NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HM5QYK7ZJCAEYYH5A28Z0
Run Details
Model:
GPT-6 Sol
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
51.6s
Cost:
$0.029020
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
97.74%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
95.48%
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)
50.00%
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)
100.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
45.36%
Sentence opener variety
(details)
66.01%
Adverb-first sentence starts
(details)
87.33%
Pronoun-first sentence starts
(details)
59.01%
Subject-first sentence starts
(details)
24.75%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
97.37%
Dialogue tag variety (said vs. fancy)
(details)
90.7681%
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 in the grey
coat came out of the Raven’s Nest at 11:47 and stopped beneath its green neon sign to check the street.
Detective Harlow Quinn watched him
from across the road, rain dripping off the brim of her cap.
He looked left toward Wardour
Street, then right toward the cab idling at the corner.
He did not look at
the empty doorway behind him.
People who expected to be
followed always checked behind them.
People who knew how to
spot a tail checked everything else.
He put a hand inside
his coat, felt for something, and set off north.
Quinn waited until a bus
pulled between them before she crossed.
She had spent eighteen years
learning not to run too soon.
The man had left the
Nest twenty minutes after Tomás Herrera, the former paramedic whose name kept turning up beside hospital thefts, missing persons, and injuries no one wanted to explain. Herrera had gone east.
The man in grey had
gone north.
Quinn had chosen the man
in grey because he carried the canvas satchel Herrera had brought into the bar. At the first junction, the man glanced back.
Quinn turned into a shop
doorway and studied a display of phone cases through wet glass. In the reflection, she saw him keep walking.
She counted to five and
followed.
The satchel bumped against his
hip as he moved. Whatever was inside had
weight
.
A stolen shipment, perhaps, or
payment for one.
She had photographed Herrera handing
it over through the Nest’s front window, but the pictures showed two blurred figures beneath old maps and black-and-white photographs. Not enough for a warrant. Not enough even to persuade her sergeant that another night outside a Soho bar was worth the overtime.
She touched the worn leather
strap of her
watch
. 11:51. The man turned down a narrower street. Quinn followed past shuttered restaurants and bags of rubbish shining black in the rain. Ahead, he broke into a run. “Police,” she called. “Stop.” He ran harder. Quinn swore and went after him.
Her shoes struck puddles, cold
water spraying up the backs of her trousers.
He had twenty yards and
a head start, but he carried the satchel and kept turning to look at her. At the next corner he clipped a pedestrian’s shoulder. Quinn slipped past the man’s angry shout and saw the grey coat vanish into the crowd along Charing Cross Road. She pushed through umbrellas. A taxi sounded its horn as she crossed against the light. On the far pavement, the man looked back. For an instant the streetlight caught his face: narrow, clean-shaven, young enough to mistake speed for a plan. He ducked into an alley. Quinn keyed her radio. “Quinn. Foot pursuit, male suspect, grey coat, heading north from Soho toward Camden. I’ll give you a cross street when I have one.” Static hissed in her ear.
Then dispatch asked her to
repeat. The alley was empty except for a delivery rider sheltering under an awning. At the far end, grey flashed past a streetlamp. Quinn ran on, gave dispatch the street name, and received an acknowledgment that units were
being sent
. For ten minutes she kept him in sight by inches.
He cut across roads, doubled
behind a row of parked vans, and once pressed himself into the recess of a locked doorway. Quinn saw his shoe before she saw him.
He lunged past her, close
enough that she caught his sleeve, but the rain-slick cloth twisted out of her fingers.
He elbowed through a cluster
of late drinkers outside a pub. Quinn shoved after him, badge raised, too breathless to offer more than “Police, move.” Northbound traffic had slowed to a crawl. The man dodged between cars and disappeared into Camden’s side streets. Quinn followed the slap of his shoes on wet pavement. Her lungs burned. The satchel was still on his shoulder.
He needed what was in
it badly enough to keep carrying it. Three years ago, DS Morris had made the same calculation about a witness who ran from them. Morris had followed him alone into a service tunnel beneath a station.
By the time Quinn found
the tunnel, the witness
was gone
and Morris lay against the wall, conscious but unable to tell her what had happened.
He died in hospital before
dawn. The postmortem called it sudden cardiac arrest. Quinn had spent three years looking for a reason the witness had never appeared on any camera near the tunnel exit. The man in grey crossed a deserted forecourt ahead. Quinn forced herself faster.
