NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HDE2SFSP3ZF7BYWFQE943
Run Details
Model:
GPT-6 Sol
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
56.2s
Cost:
$0.033490
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
95.94%
AI-ism adverb frequency
(details)
80.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
85.80%
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)
33.33%
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)
87.72%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
96.40%
Em-dash & semicolon overuse
(details)
94.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
67.34%
Sentence opener variety
(details)
45.66%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
52.47%
Subject-first sentence starts
(details)
100.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
91.2887%
Overall
Model input
System
You are an expert novelist with a gift for vivid, immersive prose. You write in tight third-person limited point of view with a strong narrative voice. Your prose is clean, precise, and engaging — you favor strong verbs, concrete details, and natural-sounding dialogue. You will be given a story bible (codex) containing canonical details about characters, locations, items, and lore. Use these details to ground your writing in the established world. Stay consistent with the codex. Write only the prose of the scene. Do not include titles, chapter headings, markdown formatting, or any commentary before or after the scene.
User/Human
<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> 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.
Model response
Messages
Meta
AI
Detective Harlow Quinn reached the
disused Tube entrance at six seventeen, twelve minutes after the first call and forty-three minutes before the next train was due on the live line running somewhere beyond it.
The iron gates beneath Camden
High Street had
been chained
shut since before she joined the Met.
Now the chain lay in
two neat pieces on the pavement, and a uniformed constable stood between the gates trying not to look down the stairs. “Victim’s below, ma’am,” he said. “Platform level.”
Quinn showed him her warrant
card. “Who found him?” “Maintenance crew. They were checking a power fault in the adjoining tunnel.” “Power fault when?” “Started at four twenty.”
She looked at the cut
chain. The exposed metal was bright, with no trace of rust. Beside it, a chalk mark on the pavement showed where someone had found a small object. “What was there?” “Bone. Or something made of bone. Scenes of crime have it.”
Quinn took out her phone
and made a note.
A cut chain and a
bone token were an odd combination for a derelict station, though Camden supplied plenty of oddities before breakfast.
The stairwell smelled of wet
plaster and electrical dust.
Her shoes scraped through grit
as she descended, one hand brushing the tiled wall for balance.
Someone had painted over the
old station name, but the raised outlines of the letters still showed beneath the cream emulsion.
Halfway down, a newer smell
reached her: hot oil, ginger, and the sharp sweetness of burned sugar. At the bottom, temporary lamps lit a platform far wider than the entrance suggested.
Stalls stood in two rows
along it, their canvas awnings collapsed or half-stripped.
A cage full of empty
glass jars swung
gently
from a hook.
Crimson fabric hung from a
rail beside a crate of chipped
porcelain
.
A hand-lettered sign offered REPAIRS
WHILE YOU WAIT; beneath it sat a workbench scattered with springs small enough for watches. Quinn stopped. “Who set all this up?” “Best guess is an illegal market,” said DS
Patel
, coming toward her from the far end of the platform.
He wore shoe covers over
his boots and carried his notebook open. “The maintenance lads said this was empty when they last checked it. About three weeks ago.” “And they’ve been through here since?” “Not through the platform. Access hatch in the service tunnel.”
A Scene of Crime officer
moved between the stalls with a camera. Two uniforms guarded the stairs and the tunnel mouth. Otherwise the platform
was deserted
, though cups sat on tables and a kettle still held lukewarm water.
Quinn pictured people leaving in
a hurry, gathering what they could carry and abandoning the rest. The place had the close, recently occupied
warmth
of a room after a party.
Patel
led her past a stall whose shelves held corked bottles packed in straw.
She read the labels as
she passed. Some bore prices; others carried marks she couldn’t identify. Beside them, a ledger lay open to a page of dates and initials. “Name on the body?” she asked. “Wallet says Daniel Armitage. Forty-eight. Works for London Underground, contracted security. His supervisor confirms he was on duty last night at the Camden Town depot. Didn’t clock out.”
They reached the body near
the old platform edge. Armitage lay on his side in a high-visibility jacket, one arm extended across a strip of dark
mosaic
flooring.
