NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HWVFD3AP31NDW7SQDWXYN
Run Details
Model:
GPT-6 Sol
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
55.8s
Cost:
$0.032550
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
96.01%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
80.04%
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)
47.73%
Name drop frequency
(details)
100.00%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
100.00%
Paragraph length variance
(details)
93.99%
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)
47.31%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
87.26%
Pronoun-first sentence starts
(details)
60.90%
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)
93.7748%
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 with blood on his cuff and looked straight at Detective Harlow Quinn. For half a second, neither of them moved.
Rain hissed against the green
neon sign above the bar, spilling down his face in thin bright lines. Then he turned and ran. Quinn went after him.
He cut across the Soho
pavement between two men sheltering under a broken umbrella.
Quinn struck one shoulder with
her own, heard a curse, and kept moving.
The suspect was twenty yards
ahead by the time she reached the corner.
A black cab slammed its
brakes as he darted in front of it.
Quinn vaulted the low bonnet
before the driver could pull away. “Police! Stop!” The man glanced back.
She caught the quick flash
of a narrow face, wet dark hair, and fear. He
wasn’t looking
for help. He
was checking
the distance. Quinn pushed harder. Inside the Nest, six minutes earlier, she’d found Tomás Herrera kneeling beside a woman on the storeroom floor.
Herrera had one bloodied hand
pressed to the woman’s abdomen and the other braced against a shelf of bottles.
His Saint Christopher medallion hung
outside his shirt. When Quinn stepped in, he’d looked up at her with the exhausted anger of someone interrupted at the worst possible moment. “Call an ambulance,” he’d said. She had.
She’d also seen the door
at the rear of the room swing shut.
The woman had been conscious
enough to grab Quinn’s sleeve. “Grey coat,” she’d whispered. “Don’t let him take it down.” “What?” But the woman’s eyes had rolled toward the door, and Herrera had snapped at Quinn to give him room.
By the time she got
through to the alley, the man
was already running
.
Now he turned north, splashing
through gutters, passing shuttered shops and queues outside late bars.
Quinn’s radio crackled against her
shoulder. She pressed it. “Suspect on foot, heading north from Wardour Street. Male, grey coat, dark hair. Possible connection to a stabbing at the Raven’s Nest. I need units at the north end of the street.”
A burst of static swallowed
the reply.
She tried again, got a
voice confirming her location, then lost it under a bus braking at the junction. The man took a sharp right. Quinn followed him into a service lane where bins lined the walls and rainwater coursed around her boots.
He knocked over a stack
of plastic crates. She hurdled them, landed badly, and felt her right ankle complain. The lane ended at a locked gate. He didn’t slow.
He seized the top rail
and climbed. Quinn had a clear view of his hands as he hauled himself over. Something pale and small
was clenched
in his left fist. He dropped out of sight.
She reached the gate, put
a foot through the bars, and climbed after him.
Her coat caught on a
bolt; she tore it free and landed in a yard behind a restaurant. A kitchen porter stood smoking under an awning. He pointed before she asked. “That way.” The suspect was already through the open loading doors. Quinn ran past sacks of onions and startled cooks, out the front of the restaurant and into another wash of headlights.
He was trying to lose
her, but he was moving with purpose. Every turn carried him north. The woman’s grip on her sleeve came back to Quinn. Don’t let him take it down. Down where?
She knew enough about the
people who gathered at the Raven’s Nest to distrust easy answers. Over the past six months, she had
traced
stolen medical supplies, assaults no one would report, and a string of payments to names that vanished when she pulled the accounts. Herrera appeared in the margins of three incidents. A former paramedic with no licence and patients who preferred bleeding in storerooms to calling 999.
She had followed him to
the Nest tonight expecting to learn something.
Instead she’d found a woman
with a wound he could barely hold closed. At the next junction, the man in grey stopped dead. For one hopeful second Quinn thought his breath had run out.
Then a motorbike passed between
them, spraying water over the road.
