NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-27-01M5YGYNZ9P974YDW5S2JHNWQX
Run Details
Model:
Kimi K3.1 Pro (Reasoning, Max)
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
9m 26s
Cost:
$0.155247
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
95.09%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
80.36%
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)
76.83%
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)
98.35%
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)
60.70%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
76.67%
Subject-first sentence starts
(details)
55.56%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
98.72%
Dialogue tag variety (said vs. fancy)
(details)
94.7424%
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
Herrera ran before Quinn reached
the middle of the road.
She had watched him leave
the Raven’s Nest just after one, the bar’s green neon washing his dark curls and black medical bag as he paused beneath the sign.
He had driven north without
speeding, signalled every turn, and parked neatly in Camden. Careful behaviour for a man with nothing to hide.
Quinn had followed at a
distance, certain he meant to lead her somewhere.
Now he was sprinting through
the rain with the bag clamped against his ribs. “Stop! Police!” Herrera glanced back.
Water streamed down his olive
face; his warm brown eyes looked almost black beneath the streetlamps.
Then he dodged between a
shuttered pharmacy and a chicken shop, and vanished into an alley.
Quinn swore and went after
him.
Rain needled her face and
plastered her closely cropped salt-and-pepper hair to her skull.
Her shoes struck water with
every third step.
Herrera was younger by twelve
years and faster in a straight line, but the bag made him clumsy.
He took the alley’s first
turning too wide, shoulder grazing brick, and she gained two strides. At forty-one, Quinn no longer mistook speed for control.
She paced her breathing and
watched his shoulders, not his feet.
Shoulders told you where a
man intended to go before his pride had finished lying about it.
She tugged her radio from
her coat. “Quinn, in foot pursuit. Male suspect, Tomás Herrera, moving north through Camden. Medical bag, dark coat.”
Static ate Control’s reply
. She caught only “units” and, a moment later, “six minutes.” Six minutes was an invitation to do something stupid.
Herrera kicked a rubbish bin
into her path.
Quinn planted one hand on
its lid and vaulted it.
The metal buckled under her
palm; she landed badly, pain spearing through her right knee, but kept moving. Ahead, Herrera’s Saint Christopher medallion had slipped free of his shirt.
It swung wildly on its
chain, flashing silver each time he passed beneath a light. “You’re making this worse!” she shouted. “Go back, Detective.” His voice carried no breathlessness. Only urgency. “Stop and I’ll consider it.” He ran faster.
They burst onto a road
where the late traffic had thinned to isolated cars. Herrera crossed against the lights. A taxi slammed on its brakes and skewed sideways, missing him by inches. Quinn put up a hand without looking and followed through the spray. The driver’s horn dopplered after them. Herrera ducked beneath scaffolding, shouldered through a door marked NO ACCESS, and disappeared. Quinn reached it four seconds later. The door opened onto a narrow service passage behind a row of shops. There were no lights except the red glow of an alarm above the far exit.
She drew her extendable baton
but did not open it. Herrera had run, not fought. So far. “Tomás,” she called. “There’s nowhere clever left to go.” Something clattered beyond the red exit.
She found him at the
end of the passage, dragging aside a sheet of corrugated hoarding.
His sleeve had ridden up
as he hauled at it, exposing the old knife scar along his left forearm. For an instant his eyes met hers through the gap. “Don’t follow me below,” he said. Then he was through. The space beyond had once been an entrance to the Underground. A condemned one, judging by the rusted gate and the sign wired to it: STRUCTURE UNSAFE. NO PUBLIC ACCESS. Herrera had forced the gate far enough to slip through. Wet stairs descended into darkness. Quinn stopped at the top. Sound rose from below. Not water. Not rats. Voices. Dozens of them, layered over the hollow strike of metal and something that might have been music played through a wall. The abandoned station smelled of damp stone, ozone, and a sweetness so dense it made her
think
of rotting flowers.
She checked the worn leather
watch
on her left wrist. One twenty-six. Backup would be looking for her on the street, if her transmission had gone through at all. Herrera’s
footsteps
echoed
down the stairs. Quinn went after him. The steps were slick with black silt.
Twice she had to catch
the wall. Old directional signs pointed toward ticket halls and platforms, their lettering scabbed by damp. The voices grew louder. So did another sound: a slow, regular tapping, like someone patiently testing a pipe with a fingernail. Her radio hissed. She raised it. “Quinn. Descending disused station entrance, east side of—” The hiss deepened into a chorus of whispers.
She nearly threw the thing
away. Instead she switched it off, told herself the circuitry had taken water, and continued down. The stairwell opened into a vaulted concourse. At its far end stood an iron gate where no gate belonged in the old plans she had studied before tonight’s surveillance. A bald man in a railway porter’s coat sat beside it on a wooden stool.
