NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD7R4RKWWVVZNBNBM0944PD
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, High)
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
1m 54s
Cost:
$0.048641
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
95.34%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
83.71%
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)
88.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
57.36%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
89.27%
Subject-first sentence starts
(details)
24.39%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
64.29%
Dialogue tag variety (said vs. fancy)
(details)
91.7453%
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 rain had been falling
over Soho for hours, needling the pavements and turning the neon into long, wet wounds of color.
Detective Harlow Quinn stood beneath
a leaning lamppost across the street from the Raven’s Nest, collar raised, hands buried in the pockets of her coat.
The bar’s green neon sign
hummed above the entrance, reflected in the black water gathering between the cobbles. Inside, shapes shifted behind fogged glass. Someone laughed.
Someone else knocked a bottle
from a table, the crash dulled by brick and distance.
Quinn checked the worn leather
watch
on her left wrist. Eleven forty-three.
Tomás Herrera had gone in
at eight.
She knew him by the
photographs clipped to the case board in her office: twenty-nine years old, olive-skinned, short curly dark hair, a former paramedic with warm brown eyes and a practiced smile. Born in Seville.
NHS credential revoked eighteen months
ago for administering unauthorized treatments. Since then, he had appeared too often in the margins of cases that refused to make sense.
Bodies with wounds that healed
before anyone could examine them.
Victims who vanished from hospital
records. Dead men seen alive three boroughs away. And tonight, Herrera
was carrying
something.
The Nest’s door opened, throwing
amber light across the pavement.
Herrera stepped out beneath the
green neon glow, hatless despite the rain, one arm pressed tight to his ribs.
The Saint Christopher medallion at
his throat caught the light. He paused at the curb, looked left, then right. Not casually.
He was checking for a
tail.
Quinn lowered her face as
a passing taxi splashed water over her boots. When she looked up again, Herrera had crossed the street.
He moved with quick, economical
steps, heading east through the thinning crowds.
She gave him half a
block, then followed.
Rain tapped the folded umbrella
in her hand. She didn’t open it. An umbrella changed a person’s silhouette.
She had learned that early
in her career, back when DS Morris used to laugh at her for treating every street like a battlefield. “You’re not in the Army anymore, Harlow,”
he would say
. Three years dead, and she still heard him. Herrera turned
sharply
into an alley. Quinn
quickened
her pace.
She reached the mouth of
the alley in time to see him glance over his shoulder.
Their eyes met through the
rain. He ran. “Stop!” Quinn shouted. “Metropolitan Police!” The shout only
seemed to
put wings on him.
He vaulted a stack of
flattened cardboard, slipped on the far side, caught himself against a wheelie bin, and sprinted toward the far end of the alley. Quinn chased him, coat flaring behind her. Water flooded her shoes. The alley narrowed between sweat-slick brick walls, crowded with bins and damp bags of refuse. Herrera grabbed a fire escape ladder. Quinn lunged and seized the back of his jacket. For a second she had him. His heels kicked. The medallion swung from his throat.
Then he twisted with a
strength that surprised her, tore free of the wet fabric, and climbed. “You don’t want to follow me!”
he called down
. “Everyone says that.” She went after him. The ladder shook under their
weight
. Herrera moved fast, hands slapping wet iron, shoes scraping rungs. Halfway up, his left sleeve snagged on a bolt. The fabric tore, revealing the pale line of an old scar along his forearm. He looked down at her, breath steaming. “Detective Quinn,” he said. That stopped her. Rain slid down the rungs into her sleeves.
Somewhere below, the alley door
banged shut. The city noises softened, as if the buildings themselves had closed around them. “You know who I am,” she said. “More people know you than you’d like.”
He reached the roof and
disappeared. Quinn hauled herself over the ledge, knees scraping concrete. Herrera
was already crossing
the flat rooftop, jumping a narrow gap onto the next building.