He used the gap to
cross and ducked into a narrow passage behind a row of darkened shops. Quinn swore and followed. Her phone
vibrated
in her pocket. She ignored it. Ahead, the passage opened onto a larger road. The suspect stepped off the kerb, flagged down a cab, and pulled the rear door open. Quinn was too far away to stop him. She caught the registration as the cab pulled out, then radioed it in while running toward the main road. Traffic held the cab at the lights. She pounded on the boot. The driver twisted around in his seat, startled. The rear window lowered halfway. The suspect leaned toward it. “You should go back,” he said. Up close, he looked younger than she’d thought. A cut ran along his cheekbone. The blood on his cuff had soaked into the fabric. “Get out of the cab.” He shook his head. “Ask your doctor friend what she stole.” The light turned green. The cab
lurched
forward, and Quinn had to let go. She got a car two streets later. It took twelve minutes to catch up with the cab near Camden, twelve minutes spent watching rain blur the windscreen and listening to dispatch report that the injured woman had
been taken
to hospital. Critical. Herrera had gone with her. “What about the rear door at the bar?” Quinn asked. “Uniform says it opens onto the alley.” That was true. It didn’t tell her what the woman had meant. The cab stopped near a fenced entrance to a disused Tube station. Quinn’s driver pulled in across the road. Before she could get out, the man in grey was through a gap in the fencing, his coat flaring behind him. “I’ve got him,” she said into her radio. “Abandoned station entrance off—” Static burst from the speaker. She checked the signal on her phone. One bar. Then none. “Wait here,” she told the driver. He looked at the fence, then at her. “You want me to call for backup?” “I already did. If they ring, tell them where I went.” Outside, the rain had eased to a cold mist. The fence had been cut and pulled back just wide enough for a person to slip through. Beyond it, cracked concrete steps descended under a tiled arch. Someone had scraped graffiti from the old station nameplate. The blank rectangle shone pale in the beam of Quinn’s torch. The suspect had disappeared below. She stopped at the top step. The sensible move was to hold position. Her units knew the location, more or less; they could cover the exits once they arrived. She was alone, her radio failing, about to enter a place she couldn’t see. From underground came the muffled sound of many voices. Not squatters. Not a handful of people sheltering from the rain. A crowd. Quinn looked back at the street. Cars went by. Across the road, her driver raised a hand to show he was on the phone. She thought of the woman on the storeroom floor, struggling to shape those few words. Then she went down. The station smelled of damp plaster and hot metal. Her torch found old advertisements buckling on the walls. A new cable ran along the ceiling, fixed in place with bright plastic clips. Somewhere below, a generator
throbbed
. Quinn descended
slowly
, listening. At the bottom of the stairs stood a steel security door. The suspect was beside it, speaking to a woman behind a barred window. Quinn killed her torch and pressed against the tiled wall. He held out his left hand. The woman at the window examined whatever lay in his palm, then slid back the door’s bolt. Warm light spilled into the stairwell. The man slipped through. Quinn got a glimpse past him: people moving between crowded stalls, glass jars glowing under lamps, bundles of herbs hanging from the old route signs. Then the door shut. She waited three beats and approached the window. The woman behind it had a shaved head and a heavy ring through one
eyebrow
. Her gaze dropped to Quinn’s empty hand. “Token,” she said. Quinn showed her warrant card instead. “Detective Quinn. Open the door.” The woman didn’t read it. “Token.” “A man just came through. Grey coat. I’m pursuing him in connection with a stabbing.” “He had a token.” Quinn put the card away. “Someone may die.” For the first time, the woman’s expression changed. Not sympathy. Calculation. “Then you’d better hurry.” She stepped back from the window and vanished. Quinn tested the door. Locked. She considered forcing it, but there was no give around the frame, and the hinges were on the other side. Through the bars she could see a sliver of platform and the backs of strangers passing with shopping bags. None looked toward her. She moved away from the door and searched the stairwell. An old ticket office stood to her right, its glass painted over from within.