His collar was buttoned to
the throat despite the heat rising from below. Herrera stood at the gate, breathing hard.
He held up a small
white disc. The porter looked at it without moving his head. “Token.” Herrera pushed it closer. The disc was the colour of old ivory, but no ivory Quinn had seen carried that faint translucence at the edge. Bone. The porter opened the gate. Herrera slipped through. As he shoved the token toward his coat pocket, it struck his wet knuckles and fell. He did not notice. It spun across the threshold, struck the wall, and rolled back toward Quinn. Beyond the gate, light moved along a crowded platform. Not lamplight. Not anything she could comfortably name. Stalls had
been erected
between the tiled pillars. Their awnings sagged with moisture. People packed the narrow aisles, some in ordinary coats, others in clothes that
seemed borrowed from different centuries
. Above them hung a chalkboard: VEIL MARKET FINAL TRADING NIGHT IN CAMDEN Beneath the words someone had drawn a full moon. Herrera turned and saw Quinn at the foot of the stairs. “Detective,” he called. “Don’t.” There was no triumph in his face. No contempt. He
looked afraid
.
Then the crowd folded around
him. The porter
began to
close the gate. Quinn picked up the token. It was colder than the stairwell. A design had
been carved
into one side: an open door with a single vertical line through it. The same design, she realized, had
been inked
on the inside of DS Morris’s wrist when his body
was found
three years ago. The pathologist had called it a tattoo. There had been no record of Morris ever getting one, and Quinn had seen every inch of his arms often enough to know he hadn’t. Her hand closed around the bone. The porter watched her. “Token or turn around.” She showed him her warrant card. He leaned forward, studied it, and sat back. “That’s tin.” “Metropolitan Police. That gate stays open.” “No,” he said. It was the flatness of it that stopped her. Not defiance.
Simply a man stating that
rain fell downward. Beyond him, something laughed in a glass bottle. Quinn looked toward the sound and saw a vendor stopper a cloudy jar. The laughter stopped. Her mind offered explanations with increasing desperation. An illegal rave. A drug market. Performers in costume. An elaborate set built by people with too much money and no fear of prosecution. None explained why the platform
appeared to
extend farther than the station above it. The porter held out his hand for the token. Every hour of Quinn’s eighteen years in the job told her to wait. Unknown location. No communications. No reliable description for backup. One suspect who knew the ground and dozens of
potential
hostiles beyond the gate. Entering alone would be indefensible. Morris had gone below alone too. The official findings on his death had contained the words unexplained and inconclusive, arranged with great care so no one had to write impossible. Quinn had spent three years telling herself that procedure would have saved him. That if he had waited, if she had reached him sooner, if either of them had obeyed the rules they taught to children in uniform, he would still be complaining about her coffee. The porter’s fingers curled impatiently. Quinn looked at the chalkboard again. Final trading night. Whatever this place was, it would not be here when backup arrived. She scored an arrow into the soft brick beside the stairs with her baton tip and added a Q beneath it. A poor trail, but better than none.
Then she put away her
badge and gave the porter the token. He dropped it into a leather pouch. “Market peace holds under the roof. No seizures. No badges. No blood unless you mean to sell it.” “I’m looking for one man.” “Everyone is.” He opened the gate. Quinn stepped through. The iron struck home behind her with a note she felt through the soles of her shoes. The
watch
on her left wrist gave a tiny
mechanical
stutter. Its second hand jumped backward, hesitated, and resumed. She did not look at it again. Inside, the market smelled of wet wool, copper, crushed herbs, and smoke. Along the old platform edge, jars of crimson liquid
pulsed
gently
though nothing touched their shelf. A sign above another stall read UNLICENSED ALCHEMY in neat capitals. Farther on, a veiled woman sold envelopes from a locked cabinet. QUESTIONS ANSWERED, her sign promised. NO REFUNDS ON BAD NEWS. A man brushed past Quinn carrying a birdcage covered in black cloth. Something inside whispered his name until he struck the bars. Quinn kept moving. Wonder was a luxury. Fear could queue behind it. She caught sight of Herrera’s bag near the mouth of the west tunnel. He
was forcing
his way through the crowd,
no longer running but
still fast. Quinn followed, using her height and shoulders, ignoring the protests in several languages. When he looked back, she was close enough to see the resignation cross his face. He turned toward the tunnel. Quinn lunged, caught the bag’s strap, and hauled him backward. Herrera stumbled. She drove him against the tiled wall and pinned his left arm before he could recover. The old scar pressed rigid beneath her fingers. “Enough,” she said. He did not struggle. “Let go.” “You ran from police.” “There’s a boy through that tunnel with a wound I can’t treat in the street.” “Convenient.” “Yes,” Herrera said, anger finally roughening his voice. “Very convenient for him.” His medical bag had fallen open. Quinn saw bandages, a sealed syringe, two bottles marked in handwriting, and a child’s woollen glove soaked dark with blood. She did not release him. Around them, the market had gone quiet. Not all at once. The
silence
spread by stalls, as though each trader had noticed something and nudged the next. A shutter slammed. Somewhere glass broke. The tapping Quinn had heard on the stairs stopped. Herrera stared into the unlit tunnel. “We need to move,” he said. “We’re going back to the gate.” “No.” His gaze dropped to her hand on his arm. When he looked up again, his fear had become something older and more tired. “If we’re still standing here when it reaches the concourse, you’ll want walls between you and it. Thick ones.” “What will?” “Stay close to me. Don’t buy anything, don’t accept anything, and if you hear your name, don’t answer.” Quinn almost laughed.
