NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHT0QP18XB2ZN1EY1VKR42TA
Run Details
Model:
GPT-5.2
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
1m 26s
Cost:
$0.054826
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
100.00%
AI-ism adverb frequency
(details)
80.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
71.44%
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)
0.00%
Name drop frequency
(details)
82.43%
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)
98.94%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
100.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
45.41%
Sentence opener variety
(details)
0.00%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
22.80%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
89.29%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
83.0102%
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
Messages
Meta
AI
The escalator had stopped years
ago, frozen halfway down like it had choked on the dark.
Detective Harlow Quinn took the
service stairs instead, boots finding the edge of each tread.
Water dripped somewhere below, slow
as a metronome.
The air thickened with cold
iron and old electricity.
Her torch cut a white
strip through the stairwell.
Camden roared up on the
street. Down here, London held its breath.
A uniform waited at the
bottom, helmet tucked under his arm.
He looked too neat for
a place like this, like someone had dropped him from a different life. “Evening, ma’am. You’re the one with the token.”
Quinn pulled a knucklebone from
her pocket.
It sat in her palm
like a tooth, polished by handling.
A line of tiny scratches
ran around it, notches that formed a circle if you stared long enough.
The uniform’s eyes stayed on
it. “Where’d you get that?” Quinn kept walking. “Evidence.”
He swallowed his questions and
led her through an arched corridor that once funnelled commuters toward platforms.
The tiled walls had peeled
into islands of grime.
Posters clung in tatters: smiling
faces advertising shows that had closed before some of the officers upstairs had been born.
The corridor opened into a
cavern that shouldn’t have fit under Camden.
Lanterns hung from cables, throwing
honey-coloured light over a maze of stalls built from scavenged doors and sheet metal.
The market buzzed like a
nest disturbed with a stick: low voices, clinks of glass, the rustle of paper, the occasional metallic knock that
sounded like a coin dropped on stone
.
Quinn’s watch strap creaked as
she checked the time. 02:17.
Her wrist felt colder down
here. People watched her. Not the curious kind of watching. The counting kind. A cordon of blue-and-white tape cut across the near end of the platform. Two forensics techs in white coveralls stood beside a stall that sold jars of something cloudy. One jar held what looked like a moth the size of Quinn’s hand, wings pinned open in a pale suspension.
Her colleague waited by the
tape. Detective Constable Imani
Patel
had her hair tied back and her sleeves rolled to the elbow as if she’d come prepared to scrub blood off the world. She held a small notepad, pen poised.
Patel
’s gaze
flicked
over Quinn’s face, then past her shoulder toward the market crowd. “Thought you’d bring half the Yard with you.” Quinn ducked under the tape. “I left them where they belonged. On the street, pretending this place didn’t exist.”
Patel
moved with her, careful not to touch anything.
Her shoes stuck for a
moment on the tacky platform. “Tell me you saw the entrance yourself.” Quinn’s eyes tracked the platform edge, the old safety line half buried under soot. “I saw enough. Someone met our witness down here last night. He didn’t walk back out.”
Patel
tapped her notepad once. “Witness. You mean the bloke who rang in that tip about stolen artefacts?” Quinn stopped at the edge of the light. The market noise dulled in the cordoned area, as if sound respected police tape. Beyond it, a body lay on the platform tiles. The victim’s head tilted toward the tracks, mouth open on nothing.
His jacket had been unzipped
and peeled back, shirt dragged up. The skin of his chest shone waxy under the torchlight. A thin cut ran from his collarbone to his sternum, neat as a tailor’s line. No pooling blood.
Patel
crouched near the feet, not too close. She stared at the cut, then at the victim’s hands. “Knife. Clean work. Street gang sort of clean. Quick slice, take what you want, make a point.” Quinn knelt on the opposite side and looked at the man’s fingernails. Dirt and black powder packed under them. The pads of his fingers showed faint burns, like he’d handled something that held heat longer than it should. “What’d they take?” Quinn asked.
Patel
opened her free hand. A clear plastic evidence bag dangled from her fingers. Inside sat a small brass compass, old enough to have lived in someone’s pocket through wars.
Its casing carried a patina
of green. Protective sigils had
been etched
around the face, lines too precise for idle decoration. “The weird trinket he brought. Forensics found it in his coat lining. Thought it was a prop at first.” Quinn stared at it. Something in her
stomach
tightened, a knot pulled by an unseen hand. “Where’s the needle pointing?”