To the left, a locked
staff passage bore a modern keypad. The market had
been installed
here, not improvised for the night. People had worked to keep it out of sight. A scrape came from behind her. Quinn turned, hand going to her baton. A boy of about sixteen stood on the stairs, soaked through, holding a paper bag against his chest. He froze when he saw her. “Market?” she asked. His eyes
flicked
to her warrant card, still visible in her hand. He took one step backward. “I’m not interested in you,” she said. “How do I get in?” He said nothing. From beyond the steel door came a woman’s sudden shout. It cut off under the noise of the crowd. Quinn looked back.
By the time she faced
the stairs again, the boy had set the bag down. He took a small white disc from his pocket and slid it across the floor with his thumb. It stopped against her boot. Bone. Smoothed thin as a coin, with a hole bored through its centre. “Don’t say I gave you that,” he said. He hurried back up the stairs before she could answer. Quinn picked up the token. A dark stain marked one edge. She couldn’t tell whether it was old blood or dye. At the window, the shaved-headed woman reappeared. “Found one, then.” “Open it.” The woman held out her hand. Quinn gave her the bone disc. A lock clanked inside the wall. “You keep your badge out,” the woman said, “you won’t make it to the far end.” The door opened. Quinn stepped onto a platform that should have been empty and found herself in the middle of a market. Stalls occupied both sides of the tracks. Ropes of bare bulbs hung from the tiled pillars. People passed beneath them carrying parcels wrapped in black paper or jars packed in straw. A man with silver pins through both ears argued over the price of a bottle filled with black liquid.
Further down, someone sold old
watches laid out on
velvet
beside sealed tins labelled in a script Quinn couldn’t read. Hot oil, incense, sewage and the sharp sweetness of cut fruit crowded the air. She
scanned
the crowd for grey. A ripple of movement near the far staircase caught her eye. There he
was, pushing
between two stalls. He turned his head, saw her, and stumbled. Quinn started after him. A vendor stepped into her path with a tray of tiny glass vials. “Mind—” She caught the tray before it tipped, shoved it back into his hands, and kept going. The suspect dropped from the platform onto the tracks. Quinn followed, boots striking gravel. A disused train stood ahead, its doors held open by wooden wedges. People
were entering
through the first carriage and leaving by the last. Grey coat disappeared into it. Quinn reached the open door and stopped. A bloody handprint marked the metal beside the handle. Fresh. Hers wasn’t the only life
measured
in seconds tonight. She gripped the doorframe and pulled herself inside. The carriage had
been stripped
of seats and filled with curtained cubicles. Behind one curtain, someone groaned. Behind another, a woman murmured instructions in a language Quinn didn’t know. At the far end, the suspect shoved through a connecting door. “Stop!” Quinn shouted. Faces turned. No one moved to help. She crossed the carriage, passing a basin of pink water and a stack of folded dressings. The smell of antiseptic broke through the incense. When she reached the connecting door, she saw him on the narrow walkway between cars. His left hand was pressed against his side now. Blood seeped between his fingers. He had
been wounded
before he left the Nest. He’d kept running anyway. He pushed into the next carriage. Quinn followed, slower this time. An enclosed space, an injured man, too many places for someone else to wait. She kept her baton ready. The second carriage was empty except for a row of wooden crates. The suspect stood at the far door. He had nowhere left to run: the carriage beyond
was sealed
, its windows boarded over. “Put your hands where I can see them,” Quinn said. He laughed once, breathlessly. “You don’t know what you followed me into.” “I know you left a woman bleeding on the floor.” “She cut me.” He took his hand from his side. The wound had soaked the lining of his coat. “I tried to stop her taking it.” “Taking what?” He reached into his pocket. Quinn raised her baton. “Slowly.” He brought out a narrow metal case, no longer than her finger. It
was dented
, and a red smear crossed its clasp. “She had this?” Quinn asked. “She opened it.” His face tightened. “At the bar. Herrera saw what happened to her.” A clang sounded behind Quinn. The door between carriages slammed shut. She turned just enough to see a bolt slide into place on the other side of its window. A figure moved away before she could make out a face. When she looked back, the man in grey had lowered the case. His eyes
were fixed
on the locked door behind her. “They let you in,” he said. Quinn shifted her grip on the baton. Beyond the sealed carriage,
footsteps
struck the platform, several pairs moving fast. She had followed him because a woman might die, because he had run, because the tunnel had offered one way forward.