She followed without thinking, boots
striking tar and gravel. A television aerial bent under her foot.
She regained her balance and
ran on. Herrera descended a stairwell at the far side. Quinn reached it six seconds later. No door.
Only darkness and the wet
iron smell of an enclosed drop. She drew her sidearm. At street level again, she found him twenty yards ahead, limping now. The object under his coat shifted with every stride.
He cut through a shuttered
market, over a chain fence and into a construction site. Quinn climbed after him, landing in ankle-deep mud. “Herrera!” He didn’t answer. They crossed the empty shell of a building, passing between concrete pillars while rain sheeted through the open floors above. Herrera knew the route too well. Every turn had
been planned
. Every shortcut took him farther from the bright arteries of Soho, through back streets where the surveillance cameras were blind, broken, or pointed the wrong way.
By the time they reached
Camden, Quinn’s lungs burned and her hair had darkened to the color of wet iron. Herrera staggered toward a dead-end lane beside the underground station. A boarded entrance stood between a shuttered pharmacy and a café with metal grilles drawn over its windows. No lights. No customers. No way through. Herrera stopped at the boards and pressed one hand to his side. When he turned, his face had gone pale beneath the rain. “You need to go home, Detective.” Quinn raised her weapon, centering the sights on his chest. “Hands where I can see them.” He lifted both hands. The object under his coat shifted again. It
was shaped
like a book, but too thick, too angular at the corners. “What are you carrying?” “Medicine.” “Off the books?” His mouth tightened. “There are people the books don’t cover.” She moved closer. Eight feet between them now. Close enough to see the fine tremor in his fingers, the blood darkening one side of his shirt. “You’re injured.” “Not mine.” “Whose?” Herrera glanced past her. Not at the street. At the shadows pooled beneath the station’s overhang. Quinn heard nothing. Then something moved. A shape slid along the wall on all fours, its joints bending the wrong way. It raised its head, and the rain
seemed to
pass through the pale surface of its face before striking the pavement beneath it. Quinn’s finger tightened on the trigger. Herrera stepped between her and the thing. “Don’t.” “Move.” “If you shoot, it’ll hear you.” “It’s already looking at me.” “No,” Herrera said
softly
. “It’s looking at the gun.” The pale shape unfolded from the shadows. Seven feet tall, perhaps more. Its limbs were too long, its skin gray and translucent. It wore a Metropolitan Police coat, though no insignia remained on the shoulders. The face beneath the cap was featureless except for a vertical seam where the mouth should have been. Quinn
knew that coat
. She had last seen it soaked in blood on a mortuary slab. “Morris,” she whispered. The thing’s head jerked. Herrera reached into his pocket. Quinn swung her aim back to him. “Don’t.” He withdrew a small white object. Bone, carved into the shape of a crescent moon. The seam in the creature’s face split open. No sound emerged, but Quinn felt it—inside her teeth, behind her eyes, in the old scar tissue at the base of her skull. Herrera slapped the bone token against the boarded entrance. The boards disappeared. No trick of the rain. No shifting panel. They simply ceased to be there, revealing a stairwell that descended into pulsing amber darkness. Warm air rolled upward, carrying the scents of spice, smoke, wet earth, and something faintly rotten. Herrera ducked through. The pale thing rushed after him. Quinn fired. The gunshot cracked down the lane. The bullet struck the creature between the shoulders and sank without blood, without impact, as though swallowed. The thing barely slowed. It vanished through the opening after Herrera.
Then the boards flickered back
into place. Quinn stood alone in the rain. For three seconds, she did nothing. Her training offered a clear answer. Withdraw. Call for armed support. Secure the entrance. Wait. Her training had also told her, three years ago, that Morris’s wounds had been consistent with an animal attack, despite the fact that no animal left human fingerprints inside a corpse. She touched the boards. Solid wood. Old nails. Rain swelling the grain. Her hand came away with a white crescent pressed into the palm. Herrera had dropped another token. The metal of her
watch
ticked against her wrist, louder than the rain. Morris’s face came back to her—
not the thing in the coat, but the man
. Grinning across a pub table. Telling her she worried too much. Walking into a derelict building alone because backup was twelve minutes away and he had never once known how to wait. Quinn looked up and down the lane. No patrol cars. No witnesses.
