NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08C58JE2ZQ7YJKRJNHS4M0
Run Details
Model:
GPT-5.4 Mini
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
16.9s
Cost:
$0.015035
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
93.90%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
81.69%
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)
6.97%
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)
46.64%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
34.07%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
90.34%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
88.4538%
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="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> Continue the story using the following instructions: <instructions> 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. </instructions>
Model response
Messages
Meta
AI
The Tube stairs groaned under
Detective Harlow Quinn’s boots as she came down into the station that did not exist on any map.
The air below Camden tasted
of rust, wet concrete, and something sharper that clung at the back of her throat. Old tiles shone under portable lamps, their cream glaze cracked into spiderwebs.
A platform stretched ahead, empty
apart from crime scene tape, three white evidence markers, and a body bag laid out like a dropped coat.
Someone had printed the name
of the station on a yellowing sign and hung it above the tracks with string. Bishop’s Close.
Quinn lifted her gaze to
it, then to the black tunnel mouths beyond the platform edge. “Not your
standard
Friday night, is it?”
Eva Kowalski stood beside a
folding table covered in paper bags, her round glasses catching the lamp glare.
She pushed a curl of
red hair behind her left ear and held up a small brass compass between two fingers. Verdigris coated the casing. The face markings looked wrong, too sharp for a thing that old.
Quinn slowed at the bottom
step. “You brought a toy to a death scene.” Eva’s mouth twitched. “You say that like it wasn’t pointed at the tunnel from the moment I got down here.” Quinn crossed to the table.
The compass needle quivered, then
swung hard toward the far end of the platform where the tunnel sank into darkness. “That’s not
standard
equipment.” “It came out of a warded drawer in the restricted archives three months ago.”
Eva turned the compass in
her palm. “I logged it, checked the provenance, and nearly had a stroke when it reacted to a sealed report about rift activity in Soho. I thought you’d want to know.”
Quinn slipped on gloves, her
worn leather
watch
catching the light as she flexed her left wrist.
She looked past the compass
to the body bag. “Who’s on the slab?” “Male, late twenties. No ID yet. Cleaner found him while the council team did a sweep for squatters.”
Eva tipped her chin toward
the platform. “The cleaners won’t come near the tunnel now.”
Quinn’s eyes moved over the
scene with the same
measured
pace she gave a suspect’s face. “Why not?” Eva huffed a breath. “Because his shoes were placed beside him. Because there were no marks on the platform from a struggle. Because the body was found fifty feet from the access stairs with his coat folded neatly on the bench.”
Quinn’s gaze dropped to the
bench. A dark wool coat lay there with careful folds, one sleeve draped over the other, as if someone had sat and folded it by hand. “No blood?” “Not much.” Eva pointed to the concrete between the bench and the body bag. “A few drops. Pathologist’s still upstairs. He’s calling it either a stabbing or a bite mark. London Forensic’s been sniffing at the tunnels since dawn, and they’re already out of their depth.” Quinn gave the platform another look. “And you?” “I’m not in their budget.” The overhead lamp buzzed. Quinn crouched beside the nearest evidence marker.
It sat beside a smear
on the concrete. Not blood.
Too dark for that, too
greasy at the edges.
She touched the smear with
a gloved finger, then rubbed it between thumb and forefinger. Powdery grit. Coal dust. Her
eyes narrowed
. “Why was there coal dust down here?” Eva frowned. “There wasn’t any on the body.” Quinn stood and moved to the bench. Her hand skimmed the seat. Cold, damp, no grit.