Now she had a wounded
suspect in front of her and someone closing in from behind. “Set the case on the floor,” she said. “Then get behind those crates.” “And you?” Quinn looked at the boarded windows, the bolted door, the man struggling to stay upright. Her radio gave a brief crackle and fell silent. “I’m going to find out who locked us in.”
created_at
"2026-09-23T16:34:33.078Z"
9/23/2026, 4:34:33 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2580
moderation_latency
(null)
generation_time
55743
tokens_prompt
888
tokens_completion
3693
native_tokens_prompt
810
native_tokens_completion
3093
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
0.03255
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790181273-K2a4NSHBvqQsDcItgDRG"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790181273-58qaaCu5rM429HH4zA0Z"
upstream_id
"resp_0a7a3ddb97568c2d016ab3ff993a6087d1be55a677794d97c4"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_0a7a3ddb97568c2d016ab3ff993a6087d1be55a677794d97c4"
is_byok
false
latency
872
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.03255
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
18
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
48
tagDensity
0.375
leniency
0.75
rawRatio
0
effectiveRatio
0
96.01%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2505
totalAiIsmAdverbs
2
found
0
adverb
"slowly"
count
2
highlights
0
"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)
80.04%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2505
totalAiIsms
10
found
0
word
"traced"
count
1
1
word
"vibrated"
count
1
2
word
"lurched"
count
1
3
word
"throbbed"
count
1
4
word
"eyebrow"
count
1
5
word
"flicked"
count
1
6
word
"velvet"
count
1
7
word
"scanned"
count
1
8
word
"measured"
count
1
9
word
"footsteps"
count
1
highlights
0
"traced"
1
"vibrated"
2
"lurched"
3
"throbbed"
4
"eyebrow"
5
"flicked"
6
"velvet"
7
"scanned"
8
"measured"
9
"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
249
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
249
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
279
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
34
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2505
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
25
unquotedAttributions
0
matches
(empty)
47.73%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
71
wordCount
2249
uniqueNames
15
maxNameDensity
2.05
worstName
"Quinn"
maxWindowNameDensity
3.5
worstWindowName
"Quinn"
discoveredNames
Raven
2
Nest
5
Detective
1
Harlow
1
Quinn
46
Soho
1
Tomás
1
Herrera
5
Saint
1
Christopher
1
Camden
1
Tube
1
Static
1
Faces
1
People
3
persons
0
"Raven"
1
"Harlow"
2
"Quinn"
3
"Tomás"
4
"Herrera"
5
"Saint"
6
"Christopher"
7
"Static"
8
"People"
places
0
"Nest"
1
"Detective"
2
"Soho"
3
"Camden"
globalScore
0.477
windowScore
0.5
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
168
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
2505
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
279
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
124
mean
20.2
std
17.29
cv
0.856
sampleLengths
0
24
1
31
2
4
3
64
4
2
5
28
6
3
7
66
8
5
9
15
10
20
11
1
12
33
13
24
14
32
15
26
16
50
17
10
18
28
19
45
20
2
21
30
22
17
23
16
24
2
25
70
26
25
27
50
28
4
29
33
30
39
31
18
32
6
33
24
34
5
35
11
36
14
37
47
38
10
39
7
40
12
41
40
42
12
43
5
44
11
45
6
46
15
47
11
48
56
49
5
93.99%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
8
totalSentences
249
matches
0
"was clenched"
1
"been taken"
2
"been installed"
3
"been stripped"
4
"been wounded"
5
"was sealed"
6
"was dented"
7
"were fixed"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
6
totalVerbs
427
matches
0
"wasn’t looking"
1
"was checking"
2
"was already running"
3
"was trying"
4
"was, pushing"
5
"were entering"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
2
flaggedSentences
2
totalSentences
279
ratio
0.007
matches
0
"Her coat caught on a bolt; she tore it free and landed in a yard behind a restaurant."
