NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX40RMVWYDRTJNBREK3KK9AC
Run Details
Model:
GPT-5.6 Sol (Reasoning)
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
1m 4s
Cost:
$0.099180
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
95.80%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
85.31%
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)
100.00%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
94.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
50.50%
Sentence opener variety
(details)
72.46%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
53.48%
Subject-first sentence starts
(details)
0.00%
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)
89.4962%
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="4417" name="Tomás Herrera" aliases="Tommy, Tomás, Herrera" pronouns="he/him" species="Human" storyRole="Support"> <eyeColor>warm brown</eyeColor> <hair>short curly dark brown</hair> <height>5'10"</height> <age>29</age> <skinTone>olive skin</skinTone> <scar>scar running along his left forearm from a knife attack</scar> <medallion>Saint Christopher medallion around his neck</medallion> <birthplace>Seville, Spain</birthplace> <description>A former paramedic who provides off-the-books medical care for the clique.</description> <backstory>Born in Seville, Spain. He moved to London to work for the NHS but lost his license after administering unauthorized treatments to supernatural patients.</backstory> </character> <location id="854" name="The Raven's Nest" aliases="the Nest, Raven, Silas' bar" realm="Earth"> <signColor>distinctive green neon sign above the entrance</signColor> <secretRoom>hidden back room accessible through a bookshelf, used for clandestine meetings</secretRoom> <description>A dimly lit bar in Soho, London. The walls are covered with old maps and black-and-white photographs.</description> </location> <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> </codex> Write a fully fleshed out scene of at least 1000 words in the thriller genre. A detective is pursuing a suspect through rain-soaked city streets at night. The chase takes them from the street level down into an underground market. The detective must decide whether to follow the suspect into unfamiliar and potentially dangerous territory. 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
The man came out of
the Raven’s Nest at 11:43 p.m. with blood on his cuff and one hand clamped over the pocket of his coat.
Detective Harlow Quinn watched him
in the warped reflection of a shuttered kebab shop across the street.
Rain slashed through the green
neon above the bar’s entrance, turning RAVEN’S NEST into a trembling smear. The man paused beneath it, head lowered, short dark curls shining with water. Tomás Herrera. Twenty-nine. Former NHS paramedic.
License revoked two years ago
for administering substances nobody at the tribunal could identify. Since then, he had become a ghost with a medical bag, appearing wherever the dead refused to stay politely dead.
Quinn had spent six weeks
trying to catch him carrying something more incriminating than gauze. Herrera looked left.
Quinn looked down at her
phone. He looked right.
The muscles along his jaw
tightened. Then he ran.
Quinn was across the street
before the first cab horn finished blaring. Her shoes struck standing water, cold spray climbing her trouser legs.
Herrera shouldered past a pair
of smokers and cut east into the narrow lane beside the bar.
Quinn followed, one hand inside
her coat, fingers brushing the grip of her warrant-issued baton. “Herrera!” He glanced back. Warm brown eyes, wide but not surprised.
That bothered her more than
the running.
He vaulted a stack of
beer crates.
Quinn went around them, clipped
one with her knee, and heard bottles crash behind her.
The alley reeked of wet
cardboard, sour hops, and the oily breath of extractor fans.
Herrera had twenty years less
mileage in his legs, but he carried a black leather medical bag that slapped against his thigh. It slowed him. Not enough. He burst onto Wardour Street, dodging a cyclist in a yellow poncho. Brakes squealed. The cyclist shouted. Quinn hit the crossing at an angle, caught the bonnet of a stopped taxi with her palm, and swung herself around it. “Herrera, stop!” He did not. The pocket of his coat bounced heavily. Whatever sat inside it was too dense for a phone and too small for a weapon. Quinn had seen him receive it in the Raven’s Nest from a woman whose face never appeared clearly on camera. The woman had arrived empty-handed, gone through the bar’s bookshelf into a room the owner claimed did not exist, and emerged without Herrera. Herrera had followed nine minutes later, cuff bloodied, carrying the
weight
in his pocket. Probable cause was thin. Instinct was not evidence. But instinct had kept Quinn alive for eighteen years.
It had failed Morris only
once. Herrera cut across Shaftesbury Avenue against the lights. A bus bore down on him, its red flank
gleaming
under the rain.
