NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ72KFB9C5ZC2YM0VPMS337X
Run Details
Model:
Qwen 3.6 27B
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
1m 33s
Cost:
$0.014204
Provider:
Morph
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
83.99%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
65.31%
AI-ism word frequency
(details)
100.00%
Cliché density
(details)
100.00%
Emotion telling (show vs. tell)
(details)
90.43%
Filter word density
(details)
100.00%
Gibberish response detection
(details)
100.00%
Markdown formatting overuse
(details)
100.00%
Missing dialogue indicators (quotation marks)
(details)
97.45%
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)
89.17%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
94.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
50.00%
Sentence opener variety
(details)
34.72%
Adverb-first sentence starts
(details)
65.83%
Pronoun-first sentence starts
(details)
69.38%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
44.82%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
81.03%
Dialogue tag variety (said vs. fancy)
(details)
82.2048%
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="4414" name="Eva Kowalski" aliases="Eva, Evie" pronouns="she/her" species="Human" storyRole="Best Friend"> <eyeColor>green</eyeColor> <hair>curly red</hair> <height>5'4"</height> <age>26</age> <glasses>round glasses</glasses> <satchel>worn leather satchel full of books</satchel> <freckles>freckled complexion</freckles> <nervousHabit>tucking hair behind her left ear</nervousHabit> <description>Aurora's childhood friend and an occult researcher.</description> <backstory>Moved to London two years before Aurora and works as a research assistant at the British Museum's restricted archives. She holds a master's degree in Ancient History from Oxford.</backstory> </character> <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> <item id="2004" name="Veil Compass" aliases="the Compass, shadow compass" type="Tool" origin="The Veil Market"> <casingMaterial>small brass compass</casingMaterial> <faceMarkings>face etched with protective sigils</faceMarkings> <needle>points toward the nearest supernatural rift or portal</needle> <patina>casing has a patina of verdigris</patina> <creator>crafted by a Shade artisan</creator> <description>A compass attuned to supernatural energy.</description> </item> </codex> Write a fully fleshed out scene of at least 1000 words in the mystery genre. A detective arrives at a crime scene in an unusual location. Something is wrong — the evidence doesn't add up. A colleague is present, offering a different interpretation. Through careful observation and deduction, the detective begins to see what others have missed. 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 iron service ladder groaned
under her
weight
, each rung slick with condensation that smelled of oxidized copper and old damp.
Harlow Quinn descended step by
step, her movements
measured
, her posture locked into the rigid economy of eighteen years on the force. At five-nine, she had learned long ago to make space without demanding it, to let her presence settle into a room rather than explode into it.
She cleared the final step
and stood on the grated access platform, tapping the heel of her boot once against the steel to test the footing before stepping beyond the yellow caution tape.
The maintenance vault belonged to
a decommissioned rail spur buried beneath Camden, a concrete intestine sealed since the nineties.
Emergency bulbs flickered overhead, casting
long, nervous shadows that made the walls
seem to
breathe. The air was cold, dry, and carried a faint metallic tang that had nothing to do with rust.
Quinn pulled a thin wool
scarf from around her neck and wrapped it
loosely
over her lower face.
Her brown eyes tracked the
perimeter, cataloging the usual choreography of a contained scene: evidence markers, camera tripods, the quiet hum of forensic equipment. But the geometry of it was wrong.
Sergeant Miller stood by the
far wall, a clipboard pressed to his chest like a shield.
He was a broad-shouldered veteran
with a face worn smooth by too many nights like this, and he met her with the automatic
tension
of a man who already knew the room
was speaking
a language he couldn’t parse. “Detective Quinn,”
he said, voice echoing slightly
in the hollow space. “We’ve got it cordoned off. Metro confirmed the sub-level hasn’t been active since the track closure. No maintenance logs, no contractor permits. Whoever was down here broke in.” “Or was already here,” Quinn murmured.
She adjusted the worn leather
watch
on her left wrist, checking the time out of habit rather than need.
The second hand swept past
the twelve.