Then she saw that his
free hand had closed around the Saint Christopher medallion at his throat. “You’re still coming with me,” she said. “If we get out.” She pulled him away from the wall. From the tunnel came the faint crackle of a damaged radio. Herrera froze. A man’s voice spoke through the static, low and
familiar
, with the slight catch at the end of each sentence that Quinn had once teased him for. “Harlow?” Her grip loosened. She had
heard that voice
in dreams for three years. Awake, she had sometimes caught it in a crowded station or passing car, always gone before she could turn.
Now it spoke from no
more than twenty feet away. “Harlow. You took your time.” Herrera seized her wrist. “Detective,” he whispered. “Whatever it says, don’t answer.”
created_at
"2026-10-27T11:11:59.989Z"
10/27/2026, 11:11:59 AM
model
"moonshotai/kimi-k3.1-pro-20261023"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3222
moderation_latency
(null)
generation_time
566202
tokens_prompt
888
tokens_completion
17225
native_tokens_prompt
909
native_tokens_completion
15389
native_tokens_completion_images
(null)
native_tokens_reasoning
12700
native_tokens_cached
256
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
0.1552472
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.1; linux; x64))"
http_referer
(null)
request_id
"req-1793099519-lcgfxhbLoHveqlin18md"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1793099519-xomNCYBtc9evCqlNluOx"
upstream_id
"chatcmpl-6ae0870159bad9cc673a782b"
provider_responses
0
endpoint_id
"a3fafaac-f097-4ef1-86b3-842854dad5c6"
id
"chatcmpl-6ae0870159bad9cc673a782b"
is_byok
false
latency
3222
model_permaslug
"moonshotai/kimi-k3.1-pro-20261023"
provider_name
"Moonshot AI"
status
200
total_cost
0.1552472
cache_discount
0.0004608
upstream_inference_cost
0
provider_name
"Moonshot AI"
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
13
adverbTagCount
1
adverbTags
0
"She caught only [only]"
dialogueSentences
39
tagDensity
0.333
leniency
0.667
rawRatio
0.077
effectiveRatio
0.051
95.09%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2037
totalAiIsmAdverbs
2
found
0
adverb
"gently"
count
1
1
adverb
"very"
count
1
highlights
0
"gently"
1
"very"
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)
80.36%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2037
totalAiIsms
8
found
0
word
"structure"
count
1
1
word
"footsteps"
count
1
2
word
"echoed"
count
1
3
word
"potential"
count
1
4
word
"mechanical"
count
1
5
word
"pulsed"
count
1
6
word
"silence"
count
1
7
word
"familiar"
count
1
highlights
0
"structure"
1
"footsteps"
2
"echoed"
3
"potential"
4
"mechanical"
5
"pulsed"
6
"silence"
7
"familiar"
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
1
narrationSentences
203
matches
0
"looked afraid"
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
2
hedgeCount
3
narrationSentences
203
filterMatches
0
"think"
1
"watch"
hedgeMatches
0
"tended to"
1
"began to"
2
"appeared to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
229
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
33
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2037
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
14
unquotedAttributions
0
matches
(empty)
76.83%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
60
wordCount
1845
uniqueNames
11
maxNameDensity
1.46
worstName
"Quinn"
maxWindowNameDensity
2.5
worstWindowName
"Quinn"
discoveredNames
Quinn
27
Raven
1
Nest
1
Camden
1
Control
1
Six
1
Herrera
20
Saint
2
Christopher
2
Underground
1
Morris
3
persons
0
"Quinn"
1
"Raven"
2
"Control"
3
"Herrera"
4
"Saint"
5
"Christopher"
6
"Morris"
places
0
"Camden"
1
"Underground"
globalScore
0.768
windowScore
0.833
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
132
glossingSentenceCount
1
matches
0
"seemed borrowed from different centuries"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.491
wordCount
2037
matches
0
"no longer running but"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
3
totalSentences
229
matches
0
"stating that rain"
1
"saw that his"
2
"heard that voice"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
112
mean
18.19
std
18.46
cv
1.015
sampleLengths
0
10
1
65
2
14
3
2
4
35
5
6
6
56
7
37
8
37
9
9
10
62
11
6
12
3
13
7
14
5
15
3
16
50
17
13
18
51
19
9
20
6
21
45
22
6
23
4
24
45
25
5
26
4
27
46
28
29
29
6
30
4
31
49
32
6
33
8
34
8
35
21
36
57
37
14
38
10
39
26
40
5
41
36
42
9
43
8
44
36
45
7
46
9
47
11
48
4
49
12
98.35%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
4
totalSentences
203
matches
0
"was buttoned"
1
"been erected"
2
"been carved"
3
"been inked"
4
"was found"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
2
totalVerbs
330
matches
0
"was sprinting"
1
"was forcing"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
2
flaggedSentences
2
totalSentences
229
ratio
0.009
matches
0
"Water streamed down his olive face; his warm brown eyes looked almost black beneath the streetlamps."