He slipped through the gap
between bus and bollard. Quinn stopped short as the vehicle roared past, warm diesel breath buffeting her coat. For half a second Herrera stood framed on the far pavement.
He met her eyes across
the wet road.
His hand rose to his
throat. Something silver flashed between his fingers—a medallion, round and worn.
Then he turned and disappeared
into the crowd. “Damn it.” Quinn checked her
watch
. The cracked leather strap had darkened with rain. 11:47. She ran north. Herrera’s route made no sense if he meant to lose her.
He avoided the bright crush
of Leicester Square and chose narrow streets with long sight lines.
He was fast, but he
kept looking back, almost as if he needed to know she was still there. A lure, then. Quinn slowed enough to draw her phone. Two taps brought up the covert surveillance channel. “Quinn to Control. Suspect mobile on foot, northbound from Soho. Tomás Herrera. Request local units to—” Static swallowed the rest.
She stopped under a pharmacy
awning and looked at the screen. No signal. In central London. A second later the display went black. The battery had been at seventy-two percent. Ahead, Herrera crossed under a streetlamp. The light
flickered
as he passed. Quinn watched the darkness move after him, lamp by lamp, a ripple flowing north.
Her dead phone felt suddenly
heavy. Three years earlier, Morris had called her from a service tunnel beneath Euston.
His last words had arrived
through the same dry crackle. Don’t follow the lights, Harlow. They had found his blood, his torch, and one shoe. No body. No explanation for the frost coating the tunnel walls in August. Quinn put the phone away and resumed the pursuit. By midnight they were in Camden, the rain driving hard enough to empty the pavements. Herrera crossed between crawling cars, ducked beneath a railway arch, and ran past locked market stalls striped in corrugated metal. Quinn’s lungs had begun to burn. Water worked down the back of her collar.
Her closely cropped hair offered
no protection, and every drop found skin. Herrera stumbled near a boarded shopfront. Quinn gained ten metres.
He caught himself with his
left hand. His sleeve dragged up, exposing a pale scar along his forearm, long and ragged. He looked over his shoulder again. “Listen to me,” he called. The Spanish cadence in his voice survived years of London. Seville, according to his file. Son of a nurse, top marks in emergency medicine, no criminal record until compassion ruined his career. “Stop and I’ll listen,” Quinn said. “If I stop, she dies.” “Who?” Herrera ran on. Quinn followed him through a gap in a construction fence. Beyond it lay a sunken service road
gleaming
with rain. A concrete stairway descended beside a wall furred with moss and old posters. At the bottom stood a steel door marked with the roundel of an Underground station that had never appeared on any current map. Herrera reached it and dragged something from his coat pocket. Not dense, Quinn realised. A handful of small objects knocking together. Bones. He selected a yellowed disc drilled through the centre and pressed it into a narrow slot beside the door. Metal groaned. The steel door opened inward. Warm air breathed out, carrying incense, scorched sugar, damp stone, and the copper stink of blood. Herrera slipped through. The door
began to
close. Quinn hit it with her shoulder. Pain jarred along her collarbone, but the mechanism yielded. She forced herself through and found Herrera waiting on the other side. He stood three paces away in a tiled passage, bent over with one hand on his knee. Water ran from his curls. His medical bag rested at his feet. The silver Saint Christopher medallion lay against his olive skin where his shirt had come open. He held another bone token between finger and thumb. “You should go back,” he said. Quinn straightened. “You first.” “You don’t have a token.” “I have you.” “That is not how this works.” “No, this is how it works. You ran from a police officer. You’re carrying suspected human remains. There’s blood on your clothes.” “The blood belongs to someone who is still alive. For now.” Quinn studied him. His breathing was hard, but his hands were steady. Paramedic’s hands. No tremor, no panic. The medical bag bore fresh scratches, as if claws had raked across the leather. Behind Herrera, the passage sloped downward. Weak bulbs glowed in wire cages along the walls. Water ticked from cracked tiles into a black gutter. Far below came the murmur of many voices, the chime of metal, and
something like a child laughing backward
. Quinn’s skin tightened across her shoulders. “What is this station?” she asked. Herrera’s gaze shifted past her to the steel door. “One that closed for a reason.” “What’s down there?” “You have spent three years asking that question.” The passage
seemed to
narrow around her. Quinn took one
measured