Only water streaming from the
gutters and the greenish city glow reflecting from low clouds. She could call it in. She could stand here and repeat what she had seen into a radio, and someone from Professional Standards would be taking her statement by sunrise. Or she could go after him. After Herrera. After the thing wearing Morris’s coat. The token in her hand was warm. Quinn pressed it to the boards. The wood dissolved. She stepped through before she could reconsider, gun held low beside her leg. The stairwell beyond was narrow and tiled in black, descending farther than any station had a right to go. Old London Underground posters lined the walls, though the destinations were wrong. Stations she had never heard of. Names that changed when she
tried to
read them. At the first landing, she found blood. Fresh. Bright. Still wet. Herrera’s, or the other person whose blood stained his shirt. The stairs ended at an abandoned platform. Beyond the broken ticket barriers, light bloomed. Quinn stopped. A market filled the station, stretching into tunnels that should have ended in rubble. Canvas stalls crowded the tracks, their frames lashed together with copper wire and braided hair. Lanterns burned with blue flames. Rain somehow fell from the vaulted ceiling in narrow threads, vanishing before it touched the crowd. And what a crowd it was. A woman with moth wings folded beneath a Victorian mourning coat argued over a jar of teeth. Two men in stained butcher’s aprons weighed powdered horn on brass scales. A child with silver eyes sat cross-legged on a luggage trolley, selling paper birds that struggled like living things. Nearby, a stall hung with surgical instruments displayed a handwritten sign: ORGANS BOUGHT. NO QUESTIONS. Quinn kept her weapon close to her side and walked through the barrier. Heads turned. Not all of them were human. A vendor with needles through his cheeks watched her pass. A hunched figure under a black umbrella sniffed the air and recoiled.
Somewhere behind the stalls, glass
shattered
. Voices rose—some in English, some in languages that scraped at her ears. She followed the blood along the platform edge. A man stepped from behind a curtain of red
silk
. He wore Herrera’s jacket, but Herrera was nowhere in sight. The man smiled with too many teeth. “New?” he asked. “Looking for someone.” His gaze slid down to the token in her hand. “Everyone is.” Quinn caught movement at the far end of the platform: Herrera, limping between two stalls, the package still clutched to his chest. Behind him, the thing in Morris’s coat moved through the crowd. People flattened themselves against walls to avoid it. Its head remained fixed forward, tracking Herrera with blind, terrible purpose. Quinn started after them. A hand closed around her arm. She turned, weapon rising, and found herself facing an old woman seated behind a stall covered in police badges. Dozens of them. Different forces, different decades. Some tarnished, some cracked, some stained dark. One bore Morris’s warrant number. The old woman’s eyes were cloud-white, but they fixed on Quinn with unnerving precision. “You shouldn’t have come down here, Detective Quinn.” “Where did you get that badge?” “The same place you’ll leave yours.” Quinn pulled free. “If you’re threatening me—” “I’m warning you.” A scream cut through the market. Herrera had fallen. The thing in Morris’s coat bent over him, its impossible fingers reaching for the package beneath his body. Herrera clung to it with both arms, his face twisted in pain. Quinn raised her weapon. The old woman seized Quinn’s wrist, surprisingly strong. “Shoot here,” she whispered, “and the Market will shoot back.” Around them, the crowd had gone still. Every eye watched her. Every hand moved toward some hidden blade, bottle,
charm
, or claw. For the second time that night, Quinn had to choose between the rules she understood and the darkness opening in front of her. She holstered the gun.