She bent and checked the
floor beneath it. Coal dust there too, gathered in a fine crescent under the legs. Old and recent together, layered over a decade of grime. She glanced toward the tracks. “Who found him?” “Two council cleaners. One of them fainted, the other screamed into her radio and called police.” “Where are they?” “Upstairs. One’s being questioned. The other’s with a paramedic. Or hiding from the question.” Eva hooked the compass chain around her wrist. “The station’s abandoned, but not untouched. There are marks on the wall.” Quinn turned. Along the tiled wall behind the bench, someone had scratched a line of symbols into the glaze. Not graffiti. Not by a bored vandal. The cuts followed the tile seams with a careful hand. Quinn stepped closer. “That’s not English.” “No.” Eva joined her, keeping a careful half step back. “It’s old transit warding. I found fragments in a nineteenth-century occult survey. Something was meant to keep passengers out of the tunnel. Or keep something in.” Quinn
traced
the edge of one symbol with her eyes. “And someone refreshed it.” Eva blinked at her. “You can tell?” “The white dust in the cuts is newer than the cracks around it.” Eva’s gaze sharpened. “You saw that from a step away.” “Your archives taught me to read rotten things.” A cough cut through the station. Detective Harlow Quinn straightened and looked over her shoulder. Detective Quinn stood at the stairhead with military precision in every line of her frame.
Her cropped salt-and-pepper hair caught
the light like iron filings. Brown eyes, hard and plain, took the scene in from top to bottom without wasting a glance.
Her sharp jaw tightened when
she saw who was already there. “Of course.”
She came down three steps
and stopped. “Restricted archives and occult hardware. Should have known.” Eva folded the compass into her palm. “Good morning to you too.” The detective’s attention landed on the brass casing. “That supposed to be evidence?” “It belonged to the station.” Eva lifted her chin. “And it’s pointing at the tunnel.” Quinn took the compass, glanced at the needle, and handed it back without breaking stride. “Wonderful. The tunnel’s haunted. Can we move on?” Harlow Quinn crouched by the body bag and rested her fingertips on the zip.
She did not open it
yet.
She let her eyes work
first. The bag’s outer plastic held a dusting of coal grit near the hem.
Not enough to show a drag, but enough to show someone had set it down after walking through
a dirty place. She stood again. “What do we have?” “Male. Unknown. No wallet. No phone at the scene.” “No shoes?” Eva answered, “Shoes were off and lined up by the bench. Clean soles.” Harlow Quinn’s gaze went to the shoes, then to the platform edge. “How clean?” “Very.” Eva slipped a notebook from her satchel and flipped it open. “The pathologist hasn’t gone over them yet, but there’s no mud. No blood. No train grease.” “Meaning?” “Meaning he probably walked here.” Harlow Quinn
let that sit
. “And then?” “Then he died.” The detective gave the body bag a glance that took in its shape, the careful lay of the limbs beneath the plastic, the way the left side sagged lower than the right. “No,” she said. “Then someone wanted us to think he’d walked here.” Eva looked up from her notebook. “Why?” Harlow Quinn pointed to the shoes. “Because if he walked, he’d have left dust on the soles. Coal dust. He didn’t. Someone put them there after they cleaned him off.” Eva’s brows rose a fraction. Harlow Quinn continued, “And this coat. Folded neat on the bench. No one folds a dead man’s coat for him unless they want to show control. Or stage a pause.” “Pause?” Eva
echoed
. “The sort people leave behind when they don’t want a scene to look like what it was.” A radio crackled upstairs. Footsteps hurried down the stairwell. A uniformed constable called something about a witness statement, and Harlow Quinn raised one hand without looking away from the platform. “Hold.” The constable stopped at the last step, nodded, and backed off. Quinn crouched at the bench now, her fingers hovering over the folded coat without touching. “Look at the seat.” Eva leaned in. “What am I looking for?” “Scratches.” There were none on the wood. The bench’s varnish had worn smooth under years of use. But along the front edge, a thin line of pale residue clung in a crescent, as if a wet hand had dragged across and dried there. Eva’s
eyes narrowed
. “Salt?” “Not table salt.” Quinn picked at it with her gloved nail. “Cleansing salt. Or something dressed up to look like it.” Eva opened her mouth, then shut it again as Quinn turned toward the tunnel. The compass jerked in Eva’s hand, needle twitching like a struck nerve. Harlow Quinn saw it and went still. “You feel that?” she asked. Eva nodded once, her fingers tightening around the brass casing. “It started as soon as I came down the stairs.” Quinn looked at the tunnel mouth. The darkness beyond it did not sit right.