Patel
frowned. “What?” “The needle. It’s a compass.”
Patel
lifted the bag and turned it. The needle
quivered
, then settled. Not north. It pointed toward the tracks.
Patel
’s lips pressed into a line. “Magnets. Someone played games.” Quinn reached out. The tech nearest them shifted, ready to object, but Quinn held up her warrant card with two fingers and kept her eyes on the compass. “I’m not touching it. Hold it steady.”
Patel
held the bag still. The needle jittered, skittering as if it wanted to bite through plastic, then steadied again toward the darkness beyond the platform edge. Quinn’s torch followed the direction. The tracks lay half submerged in stale water. A rusted maintenance ladder disappeared down the tunnel wall. In the tunnel, the dark didn’t sit flat. It folded.
Patel
leaned closer, squinting. “That tunnel’s just a tunnel.” Quinn angled the light. The beam met
something like heat shimmer, except no heat
lived down here. The air rippled in a vertical seam, a faint distortion that made the tunnel bricks
look
like they’d
been painted
on wet paper.
Patel
’s breath caught, then she turned it into a scoff and stood. “Optical illusion. We’re underground. Damp. Light bends.” Quinn rose.
Her knees cracked and the
sound snapped sharp in the hush. “Damp doesn’t make a compass lie.”
Patel
pointed at the body. “Look at the cut. No hesitation marks. No tearing. Whoever did it knew blades.” Quinn walked around the body, slow, letting her eyes catalogue. The victim’s shoes—cheap trainers—had grey grit on the soles. Not the red dust that coated parts of the platform here, ground down brick and rust. Grey grit belonged to the stairwell and the service corridor. “So he came in through the stairs.” Quinn looked at the tiles around the body. “Where’s his footprint trail?”
Patel
glanced down, then back up with impatience written across her forehead. “Forensics—” Quinn moved closer to the cut. The skin around it looked too calm. No bruising, no swelling. The edges stayed pale, as if the knife had never touched flesh.
Patel
watched her face. “You see something.” Quinn lifted the victim’s left hand with two gloved fingers. The hand flopped with dead
weight
. She turned it palm-up. A faint circular mark sat in the centre, like someone had pressed a coin heated over a flame into his skin. The mark held tiny lines, not random, a pattern too deliberate for injury.
Patel
leaned in despite herself. “Branding?” Quinn
traced
the air above it. “Stamp. Not metal. Something else.”
Patel
straightened, shoulders tightening. “Quinn, we’re not doing ghost stories. We’ve got a dead man, a knife wound, a stolen artefact case. The superintendent wants a name by breakfast.” Quinn’s
jaw clenched
. The old instinct rose in her, the one that had kept her alive through riots and raids. Follow what you can prove. Ignore the noise. But the noise, down here, wore a different skin. A market vendor stood behind a stall of twisted candles, watching them. The vendor’s eyes looked too pale. His hands never stopped moving, stringing something that glinted like fishbones. Quinn stepped away from the body and addressed
Patel
without taking her eyes off the vendor. “Who found him?”
Patel
flipped a page. “Market security. If that’s what you call it. A bloke named Gage. He called 999 from a burner phone and vanished before uniforms arrived. Locals put the tape up themselves. They wanted us contained in one corner like we were the smell.” Quinn’s gaze swept the nearby stalls. Some shutters had
been dragged
down. Others stayed open, business carrying on in whispers. People treated the cordon like weather: unpleasant but not stopping anything. “So they controlled the scene before we arrived.”
Patel
’s eyes sharpened. “Now you’re talking sense.” Quinn pointed her torch at the tiles near the victim’s head. A smear of black clung to the grout line. Not soot. It
shimmered
in the beam, like powdered glass. “Bag that.” One of the techs nodded and moved in.
Patel
followed the light, then she leaned close and grimaced. “That’s ash. He smoked something. Plenty of these punters smoke weird stuff.” Quinn moved the torch again. The ash formed a curve. Not a spill. A line. She walked the curve, slow.
It made a rough circle
around the body, broken in two places where boots had smeared it. The circle wasn’t wide, not much bigger than the victim’s outstretched arms. Quinn held her breath and looked at the points where the circle broke. The breaks didn’t match police boots. The tread pattern looked like old leather soles with a raised ridge, narrow, pointed. Not modern footwear. Not a uniform.
Patel
watched her
look
. “What?” “Someone stepped into the circle after it went down.” Quinn pointed at the faint ridge marks. “And someone stepped out.”