His face had gone grey
under the portable lights. A single puncture marked his neck below the jaw, its edges blackened. Blood had run across the tiles and collected against the base of a metal support. Quinn crouched, careful to keep outside the marked perimeter. “A stab wound?” “Pathologist’s on the way. Could be. No weapon found.”
Patel
nodded toward the abandoned stalls. “Looks like he came across this operation, someone killed him to keep it quiet, and they cleared out.” “He came across it from where?” “Service tunnel. His access card was used at the depot door at four eleven.” Quinn checked the worn leather
watch
on her left wrist. “The fault began at four twenty.” “Maybe they tripped something during the struggle.” She studied Armitage’s outstretched hand. Dirt packed beneath his nails, but his fingertips were clean. There was a pale circle on his thumb, as though he’d pressed it against a small, round object. Near his hand lay one brass screw. Beyond it, three more sat in a tidy line. “What do you make of those?” “From one of the stalls. Whole place is falling apart.” Quinn glanced toward the nearest stall.
Its frame was secured with
hex bolts, not screws. The workbench across the aisle held watchmaking tools, but its trays looked undisturbed.
She leaned closer without touching
anything. The four screws were the same size, their slots facing up. “Who found him exactly here?” “Maintenance engineer called Leung. His partner waited at the tunnel door. Leung says he came round that partition, saw Armitage, and backed out.” Quinn followed
Patel
’s gesture. A folding screen of dark wood and cloudy glass stood ten feet from the body. From the tunnel mouth, it blocked the view of the platform edge.
If Leung had come around
it, he would have passed the stalls, the cups, the ledger, and a row of coats hanging from pegs. “Was the screen in that position when he arrived?” “He says so.” “Get it in his statement.”
Patel
wrote it down. “You think he moved it?” “I think I’d like to know what he saw.” A woman’s voice rose at the far end of the platform. “I’ve already told you. I can identify the ledger.” Quinn turned. A small red-haired woman in round glasses stood beside a constable, clutching the strap of a worn leather satchel. Books bulged against its seams.
She wore a green coat
over a museum staff lanyard. “Who’s that?” “Eva Kowalski. She was stopped at the entrance about five minutes after the crew called it in.”
Patel
lowered his voice. “Says she works in the British Museum’s restricted archives and came to meet a dealer. Won’t tell us which one.” “Why is she still on the platform?” “She insisted there was something we’d need to see. I kept her here until you arrived.” Quinn rose. “Miss Kowalski?” Eva pushed her curly hair behind her left ear.
Her green eyes moved past
Quinn to the body, then away. “I wasn’t here when it happened.” “I didn’t ask if you were.” “No. Sorry.”
She tightened her grip on
the satchel strap. “I came for a book. Someone said it would be at the Market this morning.” “Which book?” “A medieval collection of burial rites.” “Someone?” Eva’s lips pressed together. “I don’t know their name.”
Patel
made a small sound in his throat. Quinn ignored him. “You said you could identify the ledger.” “Not the people in it. The writing. Some of the entries are in Latin, and some are in a cipher I’ve seen in other collections. It might help you find who runs the place.” “Why volunteer?” Eva looked toward Armitage again. “Because he’s dead.”
It was an answer, if
not a complete one. Quinn studied her for a moment, then looked down at Eva’s shoes. Their soles were dry. Grit clung to the toes, the same pale grit as on the entrance stairs, but there was no black dust from the service tunnel. The constable had her arrival time; cameras on the street might confirm it. “Wait upstairs,” Quinn said. “We’ll take a statement.” Eva opened her mouth, hesitated, then said, “Please don’t let anyone move the compass.” “What compass?” “On the workbench. Small brass one. Green on the edges.”
Her hand rose toward her
hair again. “It’s delicate.”
Patel
glanced at Quinn. “She’s trying to claim something, I reckon.” “I’m not claiming it,” Eva said. “I’m telling you it needs to stay where it is.” Quinn sent her up with the constable. Eva looked back once at the workbench, then disappeared into the stairwell.