It had depth, but also
a texture, as if the lamp light reached only a foot inside and then hit glass. “You’ve got a veil line.” Eva swallowed. “I thought the compass would settle.” “It won’t.” Harlow Quinn moved to the tunnel edge and knelt beside the track bed. The concrete shoulders between the rails carried dust, fragments of old paper, and a second, smaller trail: fresh scuffs in a straight line, the kind made by a heavy object dragged on its side.
She followed them with her
eyes until they vanished into the dark. Eva came up beside her. “Body was found on the platform. Why would drag marks run into the tunnel?” Quinn pointed to the scuffs. “Because he didn’t come from the platform. He came out of the tunnel.” Eva stared at the line, then at the platform, then back at Quinn. “The cleaners said they found him by the bench.” “They found what someone left where they could see it.” A
silence
settled.
Even the station seemed to
hold back its noise. No train rumble. No air hiss from the tunnel.
Only the hum of the
lamps. Harlow Quinn rose and dusted her hands together once. “Show me the access points.” Eva lifted a brow. “You want the official ones or the ones that aren’t on the plans?” “The ones that matter.” A faint, dry smile touched Eva’s mouth.
She patted her satchel and
led the way past the body bag toward the far stairwell, where a locked maintenance gate sat half hidden behind a hanging sheet of black plastic. Quinn noted the fresh scrape on the lock before Eva even touched it. “Anyone open this?” Quinn asked. “Only the station engineer. He swore it had been bolted from the inside.” “Was it?” Eva looked at the bent hasp. “No.” Quinn bent and inspected the concrete floor beneath the gate. More coal dust. More than under the bench. Mixed with a narrow arc of grey flakes from some kind of plaster.
She brushed two fingers over
it. “Brick.” Eva crouched too. “There isn’t any brickwork in this part of the station.” “There was.” Quinn’s gaze moved up the wall, past the white tile and the flaking strip of paint at the edge. “The station’s older than the Tube line. They built around something.” Eva’s expression shifted. “You think the tunnel was cut through a sealed chamber.” “I think someone reopened what the warding was supposed to keep shut.” Eva looked back at the compass. The needle shivered, then settled toward the maintenance gate. Harlow Quinn pulled on the gate. The chain rattled. The lock hung open with one bent side. Beyond it, a narrow service passage ran into darkness, old brick sweating in the cold. The lamp behind them failed to reach the far end. On the wall, fresh chalk marks glimmered in a rough line, each symbol cut with the same heavy hand. Eva inhaled
sharply
. “Those are protective marks.” “They were.” Quinn studied the line. “Now they’re warning marks.” “Warning who?” Quinn’s face stayed blank, but her eyes sharpened. “Whoever came through here before the body turned up.” Eva’s fingers rose to tuck hair behind her left ear, then dropped when she caught herself. “The council team didn’t mention any passage.” “They wouldn’t know what they were looking at.” Quinn stepped into the passage and stopped after two paces.
She crouched and pointed to
a patch of floor just inside the threshold. A line of wet mud cut across the dust, then broke where a boot had dragged through it. Not one boot. Two separate prints, each with a different tread pattern, overlaid and then smeared clean. She glanced back. “Two people came in.” Eva peered at the prints. “One’s heavier.” “Or carrying.” A beat passed.