Patel
folded her arms. “Fine. A suspect walked around the body. Still a stabbing.” Quinn stepped to the victim’s jacket. Forensics had unzipped it and opened the lining. Quinn didn’t touch.
She leaned in close enough
to smell it. A sharp tang hit her, like pennies and rain on hot pavement. Under it sat something sweet, rotten at the edges.
Patel
took a step back, nostrils flaring. “Jesus. What’s that stink?” Quinn kept her gaze on the lining. Thin threads stitched into the fabric, almost invisible until the torch angle caught them. The threads caught light like spider
silk
. They formed small symbols, repeated, the same shapes
etched
on the compass face.
Patel
’s voice flattened. “That’s… sewing.” Quinn’s eyes stayed on the symbols. “That’s a ward.”
Patel
’s laugh came out hard, a sound with no humour. “You learned that at Detective School, did you?” Quinn’s throat tightened. A memory cracked open: DS Morris’s laugh, the way it had bounced off a brick wall in an alley behind a nightclub, then cut off when the air had torn like fabric. Quinn had stood over his blood and watched it crawl uphill into a drain that wasn’t there. She forced the memory down. She didn’t blink. “Do me a favour,” Quinn said. “Ask your forensics tech what kind of blade makes a cut with no bruising and no blood.”
Patel
looked at the nearest tech, then back at Quinn with a
flicker
of irritation. “Oi. Collins. Cut like that—what do you think?” Collins adjusted his mask, eyes darting between the body and Quinn’s face. He held a small camera and
tried to
look
like he belonged. “Honestly? It looks… staged. Like it was made after death. Or with something sharp that cauterised. But there’s no burn.”
Patel
’s mouth tightened. She shifted her
weight
. “Post-mortem cut, then. Someone played dress-up.” Quinn crouched again, this time at the edge of the circle. She aimed her torch at the victim’s mouth. His tongue sat dry. No froth. No sign of choking. She glanced at the eyes. Pupils wide, frozen. Fear left marks even in death. This face held surprise, not terror. She looked down at his wrists. Fine red indentations circled both, as if cord had bound him. Not tight enough to cut, tight enough to guide. Quinn stood and stepped to the platform edge, the compass needle still pointing. She peered into the tunnel shimmer.
Patel
grabbed her sleeve. “Don’t.” Quinn didn’t
look
away. “You want a name by breakfast. I want a route.”
Patel
let go, fingers leaving a pale print on Quinn’s jacket. “We don’t go in tunnels without proper kit. We don’t go in—”
Patel
’s eyes
flicked
to the shimmer and she swallowed. “We don’t go in whatever that is.” Quinn nodded once, sharp. “Then we make it come to us.”
Patel
’s brow
furrowed
. “What does that even mean?” Quinn moved back to the body and pointed at the compass in the evidence bag. “This didn’t sit in his coat by chance. He hid it. Someone marked him.” She tapped the air above the brand on his palm. “Someone drew a circle. Then they used the compass like a key.”
Patel
shook her head, but her eyes stayed stuck on the compass needle, on its stubborn angle toward the tracks. “You’re building a story because you want it to fit.” Quinn looked past
Patel
at the market crowd. Two figures in long coats drifted closer, not close enough for the tape, close enough to listen. A stallholder with silver rings stopped ringing up a customer and leaned toward the commotion. Quinn lowered her voice. “This place ran on rules. Entry requirements. Tokens. Private security. People kept order because it benefited them.” She gestured at the open stalls. “A stabbing broke business. A body scared customers.”
Patel
’s chin lifted, defiant. “So someone dumped him here to scare them.” Quinn shook her head. “No. They cut him neat and left no blood. They kept it tidy. They didn’t want fear. They wanted a message for someone who understood the symbols.”
Patel
’s
eyes narrowed
. “And you understood.” Quinn held
Patel
’s gaze. “I recognised enough to know it didn’t belong in any gang file.”
Patel
looked away first, lips pressed flat. She scribbled something, pen scratching hard. “What do you want from me, Quinn? You want me to write ‘magic circle’ in the report? You want me laughed out of the unit?” Quinn walked to the tape and lifted it, letting
Patel
step under and follow her a few paces away from the body. The market noise rose again, voices like water over rocks. A man in a ragged suit leaned out of a stall stacked with old passports and yellowed maps. His eyes tracked Quinn’s
watch
, not her face. Quinn stopped near a pillar where old Tube signage hung crooked. The word WAY OUT pointed at a brick wall. She turned back to
Patel
. “You kept your head. Good. Keep it a bit longer.” Quinn nodded toward the compass bag. “That compass didn’t point north. It pointed at a distortion in the tunnel air. That distortion sat inside the arc of the circle. The ward stitched into his coat matched the compass sigils.”