step forward. “Careful.” “I know about Morris.” She struck before she decided to. Herrera blocked badly. Her forearm caught his chest and drove him against the tiled wall. The token fell, clicked once on the floor, and vanished into the gutter. Quinn pinned him by the throat, her right hand reaching beneath her coat. “Say his name again.” Herrera’s face tightened, but he did not fight her. “DS Daniel Morris. Your partner. Missing, presumed dead.” “Where did you hear it?” “The Market keeps records.” “What market?” “The one beneath us.” A bell rang somewhere down the passage. Herrera went still. Not the stillness of surrender. The stillness of prey. The bulbs dimmed in sequence from below, one after another. With each extinguished light, the distant murmur faded. Stalls closing. Conversations ending. Quinn eased pressure on his throat. “What does that mean?” “It means they know someone entered without paying.” A wet scraping came from the dark. Quinn drew her baton. Herrera looked at it and gave a breathless, humourless laugh. “That will make them nostalgic.” The scraping came closer. He bent
slowly
, eyes on Quinn, and opened his medical bag. Inside lay sealed dressings, syringes, glass vials nested in foam, and instruments Quinn did not recognise. One resembled forceps fashioned from black antler. Another was a scalpel with a translucent blade. Herrera removed a small bottle filled with grey powder. “Drop the baton,” he said. “No.” “It smells iron.” “It is steel.” “That’s worse.” A shape passed through the pool of light at the bend below.
Too tall to fit the
tunnel, it folded as it moved, joint after joint drawing inward with the sound of green branches breaking. Quinn’s grip tightened. Herrera flung the grey powder across the passage. The shape recoiled. A hiss rolled up the tunnel, deep enough to vibrate in Quinn’s teeth. The caged bulbs flared blue. For an instant she saw a white face stretched over a narrow skull, no eyes, and a mouth crowded with copper pins.
Then darkness snapped back into
place. Herrera seized Quinn’s sleeve. “Run.” She tore free on reflex. The thing rounded the bend. Quinn ran. Herrera snatched up his bag and followed. They hit the steel door together. Quinn found no handle, only the slot where the bone token had gone. She shoved at the metal. It did not move. “Open it,” she said. “My token is in the drain.” “You had more.” “Entry tokens. Not exit.” The scraping
quickened
behind them. Quinn turned, baton raised. “Convenient.” Herrera searched the wall, fingers moving over the cracked grout. “If you want to arrest me, Detective, survive the next thirty seconds.” A section of tile clicked under his palm. A narrow maintenance hatch sprang open at knee height. He dropped to the floor and dragged the medical bag through. Quinn looked down the passage. The thing unfolded beneath the nearest bulb. Its blank face turned toward her. Copper pins shifted in its mouth, clicking together. A black strip of cloth hung from one long wrist. No. Not cloth. A tie. Navy blue, marked with a narrow silver stripe. Morris had worn one like it the night he vanished. The creature lifted its hand. Something glinted between two fingers: a battered Metropolitan Police warrant card. Quinn forgot the hatch. Forgot Herrera. Forgot the rain and the chase and every sensible rule that had carried her through eighteen years. “Morris?” The thing smiled around its pins. Herrera’s hand shot from the hatch and caught her ankle. He yanked. Quinn fell hard, her sharp jaw striking the floor. Pain burst white behind her eyes. The creature lunged as Herrera dragged her backward. Its fingers closed on empty air above her face, nails scraping sparks from tile. Quinn kicked free of its reach and crawled into the hatch. Herrera slammed the panel shut. A blow struck the other side, bowing the metal inward. Dust showered over them. They crouched in a narrow duct, shoulder to shoulder. Quinn tasted blood. Her baton
was gone
. Beyond the hatch, claws
traced
slow circles through steel. Herrera clicked on a penlight. Its beam lit his face from below. “You saw the warrant card,” he whispered. Quinn wiped blood from her chin. “Where does this lead?” “To the Market.” “I thought that was the Market.” “That was the front door.” Another blow dented the hatch. Herrera started crawling. After two metres he glanced back. “You can stay here and wait for it to open the panel. Or you can follow me.” Quinn looked toward the sealed door behind them, imagining the wet Camden night on the other side. Backup would come eventually, if her last transmission had escaped the static. She could withdraw, gather a team, return with lights, weapons, maps. By then the full moon would have passed. Herrera’s file contained rumours: a market that moved every month, leaving behind nothing but bricked tunnels and people nobody remembered clearly. Ahead, the duct opened over a cavern filled with gold and violet light. Figures crowded between stalls under the abandoned station’s tiled arches. Some looked human. Others made no effort. Glass jars burned with trapped blue flames. Bundles of herbs twitched on hooks. A woman in a red veil weighed teeth on a brass scale while a horned customer counted coins cut from fingernails. Herrera lowered himself through the opening. Quinn remained in the duct. Eighteen years of procedure told her to retreat. Three years of unanswered questions pulled the other way. Morris’s warrant card flashed again in her mind, held delicately between fingers too long to be human. Below, Herrera looked up. “I am not your enemy,” he said. “People who run usually are.” “I wasn’t running from you.” The hatch boomed behind her. One hinge tore loose. Quinn checked her worn leather