He reached a chain-link fence
beside an old Tube entrance. Weeds grew between the paving stones. An enamel sign, half torn from its frame,
warned that the
station was closed.
He squeezed through a gap
where the fence met the wall. Quinn slowed, unwilling to lose him and unwilling to rush blind. She switched on her torch and followed him through. A set of stairs dropped beyond the boarded ticket windows. Water ran down the middle of the steps. “Stop where you are,” she called. Her voice came back thin and distant. At the bottom of the stairs, the man shoved through a steel gate. Quinn heard it clang, then the scrape of a bolt dragged home. She reached it seconds later. The gate held fast. Beyond it, her torch picked out a tiled corridor and the retreating swing of the satchel. She grabbed the bars. No lock she could see, only a sliding bolt on his side. “Open it.” He stopped at the end of the corridor. For a moment she thought he might answer.
Instead he drew something pale
from his pocket and held it against a patch of bare brick. A door opened where there had been no door. Quinn stared. She had been watching the wall. Its bricks had parted inward, quietly and neatly, leaving a narrow band of amber light. The man went through. The wall closed after him. Water dripped from her cap onto the back of her hand. She took her torch off the corridor, then put it back. The bricks stood flush. No frame, no handle. She pressed the radio at her shoulder. “Dispatch, suspect entered the closed station off the Camden forecourt. I’m at a locked service gate. Send the nearest unit to the entrance.” A burst of static answered. She tried again. This time a voice came through in fragments. “...unit... five minutes... position?” Quinn gave the entrance description twice. She did not mention the door. On her side of the gate, a small maintenance hatch sat low in the wall. Its padlock was new. She knelt and tested the hatch. It shifted under her hand. Behind it ran a crawl space, perhaps part of an old cable route, wide enough for a person without the satchel. She could wait for the units. They could secure the station, find another way in, and discover what trick had made a brick wall open.
Then a scream rose from
somewhere beyond it. It cut off
quickly
. Not a cry of alarm from the man she had chased. A woman’s voice, sharp with pain. Quinn took out her baton and broke the padlock with three hard blows. The sound cracked through the station. She pulled the hatch open and crawled into a passage that smelled of wet dust and warm electrical wire. Her shoulder scraped concrete. Ahead, light leaked through a metal grille. She reached it and looked out. The old platform had become a market. Stalls crowded the space beneath hanging bulbs and mismatched lanterns. Canvas awnings dripped into buckets. People moved between tables piled with bottles, clock parts, knives, jars of dark powder, and things Quinn could not name at a glance. A woman in a red raincoat held up a hand mirror that reflected the platform behind her but not her face. Near the track edge, a vendor weighed something wrapped in linen on brass scales. Quinn blinked rain from her lashes and looked for the grey coat. He stood beside a stall made from stacked wooden crates, the satchel open on the counter. A tall buyer
was inspecting
its contents. Between their shoulders Quinn glimpsed a row of stoppered glass vials cushioned in straw. The buyer lifted one toward the light. Something inside it moved, thick and silver. The man in grey looked toward her grille. Quinn pulled back. He had seen the broken padlock or heard her coming. She braced one foot against the wall and pushed. The grille gave, its rusted screws tearing free. It struck the platform with a crash that brought every nearby face around. “Metropolitan Police.” She stepped out, baton low at her side. “Nobody move.” Nobody did, for one beat.