Patel
’s throat moved. She tucked her notepad away with a stiff motion. “So what did we miss?” Quinn
scanned
the platform tiles again. The circle. The footprints. The lack of blood. The bindings. The brand. The needle. “The crime scene,” Quinn muttered, then she raised her voice. “It didn’t happen here.”
Patel
’s eyes snapped to her. “What?” Quinn pointed at the victim’s shoes. “No red dust. He didn’t stand in that circle long enough to pick it up. Someone placed him inside it. They cut him after he died, or they cut him with something that didn’t bleed.” Quinn shifted her torch to the platform edge. “They used that compass to open whatever sat in that tunnel, then they brought him through and laid him down like a parcel.”
Patel
’s face tightened, then her gaze drifted to the shimmer again. Her confidence cracked at the corner, just enough to show something raw underneath. “You’re telling me someone dragged a corpse through a wall.” Quinn watched the market crowd. The pale-eyed vendor’s hands paused for the first time, his fishbone string going still. Quinn lowered her torch and spoke without raising her voice. “I’m telling you our killer didn’t need the stairs.”
created_at
"2026-02-19T03:57:39.248Z"
2/19/2026, 3:57:39 AM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
7371
moderation_latency
(null)
generation_time
85456
tokens_prompt
1149
tokens_completion
4261
native_tokens_prompt
1009
native_tokens_completion
3790
native_tokens_completion_images
0
native_tokens_reasoning
337
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.05482575
router
(null)
provider_responses
0
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
id
"resp_02e0bc0a57fc2f340169968a335ca0819397b28b509cfcee5a"
is_byok
false
latency
195
model_permaslug
"openai/gpt-5.2-20251211"
provider_name
"OpenAI"
status
200
api_type
"completions"
id
"gen-1771473459-eKjKziyk6MFzyZjgQ452"
upstream_id
"resp_02e0bc0a57fc2f340169968a335ca0819397b28b509cfcee5a"
total_cost
0.05482575
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
10
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
72
tagDensity
0.139
leniency
0.278
rawRatio
0
effectiveRatio
0
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2626
totalAiIsmAdverbs
0
found
(empty)
highlights
(empty)
80.00%
AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions
(empty)
found
0
"Patel"
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
71.44%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2626
totalAiIsms
15
found
0
word
"flicked"
count
2
1
word
"etched"
count
2
2
word
"stomach"
count
1
3
word
"quivered"
count
1
4
word
"weight"
count
2
5
word
"traced"
count
1
6
word
"jaw clenched"
count
1
7
word
"shimmered"
count
1
8
word
"silk"
count
1
9
word
"flicker"
count
1
10
word
"furrowed"
count
1
11
word
"scanned"
count
1
highlights
0
"flicked"
1
"etched"
2
"stomach"
3
"quivered"
4
"weight"
5
"traced"
6
"jaw clenched"
7
"shimmered"
8
"silk"
9
"flicker"
10
"furrowed"
11
"scanned"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
2
maxInWindow
1
found
0
label
"eyes widened/narrowed"
count
1
1
label
"jaw/fists clenched"
count
1
highlights
0
"eyes narrowed"
1
"jaw clenched"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
222
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
4
hedgeCount
1
narrationSentences
222
filterMatches
0
"watch"
1
"look"
hedgeMatches
0
"tried to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
284
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
43
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2617
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
12
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
109
wordCount
1930
uniqueNames
9
maxNameDensity
3.01
worstName
"Quinn"
maxWindowNameDensity
5.5
worstWindowName
"Quinn"
discoveredNames
Harlow
1
Quinn
58
London
1
Camden
2
Constable
1
Imani
1
Patel
43
Morris
1
Tube
1
persons
0
"Harlow"
1
"Quinn"
2
"Camden"
3
"Imani"
4
"Patel"
5
"Morris"
places
0
"London"
globalScore
0
windowScore
0
82.43%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
148
glossingSentenceCount
4
matches
0
"sounded like a coin dropped on stone"
1
"looked like a moth the size of Quinn’s ha"
2
"something like heat shimmer, except no heat"
3
"looked like old leather soles with a rais"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