Patel
waited until she was out of earshot. “There’s a compass over there. Needle’s broken. I’ve got it logged for collection.” “Show me.” The workbench stood beneath a strip light that
flickered
every few seconds. Brass filings glittered on its scarred surface. There were clamps, a loupe, a soldering iron gone cold, and a small compass set apart from the tools. Verdigris mottled its casing. Fine marks had
been etched
around the face, too regular to be decoration. The needle pointed northwest, toward the brick wall behind the bench. “Broken?” Quinn asked.
Patel
took his pen from his pocket and held it near the compass. “It won’t follow the magnet in my pen.” “Is there a magnet in your pen?” “No.” He grinned. “That’s what the scene officer said, anyway. He used the one from his kit. Nothing.” Quinn looked at the needle, then at the wall. A rectangular patch of brickwork differed from the rest: cleaner mortar, a faint seam down either side. An old electrical cabinet might have
been sealed
behind it, though there was no visible latch. “Did Armitage have a radio?” “On his belt. Battery dead.” “His phone?” “In his pocket. Also dead. Same with the maintenance crew’s torches when they got near this end. They had spares.” The strip light blinked overhead. Quinn looked back toward the body. The trail of blood ran against the metal support; its narrow end pointed away from the apparent service-tunnel approach. A broad smear crossed the
mosaic
at shoulder height, as if someone had dragged Armitage a short distance and settled him there.
She walked back and stood
where Leung had supposedly first seen him. From that angle, the victim’s bright jacket was clearly visible past the screen. So were the screws. But the stall closest to him hid the workbench entirely.
Patel
joined her. “What?” “Armitage’s access card got him into the depot at four eleven. Where was he before that?” “His supervisor said he left his post at three fifty to investigate a report of trespassers.” “Who reported them?”
Patel
checked his notes. “Anonymous call to control.” “Find the recording.” Quinn moved beside the screen and studied its feet. One had dragged a clean arc through the dust. Someone had shifted it recently, after the platform emptied enough for dust to settle. That could have been Leung, or the killer, or Armitage himself. She returned to the body. The wound in Armitage’s neck was dark, but the blood beneath him was too little for the journey
Patel
’s theory required.
If he’d been attacked in
the service tunnel and dragged around the screen, she would have expected a trail.
Instead, most of the blood
lay where he was. “He wasn’t killed because he discovered the market,” she said. “He came here to meet someone.”
Patel
’s eyebrows rose. “Security guard answers a trespass call and gets invited to shop?” “Look at his jacket. He’s wearing it unzipped. His radio’s turned off, not just dead—the switch is at zero. His card got used at the depot door nine minutes before the fault, but that only tells us he went through that door. Maybe he came by another entrance first.” “Then why go back out through the depot?” “Perhaps he needed the card logged. Or perhaps someone else used it.” Quinn pointed toward his hand. “Those screws were put there. They’re not from the stalls nearby.”
Patel
crouched. “Could be from something he broke.” “Four of them. Same size. Set in a line. Someone opened a small case.” She looked toward the compass.
Its brass casing had a
flat base, with four dark holes at the corners. She crossed to the bench, stopping short of touching it. Under the green corrosion, brighter metal showed around each hole. The case had
been unscrewed
recently, then closed again without the screws. The needle still pointed to the wall. “Get a photograph of the underside,” Quinn told the scene officer. “And the wall behind it. Don’t move the compass yet.”
Patel
came over. “You think Armitage took it apart?” “Someone did. And those screws were beside his hand when he died.” “Why leave them?” “He may have dropped them. Or he wanted us to notice.” Quinn looked down the platform. The stalls nearest the stairs had
been stripped
of valuables. This one still held its tools, and the compass had
been left
in plain sight. “Whoever cleared this place had time to take the cash boxes, but missed the one thing Eva Kowalski wanted protected.” “Or she wants it back and thought telling us it was dangerous would make us careful.” “Maybe.” A low vibration passed through the platform.
Patel
glanced toward the live tunnel. “Train?” “Too early.” Quinn checked her
watch
. Six thirty-four. The vibration came again. Dust sifted from the mortar seam behind the workbench. The compass needle
trembled
, then steadied toward the wall. The scene officer lowered his camera. “Did you see that?” “Yes.” Quinn kept her voice level. “Everyone step back from the wall.”
