NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0890ZXHBSRTMKSQKCJNAKZ
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
15.6s
Cost:
$0.013131
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
97.67%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
53.38%
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)
46.00%
Sentence opener variety
(details)
78.43%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
48.24%
Subject-first sentence starts
(details)
29.41%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
62.50%
Useless dialogue additions
(details)
47.44%
Dialogue tag variety (said vs. fancy)
(details)
87.1022%
Overall
Model input
System
You are an expert fiction writer. Always keep the following rules in mind: - Write in past tense and use General English spelling, grammar, and colloquialisms/slang. - Write in active voice - Always follow the "show, don't tell" principle. - Avoid adverbs and cliches and overused/commonly used phrases. Aim for fresh and original descriptions. - Convey events and story through dialogue. - Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. - Skip "he/she said said" dialogue tags and convey people's actions or face expressions through their speech - Avoid mushy dialog and descriptions, have dialogue always continue the action, never stall or add unnecessary fluff. Vary the descriptions to not repeat yourself. - Put dialogue on its own paragraph to separate scene and action. - Reduce indicators of uncertainty like "trying" or "maybe" When writing text: - NEVER conclude the scene on your own, follow the beat instructions very closely. - NEVER end with foreshadowing. - NEVER write further than what I prompt you with. - AVOID imagining possible endings, NEVER deviate from the instructions. - STOP EARLY if the continuation contains what was required in the instructions. You do not need to fill out the full amount of words possible.
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <codex> <character id="4416" name="Detective Harlow Quinn" aliases="Quinn, Detective Quinn, Harlow" pronouns="she/her" species="Human" storyRole="Antagonist"> <eyeColor>brown</eyeColor> <hair>closely cropped salt-and-pepper</hair> <height>5'9"</height> <age>41</age> <jawline>sharp jaw</jawline> <watch>worn leather watch on her left wrist</watch> <bearing>military precision</bearing> <description>A Metropolitan Police detective with 18 years of decorated service who suspects the clique is involved in criminal activity.</description> <backstory>She lost her partner, DS Morris, during a case three years ago under unexplained circumstances that had supernatural origins she doesn't yet understand.</backstory> </character> <character id="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> Continue the story using the following instructions: <instructions> 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. </instructions>
Model response
Messages
Meta
AI
Rain sheeted off the shop
fronts in Soho and ran in dirty ribbons along the kerb.
Detective Harlow Quinn hit the
pavement hard, coat open, hair plastered to her scalp, one hand braced on the cold grip of her service pistol as she pushed through the wet glare of traffic lights and neon. “Stop!”
The man ahead of her
glanced back once, his face a blur under a hood, then cut between a black cab and a delivery van with a shoulder drop that nearly took him under the wheels.
Quinn drove after him, boots
skidding on the slick road paint, breath burning in her throat.
The suspect had been quick
from the start.
Too quick for a bloke
who’d spent the last hour pretending to look nervous outside a back entrance off Wardour Street.
Quinn had watched him from
across the road, watched the way he’d palmed the parcel from a courier and slipped it under his jacket before he noticed her and bolted.
Now he ran like he
knew every gutter in the district.
A bus hissed to a
halt ahead, its doors folding open. People spilled out under umbrellas, swearing when they saw the chase.
Quinn ducked round them, shoulder
checking a man in a navy suit who barked, “Oi—” She kept moving.
The suspect hit the corner
by a shuttered record shop, took it tight, and vanished into a narrower lane where the streetlamps threw bars of yellow across the wet brick.
Quinn rounded after him and
caught the flash of his trainers at the far end, then the slam of a steel door. No dead end.
Just a service passage tucked
between a tattoo parlour and a curry house, marked by a rusted security light that
flickered
like a failing
pulse
.
Quinn slowed for half a
step, eyes
scanning
. The passage stank of damp, bleach and old rubbish.
A chain-link gate stood half
open at the far end. Fresh rain dripped from its edge.
She reached it and heard
voices below ground. Not London voices. Not properly. Stripped-down, clipped, a mix of accents and something else she couldn’t place.
The sound came up through
the stairwell in a warm breath of rot and sweat.