She moved past him, boots
clicking crisply against the grated flooring, and stopped just short of the body. Victim lay on his side, curled tight against a concrete pillar. Male, mid-thirties, dressed in dark cotton trousers and a tailored wool coat that looked far too expensive for a condemned maintenance crawl.
A neat evidence card marked
his position beside a cluster of chalk outlines that didn’t
quite match his posture
.
Something about the arrangement made
Quinn’s chest tighten.
She crouched, knees bending with
deliberate control, and studied the scene from a low angle.
The dust told the first
lie. Thick, gray particulate coated the floor in an even blanket, disturbed only by two sets of prints leading toward the body and a single set retreating. But there were no scuff marks at the victim’s heels. No drag lines. No overturned tools, no knocked-over crates, no signs of a struggle that matched the violence written into his throat.
His collar was shredded, the
fabric torn upward in jagged ribbons, but there was no blood spatter on the low-hanging conduit pipes above him. No arterial spray. No pooled crimson near his head.
Just clean concrete and that
impossibly heavy
silence
. “Pathology’s holding off until the temperature stabilizes,” Miller said, falling into step behind her as she rose.
He flipped his pen between
his fingers. “Initial scan suggests blunt force trauma to the carotid, but there’s no matching impact site on the walls or the floor. No weapons recovered. No footprints beyond his own and the first responder’s. It’s like he just… folded.” “Gas leak,”
Quinn said, though the words felt thin
. “Industrial fume exposure. Maybe a fall from the service ladder, striking him on the way down.” Miller nodded, relief easing his shoulders by a fraction. “That’s working theory. We’re pulling the environmental samples now. If there’s residual methane or carbon monoxide, we’ll push it as an accidental asphyxiation with post-mortem trauma. It happens. People trip in the dark, catch their throat on a pipe, bleed out quietly.” Quinn didn’t answer.
She stepped forward, close enough
to see the fine details Miller’s distance had smoothed over. The wool of the victim’s coat
was singed
along the right shoulder, but the fabric wasn’t burned through.
It was brittle, cracked in
a fine web pattern that suggested intense, brief heat.
She extended two gloved fingers
and touched the air above the scorching. Cold. Not room temperature. Colder. The air right above the victim’s torso held a hollow
chill
that made her skin prickle.
She glanced at the ceiling
conduit. The paint around the nearest junction box
was blistered
, but the metal itself was smooth, unwarped. No electrical arc. No transformer rupture. “Run the environmental data,”
she said, voice quiet but
edged with steel. “I want particulate analysis on the floor dust near the pillar. And I want you to check the door seals on the main hatch.” Miller’s pen stopped moving. “The hatch is intact. Bolts are unbroken. We came in through the secondary maintenance shaft because the primary lock was fused shut from the outside. Whatever happened down here, it didn’t involve forced entry.” “Then how did they get in?” Quinn asked. He frowned, shifting his
weight
. “They didn’t. That’s the thing. The scene’s sealed. The victim’s prints are the only ones that match a clean entry. No tools, no pry marks, no soil transfer from the shaft. It’s clean. Too clean, maybe, but we’ve had break-ins that went undetected for days. Maybe this was just bad luck meeting a maintenance crawl.” Quinn turned
slowly
,
scanning
the pillar. The concrete
was pitted
, scarred by decades of vibration and damp, but one section near the victim’s head was unnaturally smooth.
She knelt again, pulling a
small evidence brush from her coat pocket and sweeping a faint gray residue into a petri dish.
She tilted it toward the
flickering bulb. The dust wasn’t uniform. It settled in concentric rings, delicate as ripples, radiating outward from a central point three inches above the concrete. Not footprints. Not impact. Displacement.