Patel
stared at her. “There’s a train line on the other side.” “There may be.” Quinn pointed at the seam. “Get station plans. I want to know what’s behind those bricks.” As the officer moved away, Quinn noticed a pale scratch on the floor beneath the bench. It ran from one end of the wall to the other, stopping at an iron plate set flush into the tiles. She had mistaken it for a cable channel.
Now she saw parallel scrape
marks around the plate, and a fresh crescent of brass embedded in the grout beside it. She crouched. The crescent matched the compass casing. Someone had wedged it into the plate’s narrow slot, perhaps to pry it open. Armitage had unscrewed the compass, or watched someone do it, and whatever they’d tried had cost him his life.
Patel
knelt beside her. “That plate wasn’t on the station plans we got.” “Then they aren’t the right plans.” Behind the bricks came a soft metallic click. Quinn stood at once, putting a hand out to hold
Patel
back. The seam widened by the thickness of a fingernail. Cold air flowed through it, carrying the smell of rain on stone. The lamps brightened, then dimmed. From the stairs came the constable’s voice,
calling that every
phone on the platform had lost signal. Quinn watched the seam. Someone
was opening
it from the other side,
slowly
enough to listen for a reaction. She drew her torch and aimed it at the gap. “Metropolitan Police,” she said. “Step out where I can see you.” The click stopped. For a moment there was only the hum of the failing lights.
Then a small brass screw
rolled out from under the wall and came to rest against the toe of her shoe.
created_at
"2026-09-23T16:26:07.841Z"
9/23/2026, 4:26:07 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3051
moderation_latency
(null)
generation_time
56122
tokens_prompt
896
tokens_completion
3834
native_tokens_prompt
835
native_tokens_completion
3182
native_tokens_completion_images
0
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
service_tier
"default"
usage
0.03349
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790180767-JANnuFeCTmBz454oFNLL"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790180767-jBTfBmmizKpcNCpeKZ0u"
upstream_id
"resp_03d29659773e2135016ab3fd9ff79487d1af7653d934807193"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_03d29659773e2135016ab3fd9ff79487d1af7653d934807193"
is_byok
false
latency
460
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.03349
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
19
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
106
tagDensity
0.179
leniency
0.358
rawRatio
0
effectiveRatio
0
95.94%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2464
totalAiIsmAdverbs
2
found
0
adverb
"gently"
count
1
1
adverb
"slowly"
count
1
highlights
0
"gently"
1
"slowly"
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)
85.80%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2464
totalAiIsms
7
found
0
word
"porcelain"
count
1
1
word
"warmth"
count
1
2
word
"mosaic"
count
2
3
word
"flickered"
count
1
4
word
"etched"
count
1
5
word
"trembled"
count
1
highlights
0
"porcelain"
1
"warmth"
2
"mosaic"
3
"flickered"
4
"etched"
5
"trembled"
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
160
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
2
hedgeCount
0
narrationSentences
160
filterMatches
0
"watch"
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
246
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
50
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2463
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
29
unquotedAttributions
0
matches
(empty)
33.33%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
77
wordCount
1607
uniqueNames
14
maxNameDensity
1.87
worstName
"Quinn"
maxWindowNameDensity
4
worstWindowName
"Quinn"
discoveredNames
Harlow
1
Quinn
30
Tube
1
Camden
2
High
1
Street
1
Met
1
Patel
20
Scene
1
Crime
1
Armitage
7
Leung
3
Eva
7
Six
1
persons
0
"Harlow"
1
"Quinn"
2
"Patel"
3
"Armitage"
4
"Leung"
5
"Eva"
places
0
"Camden"
1
"High"
2
"Street"
3
"Six"
globalScore
0.567
windowScore
0.333
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
115
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
2463
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
246
matches
0
"calling that every"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
119
mean
20.7
std
18.82
cv
0.91
sampleLengths
0
77
1
7
2
9
3
12
4
3
5
4
6
35
7
11
8
32
9
63
10
71
11
7
12
47
13
6
14
10
15
68
16
43
17
6
18
28
19
64
20
12
21
33
22
6
23
14
24
16
25
7
26
49
27
6
28
10
29
45
30
5
31
23
32
55
33
9
34
3
35
5
36
9
37
9
38
20
39
36
40
2
41
41
42
7
43
16
44
4
45
26
46
6
47
25
48
2
49
6
87.72%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
8
totalSentences
160
matches
0
"been chained"
1
"was deserted"
2
"been etched"
3
"been sealed"
4
"been attacked"
5
"been unscrewed"
6
"been stripped"
7
"been left"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
1
totalVerbs
264
matches
0
"was opening"
96.40%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
4
flaggedSentences
4
totalSentences
246
ratio
0.016
matches
0
"A hand-lettered sign offered REPAIRS WHILE YOU WAIT; beneath it sat a workbench scattered with springs small enough for watches."
