Run: 2026-02-20-01KHY8YREM489SF1HZ8C0VM4KM

Run Details

Model:: Ministral 3 8B
Test:: Bad Writing Habits
Scenario:: Mystery: examining a crime scene
Duration:: 4.7s
Cost:: $0.000292
Provider:: Mistral

Evaluation summary

Score	Evaluator	Details Link
66.67%	Adverbs in dialogue tags	(details)
92.16%	AI-ism adverb frequency	(details)
100.00%	AI-ism character names	(details)
100.00%	AI-ism location names	(details)
29.47%	AI-ism word frequency	(details)
100.00%	Cliché density	(details)
100.00%	Emotion telling (show vs. tell)	(details)
100.00%	Filter word density	(details)
100.00%	Gibberish response detection	(details)
100.00%	Markdown formatting overuse	(details)
100.00%	Missing dialogue indicators (quotation marks)	(details)
45.64%	Name drop frequency	(details)
100.00%	Narrator intent-glossing	(details)
41.02%	"Not X but Y" pattern overuse	(details)
100.00%	Overuse of "that" (subordinate clause padding)	(details)
100.00%	Paragraph length variance	(details)
93.76%	Passive voice overuse	(details)
100.00%	Past progressive (was/were + -ing) overuse	(details)
0.00%	Em-dash & semicolon overuse	(details)
97.38%	Purple prose (modifier overload)	(details)
100.00%	Repeated phrase echo	(details)
100.00%	Sentence length variance	(details)
41.78%	Sentence opener variety	(details)
100.00%	Adverb-first sentence starts	(details)
100.00%	Pronoun-first sentence starts	(details)
65.26%	Subject-first sentence starts	(details)
0.00%	Subordinate conjunction sentence starts	(details)
100.00%	Technical jargon density	(details)
0.00%	Useless dialogue additions	(details)
83.33%	Dialogue tag variety (said vs. fancy)	(details)
78.5490%	Overall

Model input

System

You are an expert fiction writer.

Always keep the following rules in mind:
- Write in past tense and use General English spelling, grammar, and colloquialisms/slang.
- Write in active voice
- Always follow the "show, don't tell" principle.
- Avoid adverbs and cliches and overused/commonly used phrases. Aim for fresh and original descriptions.
- Convey events and story through dialogue.
- Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety.
- Skip "he/she said said" dialogue tags and convey people's actions or face expressions through their speech
- Avoid mushy dialog and descriptions, have dialogue always continue the action, never stall or add unnecessary fluff. Vary the descriptions to not repeat yourself.
- Put dialogue on its own paragraph to separate scene and action.
- Reduce indicators of uncertainty like "trying" or "maybe"

When writing text:
- NEVER conclude the scene on your own, follow the beat instructions very closely.
- NEVER end with foreshadowing.
- NEVER write further than what I prompt you with.
- AVOID imagining possible endings, NEVER deviate from the instructions.
- STOP EARLY if the continuation contains what was required in the instructions. You do not need to fill out the full amount of words possible.

User/Human

Take into account the following glossary of characters/locations/items/lore... when writing your response:
<codex>
<character id="4416" name="Detective Harlow Quinn" aliases="Quinn, Detective Quinn, Harlow" pronouns="she/her" species="Human" storyRole="Antagonist">
  <eyeColor>brown</eyeColor>
  <hair>closely cropped salt-and-pepper</hair>
  <height>5'9"</height>
  <age>41</age>
  <jawline>sharp jaw</jawline>
  <watch>worn leather watch on her left wrist</watch>
  <bearing>military precision</bearing>
  <description>A Metropolitan Police detective with 18 years of decorated service who suspects the clique is involved in criminal activity.</description>
  <backstory>She lost her partner, DS Morris, during a case three years ago under unexplained circumstances that had supernatural origins she doesn't yet understand.</backstory>
</character>

<character id="4414" name="Eva Kowalski" aliases="Eva, Evie" pronouns="she/her" species="Human" storyRole="Best Friend">
  <eyeColor>green</eyeColor>
  <hair>curly red</hair>
  <height>5'4"</height>
  <age>26</age>
  <glasses>round glasses</glasses>
  <satchel>worn leather satchel full of books</satchel>
  <freckles>freckled complexion</freckles>
  <nervousHabit>tucking hair behind her left ear</nervousHabit>
  <description>Aurora's childhood friend and an occult researcher.</description>
  <backstory>Moved to London two years before Aurora and works as a research assistant at the British Museum's restricted archives. She holds a master's degree in Ancient History from Oxford.</backstory>
</character>