She closed her eyes for
a second, letting the architecture of the room realign in her mind. Eighteen years on the Met had taught her to trust the negative space first. The absence of blood, the absence of spatter, the absence of thermal degradation on the metal—these weren’t oversights. They were boundaries. Something had happened here that didn’t transfer mass in the way conventional physics expected. The scorch on the coat was surface-level. The
chill
in the air
was localized
. The dust rings pointed to a pressure differential, a sudden vacuum that had pulled particulate outward before it settled. “Miller,” she said, opening her eyes. “When did the first responder arrive?” “Twenty minutes ago. Dispatch flagged it when a utility worker reported a strange hum near the Camden access point. He backed out fast. We secured the shaft five minutes after that.” “Twenty minutes,” Quinn repeated. She stood, wiping her gloved hands on her trousers. “But the victim’s body temperature is consistent with death occurring at least two hours ago. Rigor’s
not fully set in, but the skin pallor
and the lack of post-mortem pooling suggest he’s been here longer than the first response window allows. The body was moved, Miller. Or the scene was staged after the fact.” The sergeant’s jaw tightened. “Staged by who? The only prints are his own and the worker’s. We’ve got CSI running Luminol and alternate light sources now, but if someone wiped it down, they used solvents. Solvents leave a residue. We’re not picking anything up.” “Because they didn’t wipe it,” Quinn said quietly. She stepped toward the smooth patch of concrete, studying the way the emergency light caught the faint sheen of moisture that shouldn’t be there. Cold condensation. She pressed a gloved thumb against the wall. It left a faint impression, like pressed wax. “They didn’t clean a crime scene, Miller. They sealed a threshold.” He stared at her, the clipboard slipping
slightly
in his grip. “Threshold? Detective, we’re two levels underground in a decommissioned rail maintenance vault. There are no thresholds. There’s concrete, rusted steel, and dead men. I’m not filing a report on metaphysical entry points.” “I’m not asking you to,” she said, voice level, sharp at the edges. “I’m asking you to look at the geometry. The door was never the point of entry. The bolts are unbroken because no one turned a key or cut a lock. The shaft access was fused from the outside, which means whatever happened here generated enough thermal or electromagnetic discharge to weld the metal shut from beyond the door. The victim wasn’t attacked down here. He was pulled. Or stepped through. The scuff marks on his heels curve inward, not outward. He didn’t fall. He was drawn toward that pillar.” She let the words hang, watching Miller’s face tighten as the implications settled over him like a dropped curtain. She had seen this exact pattern of impossibility before. Three years ago. A warehouse in Shoreditch. A body with
shattered
ribs but no blunt force impact. A room that smelled of ozone and damp earth. And her partner, DS Morris, standing over the chalk outline with that same hollow look in his eyes before the unexplained took him. She still woke with the
echo
of his voice in her head, still
traced
the missing pieces in the quiet hours before dawn. The Met had closed the file. Called it structural collapse. Called it coincidence. Quinn had stopped believing in coincidence the day she found his badge in a riverbank with no memory of how it got there. “Pull the secondary footage from the Camden station cameras,” she said, turning back toward the access ladder. “I want every frame from the last seventy-two hours. I want the utility company’s maintenance logs for this sector. And I want you to hold the environmental samples. Do not release them to the central lab until I’ve reviewed the particulate breakdown.” Miller recovered
quickly
, the procedural armor sliding back into place. “Understood. I’ll have tech pull the footage. What’s your call on the cause?” “I’m not filing anything yet,” Quinn said. She reached the ladder, one hand braced on the cold iron, the other resting
lightly
over her left wrist where the worn leather strap of her
watch
pressed into her skin. “We’re not looking at a break-in. We’re looking at a breach. And if the evidence behaves any way other than how it wants to, we’ll be chasing ghosts again.” She climbed, step by step, the metallic groan of the ladder rising behind her. Above, the rain still hammered against the hatch, a steady, indifferent rhythm. Quinn didn’t rush. She had learned patience the hard way, through files that refused to close and rooms that defied the rules of gravity and temperature. The Metropolitan Police ran on procedure, on clean lines and quantifiable cause and effect. But the world beneath it all did not. It shifted. It concealed. It waited. She would follow the dust patterns. She would trace the cold air and the fused bolts and the impossible absence of blood. She would piece together what the scene had
tried to
hide. And when the full picture finally clicked into place, she would not look away.