1
"Some bore prices; others carried marks she couldn’t identify."
2
"The constable had her arrival time; cameras on the street might confirm it."
3
"The trail of blood ran against the metal support; its narrow end pointed away from the apparent service-tunnel approach."
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1614
adjectiveStacks
1
stackExamples
0
"small red-haired woman"
adverbCount
47
adverbRatio
0.029120198265179677
lyAdverbCount
10
lyAdverbRatio
0.006195786864931847
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
246
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
246
mean
10.01
std
6.62
cv
0.661
sampleLengths
0
34
1
17
2
26
3
5
4
2
5
6
6
3
7
12
8
3
9
4
10
6
11
10
12
16
13
3
14
11
15
9
16
23
17
9
18
16
19
21
20
17
21
14
22
13
23
12
24
12
25
20
26
2
27
5
28
19
29
12
30
16
31
6
32
10
33
12
34
9
35
17
36
16
37
14
38
14
39
7
40
9
41
13
42
6
43
28
44
9
45
19
46
9
47
12
48
15
49
9
67.34%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
6
diversityRatio
0.4186991869918699
totalSentences
246
uniqueOpeners
103
45.66%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
2
totalSentences
146
matches
0
"Instead, most of the blood"
1
"Then a small brass screw"
ratio
0.014
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
23
totalSentences
146
matches
0
"She looked at the cut"
1
"Her shoes scraped through grit"
2
"He wore shoe covers over"
3
"She read the labels as"
4
"They reached the body near"
5
"His face had gone grey"
6
"She studied Armitage’s outstretched hand."
7
"Its frame was secured with"
8
"She leaned closer without touching"
9
"She wore a green coat"
10
"Her green eyes moved past"
11
"She tightened her grip on"
12
"It was an answer, if"
13
"Their soles were dry."
14
"Her hand rose toward her"
15
"She walked back and stood"
16
"She returned to the body."
17
"She looked toward the compass."
18
"Its brass casing had a"
19
"She crossed to the bench,"
ratio
0.158
52.47%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
119
totalSentences
146
matches
0
"Detective Harlow Quinn reached the"
1
"The iron gates beneath Camden"
2
"Quinn showed him her warrant"
3
"She looked at the cut"
4
"The exposed metal was bright,"
5
"Quinn took out her phone"
6
"A cut chain and a"
7
"The stairwell smelled of wet"
8
"Her shoes scraped through grit"
9
"Someone had painted over the"
10
"Halfway down, a newer smell"
11
"Stalls stood in two rows"
12
"A cage full of empty"
13
"Crimson fabric hung from a"
14
"A hand-lettered sign offered REPAIRS"
15
"He wore shoe covers over"
16
"A Scene of Crime officer"
17
"Quinn pictured people leaving in"
18
"The place had the close,"
19
"Patel led her past a"
ratio
0.815
100.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
5
totalSentences
146
matches
0
"Now the chain lay in"
1
"Otherwise the platform was deserted,"
2
"If Leung had come around"
3
"If he’d been attacked in"
4
"Now she saw parallel scrape"
ratio
0.034
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
74
technicalSentenceCount
0
matches
(empty)
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
19
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
9
fancyCount
0
fancyTags
(empty)
dialogueSentences
106
tagDensity
0.085
leniency
0.17
rawRatio
0
effectiveRatio
0
91.2887%