Then she drew her baton
and ran straight at the thing wearing her dead partner’s face.
created_at
"2026-07-25T18:14:10.464Z"
7/25/2026, 6:14:10 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3101
moderation_latency
(null)
generation_time
113878
tokens_prompt
888
tokens_completion
3840
native_tokens_prompt
910
native_tokens_completion
3199
native_tokens_completion_images
(null)
native_tokens_reasoning
379
native_tokens_cached
768
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
"stop"
service_tier
(null)
usage
0.0486414
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64fce0bd6c21e7b18fccfa"
is_byok
false
latency
3101
model_permaslug
"moonshotai/kimi-k3-20260715"
provider_name
"Moonshot AI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1785003250-g2sDPW7sW9Ih9QJjuUvS"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785003250-9OQHo6M7KI1wqFJs1N2u"
upstream_id
"chatcmpl-6a64fce0bd6c21e7b18fccfa"
total_cost
0.0486414
cache_discount
0.0020736
upstream_inference_cost
0
provider_name
"Moonshot AI"
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
"Herrera said softly [softly]"
dialogueSentences
35
tagDensity
0.257
leniency
0.514
rawRatio
0.111
effectiveRatio
0.057
95.34%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2148
totalAiIsmAdverbs
2
found
0
adverb
"sharply"
count
1
1
adverb
"softly"
count
1
highlights
0
"sharply"
1
"softly"
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)
83.71%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2148
totalAiIsms
7
found
0
word
"quickened"
count
1
1
word
"weight"
count
1
2
word
"flickered"
count
1
3
word
"streaming"
count
1
4
word
"shattered"
count
1
5
word
"silk"
count
1
6
word
"charm"
count
1
highlights
0
"quickened"
1
"weight"
2
"flickered"
3
"streaming"
4
"shattered"
5
"silk"
6
"charm"
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
232
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
2
hedgeCount
4
narrationSentences
232
filterMatches
0
"watch"
hedgeMatches
0
"appeared to"
1
"seemed to"
2
"tried to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
258
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
35
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2145
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
14
unquotedAttributions
0
matches
(empty)
50.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
88
wordCount
2017
uniqueNames
21
maxNameDensity
1.49
worstName
"Quinn"
maxWindowNameDensity
3.5
worstWindowName
"Quinn"
discoveredNames
Soho
2
Harlow
1
Quinn
30
Raven
1
Nest
2
Herrera
28
Seville
1
Saint
1
Christopher
1
Morris
7
Three
1
Camden
1
Metropolitan
1
Police
1
Professional
1
Standards
1
London
1
Underground
1
Victorian
1
English
1
Rain
4
persons
0
"Harlow"
1
"Quinn"
2
"Nest"
3
"Herrera"
4
"Saint"
5
"Christopher"
6
"Morris"
7
"Standards"
8
"Victorian"
9
"Rain"
places
0
"Soho"
1
"Raven"
2
"Seville"
3
"Professional"
4
"London"
5
"Underground"
6
"English"
globalScore
0.756
windowScore
0.5
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
155
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.466
wordCount
2145
matches
0
"not the thing in the coat, but the man"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
258
matches
0
"knew that coat"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
153
mean
14.02
std
15.62
cv
1.114
sampleLengths
0
22
1
66
2
10
3
2
4
7
5
63
6
10
7
6
8
7
9
6
10
48
11
2
12
6
13
35
14
8
15
42
16
10
17
8
18
6
19
26
20
2
21
5
22
9
23
53
24
6
25
9
26
32
27
9
28
3
29
4
30
39
31
7
32
4
33
3
34
28
35
7
36
7
37
6
38
47
39
8
40
6
41
13
42
4
43
44
44
1
45
3
46
57
47
48
48
2
49
2
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
2
totalSentences
232
matches
0
"been planned"
1
"was shaped"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
3
totalVerbs
346
matches
0
"was carrying"
1
"was checking"
2
"was already crossing"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
3
semicolonCount
0
flaggedSentences
3
totalSentences
258
ratio
0.012
matches
0
"No sound emerged, but Quinn felt it—inside her teeth, behind her eyes, in the old scar tissue at the base of her skull."
