DeepSeek tends to write with many em dashes, evenly sized sentences and a recognisable stock of phrases such as "rather than", "far more" and "a quiet". None of these proves anything alone, since people use every one of them, but clusters of them are worth noticing. The multipliers below compare fully AI-written DeepSeek-family text against human writing in the comparison corpus.
How to read the multipliers
A figure like "5.6×" means the phrase shows up that many times more often in DeepSeek-family text than in human writing of comparable kind. It describes a tendency across many texts, not a rule for one text. A phrase used once in a page says almost nothing.
English tells
Phrases that stand out against human writers
- Contrast and comparison: "rather than" (5.6×), "far more" (9.4×), "yet the" (8.5×), "beyond" (2.9×), "whether" (2.5×)
- Quiet, small-scale framing: "a quiet" (9.8×), "a moment" (5.2×), "a small" (2×), "a short" (2.9×), "a single" (3.5×), "the kind" (5.1×), "feels like" (5.6×)
- Soft evaluative words: "practical" (6.6×), "essential" (3.7×), "offers a" (6.3×), "remains" (5.6×), "shared" (4.9×), "approach" (2.6×)
Phrases that separate it from other AI models
"a short" (2.7×), "the problem" (2.5×), "examine" (2.5×), "thing" (2.2×) and "kind of" (1.8×) appear more often than in other AI families, so they hint at DeepSeek rather than AI in general.
Structural markers
- Em dashes at about 11× the human rate, and about 2.1× the rate of other AI families
- Three-item lists ("X, Y and Z") at about 1.5× the human rate
- More uniform sentence lengths than human writers
- Fewer ellipses, exclamation marks, parentheses and question marks than human writers
Chinese tells
Phrases that stand out against human writers
- Contrast and judgement: 并非 (8.8×), 而是 (6.8×), 在于 (6.2×), 往往 (9.1×), 关键 (4.7×), 判断 (4.7×), 核心 (4.2×)
- Everyday and process framing: 日常 (9.3×), 环节 (9.2×), 节奏 (11×), 习惯 (4×), 后续 (18×), 长期 (3.5×)
Phrases that separate it from other AI models
而不是 (3.3×), 那个 (2.7×), 东西 (2.6×), 心里 (2.8×) and 习惯 (2.2×) point toward DeepSeek over other families, a more conversational register than some other models.
Structural markers
"Not X but Y" contrasts at about 3.9× the human rate, and em dashes at about 3.5×.
How Qwen and GLM differ
Qwen leans on formal connectors such as "serves as" (26×), "ensures that" (20×) and "is crucial" (25×) in English. GLM leans on intensifiers such as "entirely" (11×), "ultimately" (10×) and "deeply" (9.4×). Both also use many em dashes. The checker shows these families separately; see DeepSeek versions for the models.
Why phrases are not proof
- Humans write "rather than" and em dashes every day, and a careful editor produces even sentences.
- Editing, translation and rewriting by a person quickly dilute these markers.
- Newer model versions shift habits, so lists date.
- A short text may contain none of them while still being AI-written.
Treat any list as a reason to look closer, never as a verdict. This is a style signal, and it can point at a family without proving who wrote the text.
What Veread reads beyond phrase lists
Veread, Fileverity's text model, does not count phrases. It reads the whole text and the rhythm and structure behind it, marks the passages that read as AI-written, and compares the style with each model family. Of fully AI-written DeepSeek-family texts, 95.1% were caught, with 0.5% of human texts wrongly flagged; see the accuracy page. For documents and reports, use the full AI text detector.
Check a text yourself
Paste at least 100 words into the DeepSeek AI detector for a verdict, marked passages and a style similarity for DeepSeek, Qwen and GLM. One check is free.
To compare all seven model families, see the guide how each AI model writes.