Quinn drew her torch and
shone it down the steps. Concrete stairs dropped into darkness, the walls painted a colour that had once
tried to
be white.
A handwritten sign hung crooked
on the wall beside the entrance. NO TROUBLE. NO POLICE. NO PHOTOS.
The suspect’s footsteps had already
gone down. Quinn’s jaw tightened.
She touched the worn leather
strap on her left wrist without thinking, then let her hand fall away. “Don’t be daft,”
she muttered to the empty
passage. A low thump rolled up from below, followed by a burst of laughter.
Somewhere deeper down, metal clinked
against glass.
She crouched at the edge
of the stairs and caught a whiff of incense under the damp, sharp enough to cut through the mould. Her eyes adjusted
slowly
. At the bottom of the steps, a narrow platform opened into a chamber where old Tube tiles gave way to concrete arches and hanging bulbs wrapped in red wire. Light pooled over stalls made from salvaged timber, tarpaulin, and rusted railings. People moved between them in rain-dark coats, masks, hooded jackets, and polished shoes that looked wrong in a place like that. Some wore ordinary faces. Some did not. Quinn had worked enough years in this city to know when she’d walked into a room that didn’t want her there. This one wanted her gone in pieces.
Her radio crackled in her
pocket.
She killed it before it
could speak. “No backup,” she whispered.
She took the first step
down. The air changed as she descended. Cooler, thicker.
It carried wet wool, hot
wiring, spilled spirits, and the copper sting of blood that had not yet dried. At the bottom, she tucked the torch into her coat and kept to the shadow of a pillar while she
scanned
the market. Stalls stretched down the old platform where the tunnel curved out of sight. One sold jars of black powder and pale, twitching roots. Another had racks of bone charms hung on wire hooks. A woman in a red headscarf spooned something silver into a ceramic bowl while a man beside her argued over a vial no bigger than a lipstick tube. A stack of old suitcases stood under a chalk sign that read HEALERS’ STOCK. One of the suitcases leaked a smell like ozone and mint. The suspect moved ahead of her, slipping between bodies with the practised ease of a pickpocket. Quinn caught the back of his jacket, dark and wet at the shoulders.
He looked over his shoulder
and spotted her. His
eyes widened
.
He shoved through a knot
of shoppers and vanished behind a stall draped in old theatre curtains. Quinn pushed after him. “Out the way.” A man with silver rings in both ears turned with a face carved hard and flat. “No guns on the floor, love.” “I’m not here for you.” “You’re still here.”
She brushed past him and
found the curtain-walled stall empty except for hanging chains and a ledger chained to the table. The suspect had ducked under the counter. Quinn dropped to one knee, reached beneath the wood and caught fabric, then wrist. The man jerked hard, elbow smashing into her cheekbone. Pain flashed white.
He scrambled backward, half-crawled, half-slid
through a gap in the stall’s rear wall. Quinn lunged after him and drove her shoulder into the board. The whole
structure
rattled, a jar fell and
shattered
, and people shouted from the aisle. A bell rang somewhere down the tunnel. The suspect hit the open floor again and ran. “Police!” Quinn’s voice cracked through the market. “Move.” That only made them turn. Faces watched from under hoods and veils. A woman in a black
velvet
coat stepped aside with a slow, amused smile. A boy no older than fifteen pulled a small animal—no, not an animal, something too lean and grey—closer to his chest and backed away. Quinn caught up as the suspect shoved through a crowd near a stall built from shipping pallets. The man ahead of him, broad and bald, blocked the way. “Not through there.” The suspect slapped something into the bald man’s palm. A flash of pale bone. A token. The man stepped aside. Quinn saw it and swore under her breath. Not just an underground market. A gate with rules. Her quarry knew them. “Hey!” she barked. “You lot helping him?” No one answered. No one met her eyes for long. The suspect ducked through a narrow archway lined with old ad posters and graffiti sigils, then disappeared into a side tunnel. Quinn reached the arch and found a sign fixed to the wall with wire. VEIL MARKET — LOWER RING She’d heard whispers. Camden. Full moon. No map stayed accurate. Goods that couldn’t cross a border by normal means changed hands under platforms and drains. Things with a price and a
pulse
.