Then Quinn’s gaze rose to
the brick arch overhead. There, half buried in grime, a narrow seam split the wall from floor to roof. The mortar around it had crumbled away in a circle, recent and deliberate. Eva followed her stare. “That wasn’t there on the station survey.” “No.” Quinn drew a penlight from her pocket and clicked it on. The beam washed over the seam and caught on something pale tucked into the crack. Fabric. Not much of it, just a shred. She reached for it and paused, eyes fixed on the edge where the brick met the floor. “Blood?” Eva asked. Quinn touched the stain with her glove. It came away black-red, old at the centre and sticky at the edge. “No.” Her voice stayed level. “That’s not all blood.” Eva peered closer, then went still. Quinn shone the light lower. Beneath the seam, on the base of the wall, sat a small crescent of white wax. The surface held a thumbprint, and within the thumbprint the ash of a burned match. She straightened
slowly
. “Someone lit a candle in here,” she murmured. Eva’s eyes
flicked
to the passage behind the wall, then back to Quinn. “For what?” Quinn looked at the compass in Eva’s hand. The needle now pointed straight through the brick seam, not at the tunnel behind them. “Not for what,” she said. “For where.” She placed her palm flat against the wall. The brick felt colder than the air around it, cold enough to sting through leather. Beneath her hand, a faint vibration thudded once, then again, like a second heartbeat buried in stone. Eva stepped back. “Harlow—” Quinn kept her hand on the wall, her head angled as if she listened with her skin. “Get me the scene log,” she said. “And every note on the cleaners, the engineer, and anyone who came down here before uniform sealed it.” Eva nodded once, already reaching for her satchel. Quinn looked back at the body bag on the platform, then at the tunnel mouth, then at the brick seam with its wax and blood and fresh chalk. “That body didn’t start here,” she said. Eva’s voice came quiet from the passage entrance. “No.” Quinn’s jaw tightened. “It was delivered.”
created_at
"2026-03-18T10:38:00.481Z"
3/18/2026, 10:38:00 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
424
moderation_latency
(null)
generation_time
16657
tokens_prompt
1149
tokens_completion
3941
native_tokens_prompt
1009
native_tokens_completion
3173
native_tokens_completion_images
0
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.01503525
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0ab00663843bef940169ba808888248193af089c4a04b6e0ca"
is_byok
false
latency
191
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-1773830280-YRGdU8kwQX9gYloXflXu"
upstream_id
"resp_0ab00663843bef940169ba808888248193af089c4a04b6e0ca"
total_cost
0.01503525
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
23
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
110
tagDensity
0.209
leniency
0.418
rawRatio
0
effectiveRatio
0
93.90%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2458
totalAiIsmAdverbs
3
found
0
adverb
"very"
count
1
1
adverb
"sharply"
count
1
2
adverb
"slowly"
count
1
highlights
0
"very"
1
"sharply"
2
"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)
81.69%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2458
totalAiIsms
9
found
0
word
"standard"
count
2
1
word
"quivered"
count
1
2
word
"measured"
count
1
3
word
"traced"
count
1
4
word
"echoed"
count
1
5
word
"footsteps"
count
1
6
word
"silence"
count
1
7
word
"flicked"
count
1
highlights
0
"standard"
1
"quivered"
2
"measured"
3
"traced"
4
"echoed"
5
"footsteps"
6
"silence"
7
"flicked"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
2
maxInWindow
1
found
0
label
"eyes widened/narrowed"
count
2
highlights
0
"eyes narrowed"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
181
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
1
narrationSentences
181
filterMatches
0
"watch"
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
268
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
2458
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
18
unquotedAttributions
0
matches
(empty)
6.97%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
111
wordCount
1678
uniqueNames
8
maxNameDensity
2.86
worstName
"Quinn"
maxWindowNameDensity
4.5
worstWindowName
"Eva"
discoveredNames
Tube
1
Detective
3
Harlow
12
Quinn
48
Camden
1
Close
1
Kowalski
1
Eva
44
persons
0
"Detective"
