Run: 2026-02-20-01KHYA21TD6CMSPD1BAWRST1GR

Run Details

Model:: Ministral 3 14B
Test:: Bad Writing Habits
Scenario:: Mystery: examining a crime scene
Duration:: 6.7s
Cost:: $0.000382
Provider:: Mistral

Evaluation summary

Score	Evaluator	Details Link
100.00%	Adverbs in dialogue tags	(details)
83.22%	AI-ism adverb frequency	(details)
100.00%	AI-ism character names	(details)
100.00%	AI-ism location names	(details)
16.11%	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)
49.33%	Name drop frequency	(details)
100.00%	Narrator intent-glossing	(details)
100.00%	"Not X but Y" pattern overuse	(details)
100.00%	Overuse of "that" (subordinate clause padding)	(details)
100.00%	Paragraph length variance	(details)
93.16%	Passive voice overuse	(details)
100.00%	Past progressive (was/were + -ing) overuse	(details)
0.00%	Em-dash & semicolon overuse	(details)
100.00%	Purple prose (modifier overload)	(details)
100.00%	Repeated phrase echo	(details)
100.00%	Sentence length variance	(details)
78.54%	Sentence opener variety	(details)
100.00%	Adverb-first sentence starts	(details)
100.00%	Pronoun-first sentence starts	(details)
34.47%	Subject-first sentence starts	(details)
0.00%	Subordinate conjunction sentence starts	(details)
16.81%	Technical jargon density	(details)
0.00%	Useless dialogue additions	(details)
100.00%	Dialogue tag variety (said vs. fancy)	(details)
79.0545%	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 abandoned Tube station reeked of damp concrete and something older, something that clung to the air like a second skin. Detective Harlow Quinn stepped over the yellow tape, her boots crunching on shattered glass. The flickering overhead lights cast long, jagged shadows across the graffiti-scarred walls—tags that hadn’t been there yesterday, if the crime scene photos were to be believed.

DS Whitaker stood near the body, his gloved hands adjusting the crime scene markers. He didn’t look up as she approached. "Took you long enough, Quinn. Thought you’d gotten lost."

She ignored the jab. Whitaker had always been a man who thrived on petty friction. "Where’s the victim?"

"Over there." He jerked his chin toward a huddled figure near the rusted tracks. "Looks like another junkie OD, but the tox screen’s coming back clean."

Quinn crouched beside the body. A young woman, late twenties, her dark hair matted with something dark and sticky. Not blood. Tar, maybe. Or oil. Her fingers were curled into the palm of her other hand, knuckles white even in death. A bone token lay beside her, its surface etched with spiralling lines—no, not lines. *Runes.*

Whitaker followed her gaze. "So? Plenty of weird shit in this part of town."

Quinn picked it up. The token was cold, heavier than it should’ve been. She turned it over in her fingers. "This isn’t street-level weird. This is *Veil Market* weird."

A beat of silence. Then Whitaker let out a sharp laugh. "You’re joking, right? That place’s a myth."

"Not anymore." She stood, the token tucked into her pocket. "Three bodies in as many weeks, all with these tokens. All found where they shouldn’t be." She gestured to the tracks. "This isn’t a junkie’s stash spot. The station’s been sealed for years."

Whitaker crossed his arms. "So what’s your play, Quinn? Ghosts? Fairies?"

She ignored the sarcasm. The body’s lips were slightly parted, as if she’d been about to speak. Quinn leaned in closer, examining the skin around her mouth. No bruising. No struggle marks. Just… stillness. Too still.

Then she saw it—the faintest shimmer at the edge of her vision, like heat haze over asphalt. Quinn blinked. It was gone.

Whitaker noticed her hesitation. "You seeing something?"

"No." She straightened, rubbing her temples. "But I’m not seeing *nothing* either."

A uniformed officer approached, holding a clear evidence bag. Inside was a small brass compass, its face etched with sigils that pulsed faintly under the station lights. The needle didn’t point north.

Whitaker’s smirk faded. "What the hell is *that*?"