She’d written half of it
off as criminal folklore. The sign stopped being folklore when the tunnel breathed warm air in her face and the noise changed. The chatter of the main floor faded behind her. Ahead, the passage dipped, sloping down in a rough cut through old brick. Rainwater dripped from the ceiling into shallow channels that ran beside the walkway. Blue light
pulsed
at intervals from wires strung along the walls. Quinn touched her jaw, felt the swelling starting under the skin. A voice behind her cut through the murmur. “You’re in the wrong place, Detective.” She turned. Detective Harlow Quinn had a flat look and a sharper stance than most men twice her size, but the woman standing at the tunnel mouth made her own presence without effort. Tall, dark coat, cropped grey hair, brown eyes that missed nothing. Metropolitan Police. Quinn recognised the shape of authority at once. The woman’s gaze
flicked
over her badge, coat, and weapon. “Detective Quinn.” “Now’s not the time to flirt.” The detective’s mouth twitched once. No smile. “Harlow Quinn. I’ve heard enough.” “Lucky me.” “You’re chasing a man I’ve been tracking for two weeks. He lifted evidence from three scenes, and one of my informants says he’s carrying a bone token.” Quinn stared at her. “You’re joking.” The woman’s eyes held steady. “Do I look like I’m joking?” Quinn glanced down the tunnel, then back. “You knew this place existed.” “I knew enough to be standing here.” “Then why’re you letting him get ahead?” The woman’s
watch
flashed under the tunnel light as she checked the time. “Because if I push in blind, I lose him and half my statement chain. If I follow him into his own territory, I might not come back with anything at all.” Quinn
let that sit
between them. The whole city felt built on that choice, only some streets had cleaner uniforms. A shout
echoed
from deeper in the market. The suspect again, farther away now. He’d gained time. Quinn stepped past the other detective. “Then stop talking.” The tunnel opened into a lower chamber built beneath the station platform. The ceiling arched high above them, blackened by age and webbed with pipes. Stalls crowded the space in tight rows, lit by lanterns, hanging bulbs, and glass jars full of low amber fire. The market here had teeth. It sold things in
silence
. A man behind a counter laid out glass syringes filled with liquid that
shimmered
like oil. Across from him, a woman in mirrored glasses traded bundles of dried herbs for a brass key that moved in her palm. The suspect had slowed near a stall draped in silver fabric.
He spoke to the seller
in a low rush, one hand pressing the bone token forward. The seller, a thin figure with white gloves and a face half-hidden by a surgical mask, took the token and vanished behind a curtain. Quinn and the other detective reached the edge of the aisle. “There,” Quinn breathed. The suspect looked up and saw them. Panic ripped across his face. He shoved the stall table aside, scattering jars across the floor. Glass burst. Liquid hissed against concrete. People pulled back. Someone shouted in a language Quinn didn’t know. A short, hard figure in a hood stepped between the detectives and the suspect, one palm raised. “Business,” the hood said. Quinn lifted her badge. “Met Police. Stand aside.” The hood angled its head. “Not here you’re not.” The other detective’s hand dropped near her weapon, then stayed there. Her voice went cold. “You’re obstructing an arrest.” “You’re trespassing.” The suspect bolted. Quinn moved at the same time as the hood, each of them breaking in a different direction. Quinn
charged
past a rack of hanging talismans and shouldered into the open aisle, eyes locked on the fleeing figure ahead. He reached a service door set into the far wall, yanked it open, and disappeared. Quinn hit the door a second later and found a stairwell spiralling down into black. A
pulse
of stale air rolled up from below. It carried damp stone, rust, and something metallic enough to turn her
stomach
. The stairs curved out of sight. No rail. No visible landing. Behind her, the market noise sharpened. The other detective’s
footsteps
approached,
measured
and fast. “He’s gone lower.” Quinn glanced at her. “And?” “And if that opens into the old utility tunnels, we’re into parts of the city no map admits.” Quinn listened. Below, a door slammed. Then quiet. She looked back at the tunnel behind her. The market had gone still around the edge of the noise. A cluster of faces watched from stalls and arches. One man folded his arms. A woman in a green scarf leaned on a crate and let her gaze travel over Quinn’s badge like it was an old joke. The other detective’s jaw set hard. “We can pull out.” Quinn didn’t answer straight away. She stared down the stairwell, one hand on the pistol at her hip, feeling the
pulse
in her cheek where the wall had clipped her. The air out of the shaft smelled wrong. Not just stale. Older. Like wet pennies and mould and burnt hair. She thought of the parcel the suspect had taken. Of the look in his eyes when he saw her. Of the way he’d paid with bone.