watch
. The second hand had stopped at midnight. She slid feet-first toward the light. Herrera caught her as she dropped. The instant her shoes touched the platform, every voice in the Veil Market fell silent. Hundreds of faces turned toward her. Some had eyes. Quinn straightened to her full height, rainwater dripping from her coat, blood bright on her chin. She fixed Herrera with a hard brown stare. “You’re under arrest,” she said quietly. His mouth twitched. “Of course.” Above them, the maintenance hatch screamed open. Herrera lifted his medical bag. “Can we discuss that while moving?” Quinn looked at the impossible crowd, the shifting shadows, the tunnel mouths branching into blackness.
Somewhere in this place lay
an answer carrying her dead partner’s warrant card. She took Herrera by the arm. “Lead the way.”
created_at
"2026-07-09T18:03:15.211Z"
7/9/2026, 6:03:15 PM
model
"openai/gpt-5.6-sol-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2592
moderation_latency
(null)
generation_time
63988
tokens_prompt
914
tokens_completion
4061
native_tokens_prompt
810
native_tokens_completion
3171
native_tokens_completion_images
0
native_tokens_reasoning
96
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
0.09918
router
(null)
provider_responses
0
endpoint_id
"a54c5de0-89bf-4ad7-a212-cf977eed918a"
id
"resp_09d96646ee73d666016a4fe26352a0819596d7ca081afa9fef"
is_byok
false
latency
250
model_permaslug
"openai/gpt-5.6-sol-20260709"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1783620195-l12RcVTNd6fXQR7cBV4U"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620195-cHjldsFI7rRXb9D7iqfU"
upstream_id
"resp_09d96646ee73d666016a4fe26352a0819596d7ca081afa9fef"
total_cost
0.09918
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
9
adverbTagCount
1
adverbTags
0
"she said quietly [quietly]"
dialogueSentences
56
tagDensity
0.161
leniency
0.321
rawRatio
0.111
effectiveRatio
0.036
95.80%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2383
totalAiIsmAdverbs
2
found
0
adverb
"suddenly"
count
1
1
adverb
"slowly"
count
1
highlights
0
"suddenly"
1
"slowly"
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)
85.31%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2383
totalAiIsms
7
found
0
word
"weight"
count
1
1
word
"gleaming"
count
2
2
word
"flickered"
count
1
3
word
"measured"
count
1
4
word
"quickened"
count
1
5
word
"traced"
count
1
highlights
0
"weight"
1
"gleaming"
2
"flickered"
3
"measured"
4
"quickened"
5
"traced"
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
257
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
2
hedgeCount
2
narrationSentences
257
filterMatches
0
"watch"
hedgeMatches
0
"began to"
1
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
304
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
24
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2382
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
12
unquotedAttributions
0
matches
(empty)
33.33%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
119
wordCount
2114
uniqueNames
25
maxNameDensity
2.18
worstName
"Quinn"
maxWindowNameDensity
4
worstWindowName
"Quinn"
discoveredNames
Raven
2
Nest
2
Harlow
2
Quinn
46
Herrera
40
Wardour
1
Street
1
Morris
4
Shaftesbury
1
Avenue
1
Leicester
1
Square
1
London
2
Euston
1
August
1
Camden
2
Spanish
1
Underground
1
Saint
1
Christopher
1
Metropolitan
1
Police
1
Veil
1
Market
1
Water
3
persons
0
"Raven"
1
"Harlow"
2
"Quinn"
3
"Herrera"
4
"Morris"
5
"Saint"
6
"Christopher"
7
"Police"
8
"Market"
9
"Water"
places
0
"Wardour"
1
"Street"
2
"Shaftesbury"
3
"Avenue"
4
"Leicester"
5
"London"
6
"Euston"
7
"August"
8
"Camden"
globalScore
0.412
windowScore
0.333
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
168
glossingSentenceCount
1
matches
0
"something like a child laughing backward"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
2382
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
304
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
173
mean
13.77
std
14.61
cv
1.061
sampleLengths
0
26
1
47
2
40
3
15
4
3
5
6
6
3
7
6
8
3
9
55
10
1
11
10
12
7
13
62
14
2
15
39
16
2
17
3
18
66
19
14
20
8
21
9
22
6
23
44
24
19
25
16
26
8
27
2
28
13
29
3
30
46
31
3
32
15
33
16
34
4
35
16
36
7
37
7
38
26
39
6
40
23
41
5
42
23
43
9
44
61
45
6
46
4
47
27
48
5
49
32
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
257
matches
0
"was gone"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
385
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
1
semicolonCount
0
flaggedSentences
1
totalSentences
304
ratio
0.003
matches
0
"Something silver flashed between his fingers—a medallion, round and worn."