Quinn’s pulse quickened. She knew that compass. Had seen one like it in a case file three years ago—one that had ended with Morris’s death. "That’s a Veil Compass. Points to supernatural rifts."

Whitaker scoffed. "Or it’s a cheap tourist trinket from Camden Market."

Quinn didn’t answer. She was already pulling out her phone, snapping photos of the compass, the token, the body’s unnatural stillness. The air here was thick, charged with something she couldn’t name. But she’d felt it before—the same prickling at the back of her neck, the same wrongness that had led her down the wrong path before.

Whitaker sighed. "You’re really buying into this, aren’t you?"

She pocketed her phone. "I’m buying into *evidence*, Whitaker. And right now, the evidence is screaming at me."

A distant drip echoed through the station. Water, or something else. Quinn’s eyes flicked to the shadows pooling beneath the tracks. The compass in her pocket felt heavier.

She needed answers. And she knew exactly where to start.

Evaluation details

Result

Evaluator

Details

Meta Data

100.00%

Adverbs in dialogue tags

Target: ≤10% dialogue tags with adverbs

totalTags	4
adverbTagCount	0
adverbTags	(empty)
dialogueSentences	19
tagDensity	0.211
leniency	0.421
rawRatio	0
effectiveRatio	0

83.22%

AI-ism adverb frequency

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

wordCount

596

totalAiIsmAdverbs

found

adverb	"slightly"
count	1

adverb	"really"
count	1

highlights

0	"slightly"
1	"really"

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)

16.11%

AI-ism word frequency

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

wordCount

596

totalAiIsms

found

word	"shattered"
count	1

word	"etched"
count	2

word	"silence"
count	1

word	"pulsed"
count	1

word	"pulse"
count	1

word	"quickened"
count	1

word	"charged"
count	1

word	"echoed"
count	1

word	"flicked"
count	1

highlights

0	"shattered"
1	"etched"
2	"silence"
3	"pulsed"
4	"pulse"
5	"quickened"
6	"charged"
7	"echoed"
8	"flicked"

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	58
matches	(empty)

100.00%

Filter word density

Target: ≤3% sentences with filter/hedge words

filterCount	0
hedgeCount	0
narrationSentences	58
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	28
ratio	0
matches	(empty)

100.00%

Markdown formatting overuse

Target: ≤5% words in markdown formatting

markdownSpans

markdownWords

totalWords

589

ratio

0.01

matches

0	"Runes."
1	"Veil Market"
2	"nothing"
3	"that"
4	"evidence"

100.00%

Missing dialogue indicators (quotation marks)

Target: ≤10% speech attributions without quotation marks

totalAttributions	5
unquotedAttributions	0
matches	(empty)

49.33%

Name drop frequency

Target: ≤1.0 per-name mentions per 100 words

totalMentions

wordCount

447

uniqueNames

maxNameDensity

2.01

worstName

"Whitaker"

maxWindowNameDensity

worstWindowName

"Whitaker"

discoveredNames

Tube	1
Harlow	1
Quinn	8
Whitaker	9
Morris	1

persons

0	"Harlow"
1	"Quinn"
2	"Whitaker"
3	"Morris"

places

(empty)

globalScore

0.493

windowScore

0.667

100.00%

Narrator intent-glossing

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

analyzedSentences	27
glossingSentenceCount	0
matches	(empty)

100.00%

"Not X but Y" pattern overuse

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

totalMatches	0
per1kWords	0
wordCount	589
matches	(empty)

100.00%

Overuse of "that" (subordinate clause padding)

Target: ≤2% sentences with "that" clauses

thatCount

totalSentences

matches

0	"knew that compass"

100.00%

Paragraph length variance

Target: CV ≥0.5 for paragraph word counts

totalParagraphs

mean

25.61

std

15.9

0.621

sampleLengths

0	61
1	30
2	18
3	26
4	56
5	14
6	29
7	18
8	43
9	11
10	36
11	22
12	7
13	12
14	32
15	8
16	33
17	11
18	57
19	9
20	18
21	28
22	10

93.16%

Passive voice overuse

Target: ≤2% passive sentences

passiveCount

totalSentences

matches

0	"were curled"
1	"was gone"