<location id="856" name="The Veil Market" aliases="Veil Market, the Market, underground market" realm="Earth">
  <currentLocation>abandoned Tube station beneath Camden</currentLocation>
  <entryRequirement>bone token</entryRequirement>
  <schedule>moves locations every full moon</schedule>
  <description>A hidden supernatural black market that sells enchanted goods, banned alchemical substances, and information.</description>
</location>

<item id="2004" name="Veil Compass" aliases="the Compass, shadow compass" type="Tool" origin="The Veil Market">
  <casingMaterial>small brass compass</casingMaterial>
  <faceMarkings>face etched with protective sigils</faceMarkings>
  <needle>points toward the nearest supernatural rift or portal</needle>
  <patina>casing has a patina of verdigris</patina>
  <creator>crafted by a Shade artisan</creator>
  <description>A compass attuned to supernatural energy.</description>
</item>
</codex>

Continue the story using the following instructions:
<instructions>
Write a fully fleshed out scene of at least 1000 words in the mystery genre.

A detective arrives at a crime scene in an unusual location. Something is wrong — the evidence doesn't add up. A colleague is present, offering a different interpretation. Through careful observation and deduction, the detective begins to see what others have missed.

Use the codex entries above as your world reference for characters and setting.
Only include the prose of the scene without any markdown or commentary.
</instructions>

Model response

The rain drummed against the corrugated metal roof of the abandoned Tube station like a slow, relentless drumbeat. Detective Harlow Quinn crouched in the shadows, her breath steady despite the cold seeping through her boots. The air smelled of damp concrete and something sharper—ozone, maybe, or the faint metallic tang of blood.

"Christ," muttered DS Carter beside her, his flashlight beam cutting through the gloom. "This place is a fucking death trap."

Harlow didn’t answer. She was already moving, her boots silent on the slick stone. The crime scene tape fluttered in the draft, though no one had bothered to secure it properly. The station’s name—*Camden Road*—was peeling off the walls, the letters like a warning half-erased by time.

Then she saw it.

A body.

Not just any body. This one was draped over a rusted metal bench, arms splayed as if frozen mid-fall. The victim wore a long coat, the collar turned up against the cold, but the fabric was dark, almost black, like it had been soaked in something. Harlow’s stomach twisted. The coat smelled of burnt sugar and something older—something *wrong*.

Carter crouched beside her, his voice tight. "Looks like a suicide. Or maybe a mugging gone bad."

Harlow didn’t look at him. She knelt, her gloved fingers brushing the victim’s wrist. No pulse. No breath. Just the faintest chill radiating off the skin, like the corpse had been dead for hours.

Then she saw the wound.

A neat, precise slash across the throat, but not like any knife work she’d seen before. The edges were too clean, too *surgical*. And the blood—if it was blood—hadn’t pooled. It had *dried* in strange, uneven patches, as if something had drained it away.

Carter exhaled sharply. "You think it’s supernatural?"

Harlow didn’t answer. She was already reaching into her coat, pulling out her notebook. The first thing she did was sketch the wound. Then she noted the victim’s pockets—empty except for a single bone token, its surface smooth and unmarked.

A ticket to the Veil Market.

Her fingers tightened around the notebook. She hadn’t expected this.

Carter shifted beside her, his voice dropping. "You ever hear of that place?"

Harlow didn’t look up. "The Veil Market? Yeah. Underground. Illegal shit. Enchanted goods, black-market spells."

"Then this isn’t just some random killing," Carter said, his voice low. "This is *them*."

Harlow finally met his eyes. "Who?"

"Them." Carter gestured vaguely at the station. "The ones who run the Veil. They don’t like loose ends."

Harlow stood, brushing dirt from her knees. "Then we need to find out who this was before they find out we’re asking questions."

Carter followed her as she moved to the far end of the platform, where the tracks curved into darkness. The air here was thicker, the shadows deeper. Harlow’s flashlight caught something glinting on the ground—a brass compass, its casing etched with strange sigils. The needle spun wildly before settling, pointing not at the exit, but deeper into the station.

Harlow picked it up. The moment her fingers closed around it, a cold prickle ran up her arm.

Carter watched her, his expression unreadable. "You feeling that?"

She didn’t answer. She was already walking, the compass tucked into her pocket. The tracks stretched ahead, the darkness swallowing the light behind them.

Carter fell into step beside her. "You think this is connected to Morris?"

Harlow didn’t slow down. "I think we’re standing in the middle of something bigger than either of us."

The tracks ended in a dead end, the walls closing in around them. The air grew colder. The compass in her pocket hummed, a low, steady vibration.

Then she heard it.

A whisper.

Not from the wind. Not from the station. From *inside* the walls.

And it was calling her name.

