NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37J0MBEMFP6J329M3CG971Z
Run Details
Model:
GPT-6 Sol
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
1m
Cost:
$0.033318
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
100.00%
AI-ism adverb frequency
(details)
80.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
93.96%
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)
49.94%
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)
96.21%
Em-dash & semicolon overuse
(details)
100.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
60.27%
Sentence opener variety
(details)
22.37%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
43.89%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
88.2215%
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
Detective Harlow Quinn stepped off
the disused platform and put her shoe into six inches of black water. “Mind the edge,” called DC
Patel
from the tracks.
Quinn looked down at her
submerged toe, then at him. “Useful.”
He stood beneath a tiled
roundel that still read CAMDEN TOWN, though no public timetable showed a platform this far below the street. Beyond him, bare bulbs swung on lengths of wire over rows of empty stalls.
Their frames filled the old
station: timber counters, iron cages, a glass cabinet with its shelves smashed out.
Water dripped through a crack
above a sign promising PEARS SOAP.
Something sweet and medicinal hung
in the air beneath the damp.
Patel
waded towards her, his disposable overshoes ballooning around his ankles. “Security guard found the body at five twenty. His employer leases the access tunnel from Transport for London. Claims he came down because the service gate was open.” “Claims?” “He also claims he’s never seen any of this.”
Quinn swept her torch across
a stall covered in scraps of faded
velvet
.
Rings of dust marked places
where objects had sat.
Whatever the sellers had carried
in, they had taken out in a hurry. “Guard’s upstairs?” “With uniforms. Name’s Dacre.”
Patel
pointed down the platform. “Victim’s in the old ticket office.”
A white forensic tent filled
the doorway.
Its plastic sides stirred under
a blower, and the tiled corridor beside it bore a line of wet footprints. Quinn stopped before the threshold. One set belonged to the scene officers; numbered markers stood beside the impressions left before their arrival. “Who entered first?” “Dacre. Then PC Lennox. Lennox stayed at the door.” “And Dacre?” “He says he found her where she fell and went straight back.” Quinn counted the impressions.
A broad sole came from
the service tunnel, passed the ticket office and returned. Near the office door, a second, narrower pattern crossed the broad tread and went on towards the tracks. “Whose are those?”
Patel
followed the beam. “The victim’s, we think. Trainers. Her shoes are wet.” “‘We think’ covers a lot of ground.” Inside, the office smelled of old plaster and hot plastic.
A woman lay on her
back between the ticket window and a cast-iron radiator.
She wore a charcoal coat
over a green jumper, dark trousers and white trainers stained brown at the toes.
Blood had dried beneath her
head in a narrow fan. A fallen metal cash drawer rested near her right hand. Dr Sayeed, the pathologist, rose from beside the body. “You’re late.” “The stairs took longer than the lift.” “There is no lift.” “That explains it.” Sayeed pulled off one glove. “Female, mid-twenties. Head wound. I’ll give you cause after the post-mortem, but the drawer has a bloody edge, and there’s a corresponding cut behind her left ear. Time of death looks between midnight and three.” “Identification?”
Patel
held up an evidence bag. Inside lay a British Museum staff card. EVA KOWALSKI. The photograph showed a freckled woman with curly red hair and round glasses. Quinn looked back at the body. Eva’s glasses sat folded inside her coat pocket.
Her curls had flattened where
blood touched them. “Her phone?” “Gone,”
Patel
answered. “So’s her satchel, according to the guard. He saw a strap beside her when he came in.” “You said he went straight back.” “That’s what he says.” Sayeed stepped aside as Quinn crouched. Eva’s right hand lay open, palm up. A crescent of grime darkened the nail of her index finger.
Her left hand rested beneath
her coat, fingers caught in the fabric at her hip. The coat had ridden up enough to expose the lining, where a pale rectangle interrupted the dust. “Something was in that pocket,” Quinn murmured. “We’ve checked it,”
Patel
told her. “Empty.” “Then someone checked it before you.”
Patel
folded his arms. “We have a missing phone, a missing bag, a head injury and an open service gate. Dacre walked in on a robbery, or he did it himself. He knew the place would be empty.” Quinn turned the drawer with a gloved fingertip. Blood marked one corner. Dust covered the underside except for two clean parallel lines. “Could be,” she answered. “Where did it fall from?” “The counter. Knocked down in a struggle.” The counter stood four feet away. A clean rectangle on its surface matched the drawer. Quinn held her torch low. Dust had collected in a thick lip along the edge of the counter, unbroken except where a cable had dragged across it. On the floor between counter and body, the mud lay smooth. “If it fell, it flew,” she said. “No scrape, no bounce mark. And she landed with her feet pointing at the counter. Someone held it and brought it down.”
Patel
bent to inspect the floor. “So, murder rather than an accident. Still a robbery.” “Whoever hit her put the drawer beside her. Why?” Sayeed glanced at the dried blood. “To make it look like an accident?” “Then they took the phone and bag, which makes it look like a robbery. Two stories for one body.” A camera flash lit the far wall. Quinn waited for the photographer to move, then examined the ticket window.