created_at
"2026-04-27T08:58:55.216Z"
4/27/2026, 8:58:55 AM
model
"qwen/qwen3.6-27b-20260422"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1033
moderation_latency
(null)
generation_time
92702
tokens_prompt
923
tokens_completion
6553
native_tokens_prompt
905
native_tokens_completion
5711
native_tokens_completion_images
(null)
native_tokens_reasoning
3612
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
"stop"
usage
0.01420415
router
(null)
provider_responses
0
endpoint_id
"826cab4e-dc26-4472-83be-e4ddd5ebd2ab"
id
"9726dabba17c49a58ca34f53fea0c65c"
is_byok
false
latency
775
model_permaslug
"qwen/qwen3.6-27b-20260422"
provider_name
"Morph"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777280335-xMWbOG8IRhSV5odTplbf"
session_id
(null)
api_type
"completions"
id
"gen-1777280335-ZJt9tI33Twx0W6UmcDEm"
upstream_id
"9726dabba17c49a58ca34f53fea0c65c"
total_cost
0.01420415
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Morph"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
12
adverbTagCount
1
adverbTags
0
"Quinn said quietly [quietly]"
dialogueSentences
29
tagDensity
0.414
leniency
0.828
rawRatio
0.083
effectiveRatio
0.069
83.99%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1874
totalAiIsmAdverbs
6
found
0
adverb
"loosely"
count
1
1
adverb
"slightly"
count
2
2
adverb
"slowly"
count
1
3
adverb
"quickly"
count
1
4
adverb
"lightly"
count
1
highlights
0
"loosely"
1
"slightly"
2
"slowly"
3
"quickly"
4
"lightly"
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)
65.31%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1874
totalAiIsms
13
found
0
word
"weight"
count
2
1
word
"measured"
count
1
2
word
"flickered"
count
1
3
word
"tension"
count
1
4
word
"echoing"
count
1
5
word
"silence"
count
1
6
word
"chill"
count
2
7
word
"scanning"
count
1
8
word
"shattered"
count
1
9
word
"echo"
count
1
10
word
"traced"
count
1
highlights
0
"weight"
1
"measured"
2
"flickered"
3
"tension"
4
"echoing"
5
"silence"
6
"chill"
7
"scanning"
8
"shattered"
9
"echo"
10
"traced"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
0
maxInWindow
0
found
(empty)
highlights
(empty)
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
109
matches
(empty)
90.43%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
2
hedgeCount
2
narrationSentences
109
filterMatches
0
"watch"
hedgeMatches
0
"seem to"
1
"tried to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
126
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
89
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1873
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
19
unquotedAttributions
0
matches
(empty)
97.45%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
27
wordCount
1237
uniqueNames
8
maxNameDensity
1.05
worstName
"Quinn"
maxWindowNameDensity
2
worstWindowName
"Quinn"
discoveredNames
Quinn
13
Camden
1
Miller
7
Met
2
Shoreditch
1
Morris
1
Metropolitan
1
Police
1
persons
0
"Quinn"
1
"Miller"
2
"Met"
3
"Morris"
4
"Police"
places
0
"Shoreditch"
globalScore
0.975
windowScore
1
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
78
glossingSentenceCount
1
matches
0
"quite match his posture"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.534
wordCount
1873
matches
0
"not fully set in, but the skin pallor"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
126
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
32
mean
58.53
std
30.19
cv
0.516
sampleLengths
0
102
1
101
2
55
3
39
4
50
5
75
6
6
7
99
8
62
9
25
10
51
11
62
12
49
13
36
14
38
15
8
16
60
17
84
18
99
19
12
20
31
21
67
22
44
23
61
24
43
25
102
26
136
27
59
28
23
29
67
30
80
31
47
89.17%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
5
totalSentences
109
matches
0
"was shredded"
1
"was singed"
2
"was blistered"
3
"was pitted"
4
"was localized"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
1
totalVerbs
221
matches
0
"was speaking"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
1
semicolonCount
0
flaggedSentences
1
totalSentences
126
ratio
0.008
matches
0
"The absence of blood, the absence of spatter, the absence of thermal degradation on the metal—these weren’t oversights."