1
"Harlow"
2
"Quinn"
3
"Camden"
4
"Kowalski"
5
"Eva"
places
(empty)
globalScore
0.07
windowScore
0.167
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
118
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.407
wordCount
2458
matches
0
"Not enough to show a drag, but enough to show someone had set it down after walking through"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
268
matches
0
"let that sit"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
145
mean
16.95
std
15.32
cv
0.904
sampleLengths
0
23
1
76
2
2
3
16
4
7
5
55
6
6
7
8
8
3
9
17
10
25
11
4
12
50
13
26
14
4
15
33
16
18
17
4
18
37
19
31
20
2
21
46
22
8
23
5
24
30
25
19
26
3
27
7
28
8
29
46
30
8
31
16
32
3
33
34
34
36
35
6
36
36
37
14
38
7
39
13
40
10
41
8
42
15
43
53
44
17
45
12
46
8
47
5
48
15
49
23
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
181
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
270
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
268
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1681
adjectiveStacks
0
stackExamples
(empty)
adverbCount
55
adverbRatio
0.03271861986912552
lyAdverbCount
4
lyAdverbRatio
0.002379535990481856
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
268
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
268
mean
9.17
std
6.99
cv
0.763
sampleLengths
0
23
1
20
2
12
3
24
4
20
5
2
6
16
7
7
8
18
9
21
10
4
11
12
12
6
13
8
14
3
15
17
16
5
17
20
18
4
19
21
20
29
21
17
22
9
23
4
24
25
25
8
26
16
27
2
28
4
29
37
30
6
31
25
32
2
33
14
34
32
35
6
36
2
37
5
38
4
39
7
40
8
41
2
42
9
43
15
44
2
45
2
46
3
47
7
48
2
49
6
46.64%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
9
diversityRatio
0.27611940298507465
totalSentences
268
uniqueOpeners
74
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
5
totalSentences
162
matches
0
"Too dark for that, too"
1
"Even the station seemed to"
2
"Only the hum of the"
3
"More than under the bench."
4
"Then Quinn’s gaze rose to"
ratio
0.031
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
25
totalSentences
162
matches
0
"She pushed a curl of"
1
"She looked past the compass"
2
"It sat beside a smear"
3
"She touched the smear with"
4
"Her eyes narrowed."
5
"Her hand skimmed the seat."
6
"She bent and checked the"
7
"She glanced toward the tracks."
8
"Her cropped salt-and-pepper hair caught"
9
"Her sharp jaw tightened when"
10
"She came down three steps"
11
"She did not open it"
12
"She let her eyes work"
13
"She stood again."
14
"It had depth, but also"
15
"She followed them with her"
16
"She patted her satchel and"
17
"She brushed two fingers over"
18
"She crouched and pointed to"
19
"She glanced back."
ratio
0.154
34.07%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
138
totalSentences
162
matches
0
"The Tube stairs groaned under"
1
"The air below Camden tasted"
2
"A platform stretched ahead, empty"
3
"Someone had printed the name"
4
"Quinn lifted her gaze to"
5
"Eva Kowalski stood beside a"
6
"She pushed a curl of"
7
"Verdigris coated the casing."
8
"The face markings looked wrong,"
9
"Quinn slowed at the bottom"
10
"Eva’s mouth twitched."
11
"Quinn crossed to the table."
12
"The compass needle quivered, then"
13
"Eva turned the compass in"
14
"Quinn slipped on gloves, her"
15
"She looked past the compass"
16
"Eva tipped her chin toward"
17
"Quinn’s eyes moved over the"
18
"Eva huffed a breath."
19
"Quinn’s gaze dropped to the"
ratio
0.852
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
162
matches
(empty)
ratio
0
90.34%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
68
technicalSentenceCount
5
matches
0
"A dark wool coat lay there with careful folds, one sleeve draped over the other, as if someone had sat and folded it by hand."
1
"Quinn crouched at the bench now, her fingers hovering over the folded coat without touching."
2
"But along the front edge, a thin line of pale residue clung in a crescent, as if a wet hand had dragged across and dried there."
3
"Eva nodded once, her fingers tightening around the brass casing."
4
"Quinn kept her hand on the wall, her head angled as if she listened with her skin."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
23
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
10
fancyCount
2
fancyTags
0
"Harlow Quinn continued (continue)"
1
"she murmured (murmur)"
dialogueSentences
110
tagDensity
0.091
leniency
0.182
rawRatio
0.2
effectiveRatio
0.036
88.4538%