Evaluation details

Result

Evaluator

Details

Meta Data

66.67%

Adverbs in dialogue tags

Target: ≤10% dialogue tags with adverbs

totalTags

adverbTagCount

adverbTags

0	"Carter gestured vaguely [vaguely]"

dialogueSentences

tagDensity

0.2

leniency

0.4

rawRatio

0.333

effectiveRatio

0.133

92.16%

AI-ism adverb frequency

Target: <2% AI-ism adverbs (58 tracked)

wordCount

638

totalAiIsmAdverbs

found

adverb	"sharply"
count	1

highlights

"sharply"

100.00%

AI-ism character names

Target: 0 AI-default names (17 tracked, −20% each)

codexExemptions	(empty)
found	(empty)

100.00%

AI-ism location names

Target: 0 AI-default location names (33 tracked, −20% each)

codexExemptions	(empty)
found	(empty)

29.47%

AI-ism word frequency

Target: <2% AI-ism words (290 tracked)

wordCount

638

totalAiIsms

found

word	"gloom"
count	1

word	"fluttered"
count	1

word	"stomach"
count	1

word	"pulse"
count	1

word	"chill"
count	1

word	"glinting"
count	1

word	"etched"
count	1

word	"unreadable"
count	1

word	"whisper"
count	1

highlights

0	"gloom"
1	"fluttered"
2	"stomach"
3	"pulse"
4	"chill"
5	"glinting"
6	"etched"
7	"unreadable"
8	"whisper"

100.00%

Cliché density

Target: ≤1 cliche(s) per 800-word window

totalCliches	0
maxInWindow	0
found	(empty)
highlights	(empty)

100.00%

Emotion telling (show vs. tell)

Target: ≤3% sentences with emotion telling

emotionTells	0
narrationSentences	61
matches	(empty)

100.00%

Filter word density

Target: ≤3% sentences with filter/hedge words

filterCount	0
hedgeCount	0
narrationSentences	61
filterMatches	(empty)
hedgeMatches	(empty)

100.00%

Gibberish response detection

Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)

analyzedSentences	73
gibberishSentences	0
adjustedGibberishSentences	0
longSentenceCount	0
runOnParagraphCount	0
giantParagraphCount	0
wordSaladCount	0
repetitionLoopCount	0
controlTokenCount	0
maxSentenceWordsSeen	27
ratio	0
matches	(empty)

100.00%

Markdown formatting overuse

Target: ≤5% words in markdown formatting

markdownSpans

markdownWords

totalWords

629

ratio

0.011

matches

0	"Camden Road"
1	"wrong"
2	"surgical"
3	"dried"
4	"them"
5	"inside"

100.00%

Missing dialogue indicators (quotation marks)

Target: ≤10% speech attributions without quotation marks

totalAttributions	7
unquotedAttributions	0
matches	(empty)

45.64%

Name drop frequency

Target: ≤1.0 per-name mentions per 100 words

totalMentions

wordCount

527

uniqueNames

maxNameDensity

2.09

worstName

"Harlow"

maxWindowNameDensity

worstWindowName

"Harlow"

discoveredNames

Tube	1
Harlow	11
Quinn	1
Carter	9
Veil	1
Market	1

persons

0	"Harlow"
1	"Quinn"
2	"Carter"

places

"Veil"

globalScore

0.456

windowScore

0.667

100.00%

Narrator intent-glossing

Target: ≤2% narration sentences with intent-glossing patterns

analyzedSentences	37
glossingSentenceCount	0
matches	(empty)

41.02%

"Not X but Y" pattern overuse

Target: ≤1 "not X but Y" per 1000 words

totalMatches

per1kWords

1.59

wordCount

629

matches

0	"not at the exit, but deeper into the station"

100.00%

Overuse of "that" (subordinate clause padding)

Target: ≤2% sentences with "that" clauses

thatCount	0
totalSentences	73
matches	(empty)

100.00%

Paragraph length variance

Target: CV ≥0.5 for paragraph word counts

totalParagraphs

mean

20.29

std

16.69

0.823

sampleLengths

0	52
1	20
2	47
3	4
4	2
5	59
6	17
7	34
8	5
9	44
10	7
11	40
12	6
13	10
14	13
15	15
16	15
17	6
18	18
19	23
20	59
21	18
22	9
23	24
24	13
25	18
26	27
27	4
28	2
29	12
30	6

93.76%

Passive voice overuse

Target: ≤2% passive sentences

passiveCount

totalSentences

matches

0	"was draped"
1	"been soaked"

100.00%

Past progressive (was/were + -ing) overuse

Target: ≤2% past progressive verbs

pastProgressiveCount

totalVerbs

matches

0	"was calling"