1
"Her units knew the location, more or less; they could cover the exits once they arrived."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
2250
adjectiveStacks
0
stackExamples
(empty)
adverbCount
49
adverbRatio
0.021777777777777778
lyAdverbCount
6
lyAdverbRatio
0.0026666666666666666
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
279
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
279
mean
8.98
std
5.58
cv
0.622
sampleLengths
0
24
1
8
2
18
3
5
4
4
5
14
6
13
7
13
8
13
9
11
10
2
11
4
12
14
13
5
14
5
15
3
16
18
17
19
18
8
19
21
20
5
21
2
22
13
23
10
24
4
25
6
26
1
27
19
28
14
29
15
30
6
31
3
32
32
33
7
34
19
35
6
36
18
37
8
38
11
39
7
40
3
41
7
42
13
43
10
44
5
45
14
46
18
47
8
48
5
49
2
47.31%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
13
diversityRatio
0.3118279569892473
totalSentences
279
uniqueOpeners
87
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
7
totalSentences
223
matches
0
"Then he turned and ran."
1
"Instead she’d found a woman"
2
"Then a motorbike passed between"
3
"Then she went down."
4
"Somewhere below, a generator throbbed."
5
"Then the door shut."
6
"Further down, someone sold old"
ratio
0.031
87.26%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
74
totalSentences
223
matches
0
"He cut across the Soho"
1
"She caught the quick flash"
2
"He wasn’t looking for help."
3
"He was checking the distance."
4
"His Saint Christopher medallion hung"
5
"She’d also seen the door"
6
"She pressed it."
7
"She tried again, got a"
8
"He knocked over a stack"
9
"She hurdled them, landed badly,"
10
"He didn’t slow."
11
"He seized the top rail"
12
"He dropped out of sight."
13
"She reached the gate, put"
14
"Her coat caught on a"
15
"He pointed before she asked."
16
"He was trying to lose"
17
"She knew enough about the"
18
"She had followed him to"
19
"He used the gap to"
ratio
0.332
60.90%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
178
totalSentences
223
matches
0
"The man in the grey"
1
"Rain hissed against the green"
2
"Quinn went after him."
3
"He cut across the Soho"
4
"Quinn struck one shoulder with"
5
"The suspect was twenty yards"
6
"A black cab slammed its"
7
"Quinn vaulted the low bonnet"
8
"The man glanced back."
9
"She caught the quick flash"
10
"He wasn’t looking for help."
11
"He was checking the distance."
12
"Quinn pushed harder."
13
"Herrera had one bloodied hand"
14
"His Saint Christopher medallion hung"
15
"She’d also seen the door"
16
"The woman had been conscious"
17
"Quinn’s radio crackled against her"
18
"She pressed it."
19
"A burst of static swallowed"
ratio
0.798
100.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
6
totalSentences
223
matches
0
"By the time she got"
1
"Now he turned north, splashing"
2
"Before she could get out,"
3
"To the left, a locked"
4
"By the time she faced"
5
"Now she had a wounded"
ratio
0.027
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
98
technicalSentenceCount
1
matches
0
"A former paramedic with no licence and patients who preferred bleeding in storerooms to calling 999."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
18
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
14
fancyCount
1
fancyTags
0
"Quinn shouted (shout)"
dialogueSentences
48
tagDensity
0.292
leniency
0.583
rawRatio
0.071
effectiveRatio
0.042
93.7748%