Then the man in grey
snatched the satchel from the buyer and ran. Quinn went after him through the crowd. A vendor swept a tray of small bones off his counter before she could hit it. Someone seized her elbow; she tore free. She saw the grey coat ahead, passing under a faded sign for northbound trains. The woman screamed again. This time Quinn could place it: behind a curtained stall to her left. The suspect was getting away. Quinn stopped. She pulled the curtain aside. A woman sat in a chair with both hands clamped over her wrist. Blood ran between her fingers. A man crouched before her, pressing clean gauze against the wound. He looked up, and Quinn recognized Tomás Herrera. For a second neither spoke. His short curls were damp, his olive face tight with concentration. The Saint Christopher medallion at his throat glinted as he shifted. “She’ll live,” he said. “If you let me finish.” “What happened?” “Broken glass.” He pressed the gauze harder. The woman hissed. “I need that bandage. In the blue tin.” Quinn found it on the table beside him. Her eyes stayed on his hands as she gave it over. A pale scar ran along his left forearm. He wrapped the woman’s wrist with the practiced economy of a man who had done it in worse places. “
The man in the grey
coat,” Quinn said. Herrera looked at the opening in the curtain. “You followed him down here?” “He ran.” “That wasn’t an answer.” From the platform came a rising murmur, voices crossing over one another. Quinn heard running feet, then a metal shutter slammed somewhere beyond the stalls. She leaned toward Herrera. “What is this place?” “The Market.” “What market?” He tied off the bandage. “The Veil Market. It’s here until the full moon. Then it moves.” Quinn wanted to dismiss it as a name meant to impress customers. She had seen the brick wall open. She had seen what moved inside the vial. Herrera helped the injured woman to her feet and handed her to a waiting friend. As they slipped out, he glanced at Quinn’s radio. “Your colleagues shouldn’t come down alone.” “They won’t.” “They won’t get through the door without a bone token.” Quinn pictured the small pale object in the suspect’s hand. She looked back toward the fallen grille. “I didn’t use the door.” “No,” Herrera said. “I heard you.” A bang rang out on the platform. People ducked. Quinn drew her baton higher and pulled the curtain wide enough to see. At the far end, the man in grey had reached a service stair. He
was hauling
at a shutter over its entrance while two figures pushed through the crowd after him. Neither looked like police. Herrera came beside her. “The vials in his bag aren’t yours to collect.” “They’re evidence.” “They’re dangerous.” “Then tell me what’s in them.” He looked at her, warm brown eyes steady despite the noise. “Ask him.” The shutter jerked upward. The man in grey dropped to his knees to crawl beneath it. One of his pursuers caught the satchel strap. Glass broke inside. Silver liquid spread across the platform between their shoes. The crowd surged away from it. Quinn did not wait to learn why. She ran toward the stair, shouting for them to get back. The man in grey kicked free of his coat and scrambled under the shutter with the satchel. His pursuer stumbled as the silver liquid ran toward his heel. Quinn caught a stall’s canvas awning, ripped it loose, and threw it over the spill. The cloth darkened at once. Beneath it, something struck the boards hard enough to lift a corner. She vaulted over the covered patch and slid under the shutter. On the other side, a stair climbed into blackness. The man’s
footsteps
beat upward, fast and uneven. “Stop,” she shouted, and followed him. Her radio crackled. Dispatch, clearer now: “Quinn, officers at the entrance. Where are you?” She glanced back. Through the gap beneath the shutter, she could see Herrera dragging the awning farther over the broken glass, warning people away. “Below the station,” she told dispatch. “There’s another exit. I’m going after him.” She took the stairs two at a time. Behind her, the shutter crashed down, sealing off the light of the market. Ahead, a door flew open onto rain and the sound of traffic. Quinn raised her torch and ran toward it, keeping the grey coatless figure in its beam.
created_at
"2026-09-23T16:29:48.677Z"
9/23/2026, 4:29:48 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2065
moderation_latency
(null)
generation_time
51604
tokens_prompt
888
tokens_completion
3268
native_tokens_prompt
810
native_tokens_completion
2740
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
0.02902
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790180988-FMvfa3VP7ORw7Qedhowk"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790180988-IKZT2Sx8Dtd5RYtuTesP"
upstream_id
"resp_0dd977b77680a3e6016ab3fe7cc6ac87d1a7f7fd95e8b3657c"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_0dd977b77680a3e6016ab3fe7cc6ac87d1a7f7fd95e8b3657c"
is_byok
false
latency
485
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.02902
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
10
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
38
tagDensity
0.263
leniency
0.526
rawRatio
0
effectiveRatio
0
97.74%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2212
totalAiIsmAdverbs
1
found
0
adverb
"quickly"