0.00%

Em-dash & semicolon overuse

Target: ≤2% sentences with em-dashes/semicolons

emDashCount

semicolonCount

flaggedSentences

totalSentences

ratio

0.082

matches

0	"The air smelled of damp concrete and something sharper—ozone, maybe, or the faint metallic tang of blood."
1	"The station’s name—Camden Road—was peeling off the walls, the letters like a warning half-erased by time."
2	"The coat smelled of burnt sugar and something older—something wrong."
3	"And the blood—if it was blood—hadn’t pooled."
4	"Then she noted the victim’s pockets—empty except for a single bone token, its surface smooth and unmarked."
5	"Harlow’s flashlight caught something glinting on the ground—a brass compass, its casing etched with strange sigils."

97.38%

Purple prose (modifier overload)

Target: <4% adverbs, <2% -ly adverbs, no adj stacking

wordCount	535
adjectiveStacks	0
stackExamples	(empty)
adverbCount	23
adverbRatio	0.04299065420560748
lyAdverbCount	5
lyAdverbRatio	0.009345794392523364

100.00%

Repeated phrase echo

Target: ≤20% sentences with echoes (window: 2)

totalSentences	73
echoCount	0
echoWords	(empty)

100.00%

Sentence length variance

Target: CV ≥0.4 for sentence word counts

totalSentences

mean

8.62

std

5.45

0.632

sampleLengths

0	18
1	17
2	17
3	13
4	7
5	3
6	11
7	17
8	16
9	4
10	2
11	4
12	15
13	27
14	3
15	10
16	7
17	10
18	5
19	9
20	2
21	2
22	16
23	5
24	16
25	7
26	7
27	14
28	3
29	4
30	3
31	11
32	9
33	17
34	6
35	6
36	4
37	7
38	6
39	4
40	11
41	12
42	3
43	5
44	1
45	7
46	11
47	7
48	16
49	19

41.78%

Sentence opener variety

Target: ≥60% unique sentence openers

consecutiveRepeats	6
diversityRatio	0.2876712328767123
totalSentences	73
uniqueOpeners	21

100.00%

Adverb-first sentence starts

Target: ≥3% sentences starting with an adverb

adverbCount

totalSentences

matches

0	"Then she saw it."
1	"Just the faintest chill radiating"
2	"Then she saw the wound."
3	"Then she noted the victim’s"
4	"Then she heard it."

ratio

0.088

100.00%

Pronoun-first sentence starts

Target: ≤30% sentences starting with a pronoun

pronounCount

totalSentences

matches

0	"She was already moving, her"
1	"She knelt, her gloved fingers"
2	"It had dried in strange,"
3	"She was already reaching into"
4	"Her fingers tightened around the"
5	"She hadn’t expected this."
6	"She didn’t answer."
7	"She was already walking, the"

ratio

0.14

65.26%

Subject-first sentence starts

Target: ≤72% sentences starting with a subject

subjectCount

totalSentences

matches

0	"The rain drummed against the"
1	"Detective Harlow Quinn crouched in"
2	"The air smelled of damp"
3	"Harlow didn’t answer."
4	"She was already moving, her"
5	"The crime scene tape fluttered"
6	"The station’s name—Camden Road—was peeling"
7	"This one was draped over"
8	"The victim wore a long"
9	"Harlow’s stomach twisted."
10	"The coat smelled of burnt"
11	"Carter crouched beside her, his"
12	"Harlow didn’t look at him."
13	"She knelt, her gloved fingers"
14	"A neat, precise slash across"
15	"The edges were too clean,"
16	"It had dried in strange,"
17	"Carter exhaled sharply."
18	"Harlow didn’t answer."
19	"She was already reaching into"

ratio

0.789

0.00%

Subordinate conjunction sentence starts

Target: ≥2% sentences starting with a subordinating conjunction

subConjCount	0
totalSentences	57
matches	(empty)
ratio	0

100.00%

Technical jargon density

Target: ≤6% sentences with technical-jargon patterns

analyzedSentences

technicalSentenceCount

matches

0	"She was already reaching into her coat, pulling out her notebook."

0.00%

Useless dialogue additions

Target: ≤5% dialogue tags with trailing filler fragments

totalTags

uselessAdditionCount

matches

0	"muttered DS Carter beside her, his flashlight beam cutting through the gloom"
1	"Carter said, his voice low"

83.33%

Dialogue tag variety (said vs. fancy)

Target: ≤10% fancy dialogue tags

totalTags

fancyCount

fancyTags

0	"muttered DS Carter beside her (mutter)"

dialogueSentences

tagDensity

0.133

leniency

0.267

rawRatio

0.5

effectiveRatio

0.133

78.5490%