Then she thought of the
last three hours, the dead end outside Wardour, the missing statements, the gaps in CCTV, the name she’d written in her notebook and crossed out because it pointed at nowhere sensible. She glanced once at the woman beside her. “You go back to your paperwork, Detective.” The woman’s brow lifted. “You don’t know what’s down there.” Quinn put one boot on the first stair. “Neither do you.”
created_at
"2026-03-18T10:36:17.803Z"
3/18/2026, 10:36:17 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3216
moderation_latency
(null)
generation_time
15332
tokens_prompt
1140
tokens_completion
3439
native_tokens_prompt
984
native_tokens_completion
2754
native_tokens_completion_images
0
native_tokens_reasoning
60
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.013131
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0743b5f68eb3651d0169ba8021df7c81939b1dc2a044bc8cfc"
is_byok
false
latency
194
model_permaslug
"openai/gpt-5.4-mini-20260317"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773830177-iuFrl7wetHs45qPhbZdM"
upstream_id
"resp_0743b5f68eb3651d0169ba8021df7c81939b1dc2a044bc8cfc"
total_cost
0.013131
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
8
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
39
tagDensity
0.205
leniency
0.41
rawRatio
0
effectiveRatio
0
97.67%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2145
totalAiIsmAdverbs
1
found
0
adverb
"slowly"
count
1
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)
53.38%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2145
totalAiIsms
20
found
0
word
"flickered"
count
1
1
word
"pulse"
count
4
2
word
"scanning"
count
1
3
word
"footsteps"
count
2
4
word
"scanned"
count
1
5
word
"structure"
count
1
6
word
"shattered"
count
1
7
word
"velvet"
count
1
8
word
"pulsed"
count
1
9
word
"flicked"
count
1
10
word
"echoed"
count
1
11
word
"silence"
count
1
12
word
"shimmered"
count
1
13
word
"charged"
count
1
14
word
"stomach"
count
1
15
word
"measured"
count
1
highlights
0
"flickered"
1
"pulse"
2
"scanning"
3
"footsteps"
4
"scanned"
5
"structure"
6
"shattered"
7
"velvet"
8
"pulsed"
9
"flicked"
10
"echoed"
11
"silence"
12
"shimmered"
13
"charged"
14
"stomach"
15
"measured"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"eyes widened/narrowed"
count
1
highlights
0
"eyes widened"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
189
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
1
narrationSentences
189
filterMatches
0
"watch"
hedgeMatches
0
"tried to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
221
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
37
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2144
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
12
unquotedAttributions
0
matches
(empty)
50.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
51
wordCount
1941
uniqueNames
10
maxNameDensity
1.85
worstName
"Quinn"
maxWindowNameDensity
3.5
worstWindowName
"Quinn"
discoveredNames
Soho
1
Harlow
2
Quinn
36
Wardour
2
Street
1
London
1
Tube
1
One
3
Police
1
People
3
persons
0
"Harlow"
1
"Quinn"
2
"Tube"
3
"One"
4
"People"
places
0
"Soho"
1
"Wardour"
2
"Street"
3
"London"
globalScore
0.573
windowScore
0.5
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
131
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
2144
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
221
matches
0
"let that sit"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
106
mean
20.23
std
20.68
cv
1.022
sampleLengths
0
53
1
1
2
52
3
59
4
11
5
37
6
3
7
52
8
28
9
33
10
8
11
32
12
10
13
28
14
6
15
7
16
21
17
9
18
20
19
97
20
28
21
13
22
4
23
6
24
50
25
86
26
37
27
3
28
17
29
4
30
3
31
16
32
6
33
5
34
3
35
51
36
3
37
39
38
7
39
9
40
8
41
50
42
28
43
3
44
16
45
4
46
21
47
7
48
10
49
21
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
189
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
321
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
3
semicolonCount
0
flaggedSentences
2
totalSentences
221
ratio
0.009
matches
0
"A boy no older than fifteen pulled a small animal—no, not an animal, something too lean and grey—closer to his chest and backed away."