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
2120
adjectiveStacks
1
stackExamples
0
"Inside lay sealed dressings,"
adverbCount
46
adverbRatio
0.02169811320754717
lyAdverbCount
14
lyAdverbRatio
0.006603773584905661
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
304
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
304
mean
7.84
std
5.09
cv
0.65
sampleLengths
0
11
1
15
2
17
3
17
4
13
5
2
6
1
7
3
8
14
9
20
10
15
11
3
12
6
13
3
14
6
15
3
16
12
17
11
18
17
19
15
20
1
21
3
22
7
23
7
24
7
25
15
26
15
27
22
28
3
29
2
30
12
31
2
32
3
33
22
34
2
35
3
36
7
37
16
38
20
39
23
40
14
41
4
42
4
43
9
44
6
45
8
46
13
47
9
48
14
49
11
50.50%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
7
diversityRatio
0.31683168316831684
totalSentences
303
uniqueOpeners
96
72.46%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
5
totalSentences
230
matches
0
"Then he ran."
1
"Then he turned and disappeared"
2
"Too tall to fit the"
3
"Then darkness snapped back into"
4
"Somewhere in this place lay"
ratio
0.022
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
47
totalSentences
230
matches
0
"He looked right."
1
"Her shoes struck standing water,"
2
"He glanced back."
3
"He vaulted a stack of"
4
"It slowed him."
5
"He burst onto Wardour Street,"
6
"He did not."
7
"It had failed Morris only"
8
"He slipped through the gap"
9
"He met her eyes across"
10
"His hand rose to his"
11
"She ran north."
12
"He avoided the bright crush"
13
"He was fast, but he"
14
"She stopped under a pharmacy"
15
"Her dead phone felt suddenly"
16
"His last words had arrived"
17
"They had found his blood,"
18
"Her closely cropped hair offered"
19
"He caught himself with his"
ratio
0.204
53.48%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
187
totalSentences
230
matches
0
"The man came out of"
1
"Detective Harlow Quinn watched him"
2
"Rain slashed through the green"
3
"The man paused beneath it,"
4
"License revoked two years ago"
5
"Quinn had spent six weeks"
6
"Herrera looked left."
7
"Quinn looked down at her"
8
"He looked right."
9
"The muscles along his jaw"
10
"Quinn was across the street"
11
"Her shoes struck standing water,"
12
"Herrera shouldered past a pair"
13
"Quinn followed, one hand inside"
14
"He glanced back."
15
"That bothered her more than"
16
"He vaulted a stack of"
17
"Quinn went around them, clipped"
18
"The alley reeked of wet"
19
"Herrera had twenty years less"
ratio
0.813
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
230
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
86
technicalSentenceCount
2
matches
0
"Herrera had twenty years less mileage in his legs, but he carried a black leather medical bag that slapped against his thigh."
1
"Herrera’s file contained rumours: a market that moved every month, leaving behind nothing but bricked tunnels and people nobody remembered clearly."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
9
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
9
fancyCount
1
fancyTags
0
"he whispered (whisper)"
dialogueSentences
56
tagDensity
0.161
leniency
0.321
rawRatio
0.111
effectiveRatio
0.036
89.4962%