench v2 combines the measurements with additional weight on bypass. Read the complete method.

Find the right view for your use case

Explore the same recorded outputs by category, detector, or model type. No new examples are generated for these views.

Seven detectors.
Every result visible.

Explore reported human-likelihood scores, collection coverage, and the exact rewrites behind each detector’s results.

Frequently asked
questions

What the numbers mean, where the outputs came from, and what this benchmark can tell you.

Is there a final winner yet?+

The leaderboard is provisional while detector requests remain unresolved. A finished collection can include explicit provider exclusions, which are shown as unscored and handled as null by the original scorer. Numeric coverage remains visible for every entry.

Are open and closed entries scored the same way?+

Yes. All saved rewrites use the same detector routes, NVIDIA readability rubric, embedding profile, classification rules, weights, and penalties. Closed-source rewrites are published historical outputs; open-weight rewrites are from our recorded GPU runs.

What does “meaning” measure?+

It starts as cosine similarity between source and output embeddings. The original scorer rescales the interval from 0.75 to 1.00 onto 0 to 100. These original thresholds are retained without calibration for our NVIDIA embedding substitute.

Why are there several Humanizer 12B entries?+

The requested roster includes different formats, conversions, and repositories. They remain separate tested entries; related weight families are identified in the model pages and should not be counted as independent model designs.

Does a high detector score prove text is human-written?+

No. It is a measurement of the selected detector response on that output. It is not proof of authorship, and this benchmark makes no claim of guaranteed bypass on unseen text.

Can I inspect the actual rewrites?+

Yes. The evidence pages contain all 33 source texts, the 759 saved rewrites, measured quality scores, and available detector scores. JSON downloads are available without an account.

Is this identical to the original evaluation?+

No. The source texts and scoring arithmetic are preserved, but we use the agreed NVIDIA readability and embedding substitutes, a reconstructed rubric, current detector routes, and a shared conservative classification heuristic.

Notes from our benchmark

Original research notes about this run, its measurements, and its limits.