1
"VEIL MARKET — LOWER RING She’d heard whispers."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
867
adjectiveStacks
0
stackExamples
(empty)
adverbCount
19
adverbRatio
0.02191464821222607
lyAdverbCount
3
lyAdverbRatio
0.0034602076124567475
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
221
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
221
mean
9.7
std
7.51
cv
0.774
sampleLengths
0
16
1
37
2
1
3
36
4
16
5
8
6
21
7
30
8
11
9
11
10
11
11
15
12
3
13
30
14
22
15
3
16
25
17
8
18
9
19
10
20
6
21
8
22
3
23
2
24
12
25
15
26
10
27
17
28
11
29
2
30
2
31
2
32
7
33
3
34
18
35
9
36
13
37
7
38
24
39
4
40
29
41
12
42
21
43
4
44
3
45
21
46
7
47
6
48
7
49
4
46.00%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
15
diversityRatio
0.3167420814479638
totalSentences
221
uniqueOpeners
70
78.43%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
4
totalSentences
170
matches
0
"Too quick for a bloke"
1
"Just a service passage tucked"
2
"Somewhere deeper down, metal clinked"
3
"Then she thought of the"
ratio
0.024
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
28
totalSentences
170
matches
0
"She kept moving."
1
"She reached it and heard"
2
"She touched the worn leather"
3
"she muttered to the empty"
4
"She crouched at the edge"
5
"Her eyes adjusted slowly."
6
"Her radio crackled in her"
7
"She killed it before it"
8
"She took the first step"
9
"It carried wet wool, hot"
10
"He looked over his shoulder"
11
"His eyes widened."
12
"He shoved through a knot"
13
"She brushed past him and"
14
"He scrambled backward, half-crawled, half-slid"
15
"Her quarry knew them."
16
"She’d written half of it"
17
"He’d gained time."
18
"It sold things in silence."
19
"He spoke to the seller"
ratio
0.165
48.24%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
140
totalSentences
170
matches
0
"Rain sheeted off the shop"
1
"Detective Harlow Quinn hit the"
2
"The man ahead of her"
3
"Quinn drove after him, boots"
4
"The suspect had been quick"
5
"Quinn had watched him from"
6
"A bus hissed to a"
7
"People spilled out under umbrellas,"
8
"Quinn ducked round them, shoulder"
9
"She kept moving."
10
"The suspect hit the corner"
11
"Quinn rounded after him and"
12
"Quinn slowed for half a"
13
"The passage stank of damp,"
14
"A chain-link gate stood half"
15
"She reached it and heard"
16
"The sound came up through"
17
"Quinn drew her torch and"
18
"A handwritten sign hung crooked"
19
"The suspect’s footsteps had already"
ratio
0.824
29.41%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
170
matches
0
"Now he ran like he"
ratio
0.006
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
80
technicalSentenceCount
3
matches
0
"Too quick for a bloke who’d spent the last hour pretending to look nervous outside a back entrance off Wardour Street."
1
"People moved between them in rain-dark coats, masks, hooded jackets, and polished shoes that looked wrong in a place like that."
2
"Tall, dark coat, cropped grey hair, brown eyes that missed nothing."
62.50%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
8
uselessAdditionCount
1
matches
0
"Quinn ducked, shoulder checking a man in a navy suit who barked,"
47.44%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
5
fancyCount
4
fancyTags
0
"she muttered (mutter)"
1
"she whispered (whisper)"
2
"she barked (bark)"
3
"Quinn breathed (breathe)"
dialogueSentences
39
tagDensity
0.128
leniency
0.256
rawRatio
0.8
effectiveRatio
0.205
87.1022%