1
"The metal buckled under her palm; she landed badly, pain spearing through her right knee, but kept moving."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1849
adjectiveStacks
0
stackExamples
(empty)
adverbCount
65
adverbRatio
0.035154137371552194
lyAdverbCount
14
lyAdverbRatio
0.0075716603569497025
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
229
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
229
mean
8.9
std
6.04
cv
0.679
sampleLengths
0
10
1
29
2
14
3
9
4
13
5
14
6
2
7
3
8
16
9
16
10
6
11
14
12
8
13
18
14
16
15
9
16
11
17
17
18
7
19
20
20
10
21
9
22
8
23
10
24
18
25
11
26
15
27
6
28
3
29
5
30
2
31
5
32
3
33
14
34
5
35
13
36
12
37
6
38
13
39
6
40
13
41
15
42
10
43
5
44
2
45
3
46
6
47
6
48
16
49
19
60.70%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
6
diversityRatio
0.3799126637554585
totalSentences
229
uniqueOpeners
87
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
9
totalSentences
180
matches
0
"Then he dodged between a"
1
"Then he was through."
2
"Twice she had to catch"
3
"Instead she switched it off,"
4
"Then the crowd folded around"
5
"Simply a man stating that"
6
"Then she put away her"
7
"Somewhere glass broke."
8
"Then she saw that his"
ratio
0.05
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
46
totalSentences
180
matches
0
"She had watched him leave"
1
"He had driven north without"
2
"Her shoes struck water with"
3
"He took the alley’s first"
4
"She paced her breathing and"
5
"She tugged her radio from"
6
"She caught only and, a"
7
"It swung wildly on its"
8
"His voice carried no breathlessness."
9
"He ran faster."
10
"They burst onto a road"
11
"She drew her extendable baton"
12
"She found him at the"
13
"His sleeve had ridden up"
14
"She checked the worn leather"
15
"Her radio hissed."
16
"She raised it."
17
"She nearly threw the thing"
18
"His collar was buttoned to"
19
"He held up a small"
ratio
0.256
76.67%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
138
totalSentences
180
matches
0
"Herrera ran before Quinn reached"
1
"She had watched him leave"
2
"He had driven north without"
3
"Quinn had followed at a"
4
"Herrera glanced back."
5
"Water streamed down his olive"
6
"Quinn swore and went after"
7
"Rain needled her face and"
8
"Her shoes struck water with"
9
"Herrera was younger by twelve"
10
"He took the alley’s first"
11
"She paced her breathing and"
12
"Shoulders told you where a"
13
"She tugged her radio from"
14
"Static ate Control’s reply"
15
"She caught only and, a"
16
"Herrera kicked a rubbish bin"
17
"Quinn planted one hand on"
18
"The metal buckled under her"
19
"It swung wildly on its"
ratio
0.767
55.56%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
2
totalSentences
180
matches
0
"Now he was sprinting through"
1
"Now it spoke from no"
ratio
0.011
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
83
technicalSentenceCount
3
matches
0
"Dozens of them, layered over the hollow strike of metal and something that might have been music played through a wall."
1
"People packed the narrow aisles, some in ordinary coats, others in clothes that seemed borrowed from different centuries."
2
"The silence spread by stalls, as though each trader had noticed something and nudged the next."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
13
uselessAdditionCount
0
matches
(empty)
98.72%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
10
fancyCount
2
fancyTags
0
"she shouted (shout)"
1
"he whispered (whisper)"
dialogueSentences
39
tagDensity
0.256
leniency
0.513
rawRatio
0.2
effectiveRatio
0.103
94.7424%