2617
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
284
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
161
mean
16.25
std
14.66
cv
0.902
sampleLengths
0
48
1
21
2
29
3
8
4
36
5
6
6
4
7
3
8
1
9
46
10
62
11
16
12
12
13
49
14
40
15
14
16
8
17
5
18
14
19
19
20
7
21
14
22
16
23
5
24
13
25
31
26
47
27
3
28
18
29
17
30
38
31
5
32
51
33
19
34
16
35
4
36
2
37
1
38
5
39
14
40
5
41
6
42
4
43
28
44
7
45
27
46
32
47
4
48
5
49
40
98.94%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
4
totalSentences
222
matches
0
"been unzipped"
1
"been etched"
2
"been painted"
3
"been dragged"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
346
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
2
semicolonCount
0
flaggedSentences
1
totalSentences
284
ratio
0.004
matches
0
"The victim’s shoes—cheap trainers—had grey grit on the soles."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1937
adjectiveStacks
0
stackExamples
(empty)
adverbCount
59
adverbRatio
0.030459473412493547
lyAdverbCount
0
lyAdverbRatio
0
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
284
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
284
mean
9.21
std
6.71
cv
0.728
sampleLengths
0
16
1
15
2
8
3
9
4
9
5
6
6
6
7
11
8
18
9
8
10
7
11
11
12
18
13
6
14
4
15
3
16
1
17
17
18
9
19
20
20
12
21
19
22
31
23
9
24
1
25
6
26
3
27
6
28
3
29
13
30
16
31
20
32
6
33
27
34
7
35
14
36
8
37
5
38
14
39
9
40
10
41
7
42
14
43
16
44
5
45
13
46
8
47
14
48
9
49
11
45.41%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
13
diversityRatio
0.26501766784452296
totalSentences
283
uniqueOpeners
75
0.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
0
totalSentences
207
matches
(empty)
ratio
0
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
36
totalSentences
207
matches
0
"Her torch cut a white"
1
"He looked too neat for"
2
"It sat in her palm"
3
"He swallowed his questions and"
4
"Her wrist felt colder down"
5
"Her colleague waited by the"
6
"She held a small notepad,"
7
"Her shoes stuck for a"
8
"His jacket had been unzipped"
9
"She stared at the cut,"
10
"Its casing carried a patina"
11
"It pointed toward the tracks."
12
"Her knees cracked and the"
13
"She turned it palm-up."
14
"His hands never stopped moving,"
15
"It shimmered in the beam,"
16
"She walked the curve, slow."
17
"It made a rough circle"
18
"She leaned in close enough"
19
"They formed small symbols, repeated,"
ratio
0.174
22.80%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
181
totalSentences
207
matches
0
"The escalator had stopped years"
1
"Detective Harlow Quinn took the"
2
"Water dripped somewhere below, slow"
3
"The air thickened with cold"
4
"Her torch cut a white"
5
"Camden roared up on the"
6
"A uniform waited at the"
7
"He looked too neat for"
8
"Quinn pulled a knucklebone from"
9
"It sat in her palm"
10
"A line of tiny scratches"
11
"The uniform’s eyes stayed on"
12
"Quinn kept walking."
13
"He swallowed his questions and"
14
"The tiled walls had peeled"
15
"Posters clung in tatters: smiling"
16
"The corridor opened into a"
17
"Lanterns hung from cables, throwing"
18
"The market buzzed like a"
19
"Quinn’s watch strap creaked as"
ratio
0.874
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
207
matches
(empty)
ratio
0
89.29%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
80
technicalSentenceCount
6
matches
0
"Two forensics techs in white coveralls stood beside a stall that sold jars of something cloudy."
1
"Detective Constable Imani Patel had her hair tied back and her sleeves rolled to the elbow as if she’d come prepared to scrub blood off the world."
2
"The pads of his fingers showed faint burns, like he’d handled something that held heat longer than it should."
3
"The needle jittered, skittering as if it wanted to bite through plastic, then steadied again toward the darkness beyond the platform edge."
4
"The air rippled in a vertical seam, a faint distortion that made the tunnel bricks look like they’d been painted on wet paper."
5
"His hands never stopped moving, stringing something that glinted like fishbones."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
10
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
3
fancyCount
1
fancyTags
0
"Quinn muttered (mutter)"
dialogueSentences
72
tagDensity
0.042
leniency
0.083
rawRatio
0.333
effectiveRatio
0.028
83.0102%