100.00%

Past progressive (was/were + -ing) overuse

Target: ≤2% past progressive verbs

pastProgressiveCount	0
totalVerbs	81
matches	(empty)

0.00%

Em-dash & semicolon overuse

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

emDashCount

semicolonCount

flaggedSentences

totalSentences

ratio

0.068

matches

0	"The flickering overhead lights cast long, jagged shadows across the graffiti-scarred walls—tags that hadn’t been there yesterday, if the crime scene photos were to be believed."
1	"A bone token lay beside her, its surface etched with spiralling lines—no, not lines."
2	"Then she saw it—the faintest shimmer at the edge of her vision, like heat haze over asphalt."
3	"Had seen one like it in a case file three years ago—one that had ended with Morris’s death."
4	"But she’d felt it before—the same prickling at the back of her neck, the same wrongness that had led her down the wrong path before."

100.00%

Purple prose (modifier overload)

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

wordCount	453
adjectiveStacks	0
stackExamples	(empty)
adverbCount	12
adverbRatio	0.026490066225165563
lyAdverbCount	3
lyAdverbRatio	0.006622516556291391

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

8.07

std

5.91

0.732

sampleLengths

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

78.54%

Sentence opener variety

Target: ≥60% unique sentence openers

consecutiveRepeats	1
diversityRatio	0.4794520547945205
totalSentences	73
uniqueOpeners	35

100.00%

Adverb-first sentence starts

Target: ≥3% sentences starting with an adverb

adverbCount

totalSentences

matches

0	"Then Whitaker let out a"
1	"Then she saw it—the faintest"

ratio

0.043

100.00%

Pronoun-first sentence starts

Target: ≤30% sentences starting with a pronoun

pronounCount

totalSentences

matches

0	"He didn’t look up as"
1	"She ignored the jab."
2	"He jerked his chin toward"
3	"Her fingers were curled into"
4	"She turned it over in"
5	"She stood, the token tucked"
6	"She gestured to the tracks"
7	"She ignored the sarcasm."
8	"It was gone."
9	"She straightened, rubbing her temples"
10	"She knew that compass."
11	"She was already pulling out"
12	"She pocketed her phone."
13	"She needed answers."

ratio

0.298

34.47%

Subject-first sentence starts

Target: ≤72% sentences starting with a subject

subjectCount

totalSentences

matches

0	"The abandoned Tube station reeked"
1	"Detective Harlow Quinn stepped over"
2	"The flickering overhead lights cast"
3	"DS Whitaker stood near the"
4	"He didn’t look up as"
5	"She ignored the jab."
6	"Whitaker had always been a"
7	"He jerked his chin toward"
8	"Quinn crouched beside the body."
9	"A young woman, late twenties,"
10	"Her fingers were curled into"
11	"A bone token lay beside"
12	"Whitaker followed her gaze."
13	"Quinn picked it up."
14	"The token was cold, heavier"
15	"She turned it over in"
16	"A beat of silence."
17	"She stood, the token tucked"
18	"She gestured to the tracks"
19	"Whitaker crossed his arms."

ratio

0.851

0.00%

Subordinate conjunction sentence starts

Target: ≥2% sentences starting with a subordinating conjunction

subConjCount	0
totalSentences	47
matches	(empty)
ratio	0

16.81%

Technical jargon density

Target: ≤6% sentences with technical-jargon patterns

analyzedSentences

technicalSentenceCount

matches

0	"The abandoned Tube station reeked of damp concrete and something older, something that clung to the air like a second skin."
1	"She was already pulling out her phone, snapping photos of the compass, the token, the body’s unnatural stillness."
2	"But she’d felt it before—the same prickling at the back of her neck, the same wrongness that had led her down the wrong path before."

0.00%

Useless dialogue additions

Target: ≤5% dialogue tags with trailing filler fragments

totalTags

uselessAdditionCount

matches

0	"She stood, the token tucked into her pocket"

100.00%

Dialogue tag variety (said vs. fancy)

Target: ≤10% fancy dialogue tags

totalTags

79.0545%