count
1
highlights
0
"quickly"
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)
95.48%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2212
totalAiIsms
2
found
0
word
"weight"
count
1
1
word
"footsteps"
count
1
highlights
0
"weight"
1
"footsteps"
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
211
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
0
narrationSentences
211
filterMatches
0
"watch"
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
238
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
31
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2212
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
11
unquotedAttributions
0
matches
(empty)
50.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
77
wordCount
2025
uniqueNames
20
maxNameDensity
1.88
worstName
"Quinn"
maxWindowNameDensity
3.5
worstWindowName
"Quinn"
discoveredNames
Raven
1
Nest
3
Harlow
1
Quinn
38
Wardour
1
Street
1
Tomás
2
Herrera
11
Soho
1
Charing
1
Cross
1
Road
1
Northbound
1
Camden
1
Morris
3
Tube
1
Saint
1
Christopher
1
People
4
Ahead
3
persons
0
"Raven"
1
"Harlow"
2
"Quinn"
3
"Tomás"
4
"Herrera"
5
"Morris"
6
"Saint"
7
"Christopher"
8
"People"
places
0
"Nest"
1
"Wardour"
2
"Street"
3
"Soho"
4
"Charing"
5
"Cross"
6
"Road"
7
"Camden"
globalScore
0.562
windowScore
0.5
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
157
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
2212
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
238
matches
0
"warned that the"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
89
mean
24.85
std
21.86
cv
0.88
sampleLengths
0
25
1
63
2
14
3
83
4
8
5
30
6
70
7
10
8
27
9
4
10
3
11
68
12
41
13
5
14
27
15
11
16
39
17
60
18
25
19
50
20
89
21
13
22
41
23
38
24
6
25
7
26
50
27
16
28
2
29
33
30
9
31
32
32
30
33
30
34
20
35
12
36
76
37
8
38
21
39
49
40
6
41
7
42
73
43
12
44
51
45
8
46
43
47
12
48
5
49
13
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
2
totalSentences
211
matches
0
"being sent"
1
"was gone"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
2
totalVerbs
354
matches
0
"was inspecting"
1
"was hauling"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
1
flaggedSentences
1
totalSentences
238
ratio
0.004
matches
0
"Someone seized her elbow; she tore free."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
2030
adjectiveStacks
0
stackExamples
(empty)
adverbCount
43
adverbRatio
0.021182266009852218
lyAdverbCount
5
lyAdverbRatio
0.0024630541871921183
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
238
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
238
mean
9.29
std
5.49
cv
0.591
sampleLengths
0
25
1
17
2
15
3
10
4
10
5
11
6
14
7
11
8
11
9
31
10
4
11
7
12
19
13
8
14
16
15
8
16
6
17
9
18
5
19
8
20
25
21
5
22
18
23
9
24
1
25
7
26
14
27
6
28
3
29
1
30
3
31
6
32
13
33
20
34
9
35
20
36
4
37
11
38
8
39
18
40
5
41
4
42
23
43
5
44
6
45
13
46
9
47
17
48
10
49
22
45.36%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
11
diversityRatio
0.27848101265822783
totalSentences
237
uniqueOpeners
66
66.01%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
4
totalSentences
202
matches
0
"Then dispatch asked her to"
1
"Instead he drew something pale"
2
"Then a scream rose from"
3
"Then the man in grey"
ratio
0.02
87.33%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
67
totalSentences
202
matches
0
"He looked left toward Wardour"
1
"He did not look at"
2
"He put a hand inside"
3
"She had spent eighteen years"
4
"She counted to five and"
5
"She had photographed Herrera handing"
6
"She touched the worn leather"
7
"He ran harder."
8
"Her shoes struck puddles, cold"
9
"He had twenty yards and"
10
"She pushed through umbrellas."
11
"He ducked into an alley."
12
"He cut across roads, doubled"
13
"He lunged past her, close"
14
"He elbowed through a cluster"
15
"Her lungs burned."
16
"He needed what was in"
17
"He died in hospital before"
18
"He reached a chain-link fence"
19
"He squeezed through a gap"
ratio
0.332
59.01%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
162
totalSentences
202
matches
0
"The man in the grey"
1
"Detective Harlow Quinn watched him"
2
"He looked left toward Wardour"
3
"He did not look at"
4
"People who expected to be"
5
"People who knew how to"
6
"He put a hand inside"
7
"Quinn waited until a bus"
8
"She had spent eighteen years"
9
"The man had left the"
10
"Herrera had gone east."
11
"The man in grey had"
12
"Quinn had chosen the man"
13
"Quinn turned into a shop"
14
"She counted to five and"
15
"The satchel bumped against his"
16
"Whatever was inside had weight."
17
"A stolen shipment, perhaps, or"
18
"She had photographed Herrera handing"
19
"She touched the worn leather"
ratio
0.802
24.75%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
202
matches
0
"By the time Quinn found"
ratio
0.005
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
91
technicalSentenceCount
1
matches
0
"She pulled the hatch open and crawled into a passage that smelled of wet dust and warm electrical wire."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
10
uselessAdditionCount
0
matches
(empty)
97.37%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
8
fancyCount
2
fancyTags
0
"He pressed (press)"
1
"she shouted (shout)"
dialogueSentences
38
tagDensity
0.211
leniency
0.421
rawRatio
0.25
effectiveRatio
0.105
90.7681%