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1244
adjectiveStacks
1
stackExamples
0
"suggested intense, brief heat."
adverbCount
32
adverbRatio
0.02572347266881029
lyAdverbCount
12
lyAdverbRatio
0.00964630225080386
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
126
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
126
mean
14.87
std
12.79
cv
0.86
sampleLengths
0
21
1
22
2
26
3
33
4
19
5
15
6
18
7
18
8
24
9
7
10
16
11
39
12
11
13
28
14
6
15
19
16
7
17
18
18
11
19
22
20
19
21
8
22
15
23
6
24
26
25
10
26
3
27
19
28
24
29
3
30
6
31
8
32
17
33
7
34
38
35
9
36
16
37
9
38
42
39
3
40
15
41
18
42
14
43
12
44
1
45
3
46
1
47
16
48
6
49
16
50.00%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
17
diversityRatio
0.38095238095238093
totalSentences
126
uniqueOpeners
48
34.72%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
96
matches
0
"Just clean concrete and that"
ratio
0.01
65.83%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
37
totalSentences
96
matches
0
"She cleared the final step"
1
"Her brown eyes tracked the"
2
"He was a broad-shouldered veteran"
3
"he said, voice echoing slightly"
4
"She adjusted the worn leather"
5
"She moved past him, boots"
6
"She crouched, knees bending with"
7
"His collar was shredded, the"
8
"He flipped his pen between"
9
"She stepped forward, close enough"
10
"It was brittle, cracked in"
11
"She extended two gloved fingers"
12
"She glanced at the ceiling"
13
"she said, voice quiet but"
14
"He frowned, shifting his weight."
15
"She knelt again, pulling a"
16
"She tilted it toward the"
17
"It settled in concentric rings,"
18
"She closed her eyes for"
19
"They were boundaries."
ratio
0.385
69.38%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
75
totalSentences
96
matches
0
"The iron service ladder groaned"
1
"Harlow Quinn descended step by"
2
"She cleared the final step"
3
"The maintenance vault belonged to"
4
"Emergency bulbs flickered overhead, casting"
5
"The air was cold, dry,"
6
"Quinn pulled a thin wool"
7
"Her brown eyes tracked the"
8
"Sergeant Miller stood by the"
9
"He was a broad-shouldered veteran"
10
"he said, voice echoing slightly"
11
"She adjusted the worn leather"
12
"The second hand swept past"
13
"She moved past him, boots"
14
"Victim lay on his side,"
15
"A neat evidence card marked"
16
"Something about the arrangement made"
17
"She crouched, knees bending with"
18
"The dust told the first"
19
"His collar was shredded, the"
ratio
0.781
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
96
matches
(empty)
ratio
0
44.82%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
51
technicalSentenceCount
7
matches
0
"The iron service ladder groaned under her weight, each rung slick with condensation that smelled of oxidized copper and old damp."
1
"Emergency bulbs flickered overhead, casting long, nervous shadows that made the walls seem to breathe."
2
"The air was cold, dry, and carried a faint metallic tang that had nothing to do with rust."
3
"Male, mid-thirties, dressed in dark cotton trousers and a tailored wool coat that looked far too expensive for a condemned maintenance crawl."
4
"The air right above the victim’s torso held a hollow chill that made her skin prickle."
5
"The dust rings pointed to a pressure differential, a sudden vacuum that had pulled particulate outward before it settled."
6
"She stepped toward the smooth patch of concrete, studying the way the emergency light caught the faint sheen of moisture that shouldn’t be there."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
12
uselessAdditionCount
3
matches
0
"he said, voice echoing slightly in the hollow space"
1
"Quinn said, though the words felt thin"
2
"she said, voice quiet but edged with steel"
81.03%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
12
fancyCount
2
fancyTags
0
"Quinn murmured (murmur)"
1
"Quinn repeated (repeat)"
dialogueSentences
29
tagDensity
0.414
leniency
0.828
rawRatio
0.167
effectiveRatio
0.138
82.2048%