1
"Morris’s face came back to her—not the thing in the coat, but the man."
2
"Voices rose—some in English, some in languages that scraped at her ears."
88.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
2028
adjectiveStacks
2
stackExamples
0
"short curly dark hair,"
1
"aerial bent under her"
adverbCount
52
adverbRatio
0.02564102564102564
lyAdverbCount
12
lyAdverbRatio
0.005917159763313609
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
258
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
258
mean
8.31
std
5.99
cv
0.721
sampleLengths
0
22
1
25
2
18
3
6
4
2
5
15
6
10
7
2
8
7
9
33
10
3
11
10
12
17
13
10
14
6
15
7
16
6
17
10
18
19
19
10
20
9
21
2
22
6
23
13
24
10
25
12
26
8
27
8
28
4
29
6
30
24
31
10
32
8
33
6
34
4
35
16
36
6
37
2
38
3
39
2
40
9
41
27
42
7
43
4
44
15
45
6
46
9
47
6
48
3
49
6
57.36%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
12
diversityRatio
0.37209302325581395
totalSentences
258
uniqueOpeners
96
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
8
totalSentences
205
matches
0
"Then he twisted with a"
1
"Somewhere below, the alley door"
2
"Only darkness and the wet"
3
"Then something moved."
4
"Then the boards flickered back"
5
"Only water streaming from the"
6
"Somewhere behind the stalls, glass"
7
"Then she drew her baton"
ratio
0.039
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
46
totalSentences
205
matches
0
"She knew him by the"
1
"He paused at the curb,"
2
"He was checking for a"
3
"He moved with quick, economical"
4
"She gave him half a"
5
"She didn’t open it."
6
"She had learned that early"
7
"he would say"
8
"She reached the mouth of"
9
"Their eyes met through the"
10
"He vaulted a stack of"
11
"His heels kicked."
12
"he called down"
13
"She went after him."
14
"He looked down at her,"
15
"He reached the roof and"
16
"She followed without thinking, boots"
17
"She regained her balance and"
18
"She drew her sidearm."
19
"He cut through a shuttered"
ratio
0.224
89.27%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
152
totalSentences
205
matches
0
"The rain had been falling"
1
"Detective Harlow Quinn stood beneath"
2
"The bar’s green neon sign"
3
"Someone else knocked a bottle"
4
"Quinn checked the worn leather"
5
"Tomás Herrera had gone in"
6
"She knew him by the"
7
"NHS credential revoked eighteen months"
8
"Bodies with wounds that healed"
9
"Victims who vanished from hospital"
10
"The Nest’s door opened, throwing"
11
"Herrera stepped out beneath the"
12
"The Saint Christopher medallion at"
13
"He paused at the curb,"
14
"He was checking for a"
15
"Quinn lowered her face as"
16
"He moved with quick, economical"
17
"She gave him half a"
18
"Rain tapped the folded umbrella"
19
"She didn’t open it."
ratio
0.741
24.39%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
205
matches
0
"By the time they reached"
ratio
0.005
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
82
technicalSentenceCount
3
matches
0
"They simply ceased to be there, revealing a stairwell that descended into pulsing amber darkness."
1
"A child with silver eyes sat cross-legged on a luggage trolley, selling paper birds that struggled like living things."
2
"Voices rose—some in English, some in languages that scraped at her ears."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
9
uselessAdditionCount
0
matches
(empty)
64.29%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
7
fancyCount
3
fancyTags
0
"Quinn shouted (shout)"
1
"she whispered (whisper)"
2
"she whispered (whisper)"
dialogueSentences
35
tagDensity
0.2
leniency
0.4
rawRatio
0.429
effectiveRatio
0.171
91.7453%