Its glass had cracked years
before. Someone had taped a pane of clear plastic over it, and three tiny holes pierced the plastic at eye height. She leaned closer. The holes formed a rough triangle; around each, the surface had clouded. “
Patel
. Who uses this room?” “Dacre says no one. They’re stripping cable out of the access tunnel next month. That’s why his firm has the keys.” “And the bulbs? The stalls?” “He doesn’t know.” Quinn put her face near the holes. Through them she could see the full length of the platform and the tracks. A customer could have stood here, looking out, without anyone on the platform seeing more than a silhouette behind the cracked pane. She turned. Eva’s trainers faced the counter, but the brown stain on their toes had dried in fine specks.
It did not match the
black water outside, and no muddy track led from the doorway to her body. “Was the floor wet when the first officer got here?” “Lennox photographed it. The water was out on the platform, same as now.” “Her shoes were dry when she came in.”
Patel
looked from Eva’s feet to the doorway. “Someone carried her?” “Look at the heels.” Both soles were clean at the back. Quinn rose and crossed to the corridor. The narrow prints there showed the same pattern as Eva’s trainers. Each impression held water around the heel and a darker grit at the toe. Someone wearing those shoes had walked through the flood after the blood dried, or had pressed them into the wet floor with another person’s
weight
.
She followed the prints past
the ticket office.
They ended beside the stairs
down to the tracks. No return prints. At the stair rail, a blue nitrile glove hung by its torn cuff from a splinter of rusted metal. It had turned inside out. Quinn called for a scene officer, pointed it out, and left it untouched. “You’re thinking the killer wore her shoes?”
Patel
asked. “Her feet are in them.” “Then someone carried her as far as the stairs and brought her back?” “Why carry her away, change your mind and leave no marks beneath the body?”
Patel
said nothing. Quinn turned her light upwards. A grey smear ran across the tiles above the stairwell, well above head height. Beneath it, a hook had
been drilled
into a grout line. Another hook stood across the platform. A length of fine wire remained between them, slack enough to disappear against the soot. “What did they hang there?” “A banner? The guard mentioned seeing cloth around the stalls.” Quinn
traced
the line with her torch. “The holes in the ticket window face the tracks. That wire crosses the view.” She climbed down two steps. From there she could see a square of clean tile near the stair landing, shaped like a notice board that had
been taken
down. A brass tack still held a curled scrap of black paper. Ink shone on it when the torch moved.
Patel
came close enough to read over her shoulder. “What does that say?” “Not much.” Quinn angled the light. A painted white arrow pointed towards the service tunnel. Beneath it, only the final letters of a word remained: KET. “Market,”
Patel
supplied. “That would explain the stalls.” “And the guard’s selective eyesight.”
Patel
looked back at the ticket office. “Underground market. Drugs, stolen antiques, fake documents. Museum assistant comes down to buy or sell something. A deal goes bad.” “That gets us closer.” Quinn handed him the torch beam while she studied the wall. “But there are no stall signs, no rubbish, no packing material. They cleared this place without cleaning it. They took goods. They left a body.” “An alarm went up.” “From whom? Dacre says the gate stood open when he arrived.” The faint rattle of wheels reached them from the access tunnel. A scene officer pushed equipment through the water, cursing the depth. Quinn stepped aside and caught sight of something beneath the bottom stair: a small brass disk lodged between a pipe and the wall. She squatted. Verdigris crusted its edge.
Once she cleared the sightline
with her torch, she
saw that it
was a compass. Protective marks had been cut around its face in tight rings, and the needle pointed
not north but across the tracks, towards a bricked-up arch
. “Don’t touch it,”
she told Patel
. “I wasn’t going to.” “You were leaning.” “I wanted a better look.” Quinn moved her light across the arch. Most of the bricks wore the same soot as the rest of the station. Six near the centre looked damp and dark. The mortar around them had cracked into neat, fresh seams. “You know what this is?”
Patel
asked, nodding at the compass. “A reason to photograph beneath the stairs.” The scene officer with the trolley stopped. Quinn asked for a marker and placed it beside the brass casing. As the officer took photographs, she returned to the office. On Eva’s coat, dust had caught in the fold beneath her left arm. Quinn crouched again and held the fabric away from the body without pulling it. A short red hair clung to the lining. Several more lay across the bloodless part of Eva’s collar.
Her own curls had shed
against her coat, but these strands were straight and coarse. She checked the staff-card photograph. Eva wore a worn leather satchel across her shoulder, strap running from right shoulder to left hip. The coat in the picture had a faint abrasion at the left hip where the bag rubbed. The body’s left hand lay over that spot, gripping the lining. “The satchel was on her when she died,” Quinn said.
Patel
moved beside her. “Dacre saw the strap.” “No. He said he saw a strap beside her. Different thing. If she wore the bag when she fell, the strap should have left a mark across her coat. There’s no pressure line. She took it off before the blow, or someone took it from her while she was standing.” “Then he grabbed it afterwards.” “Look at the blood.” Quinn pointed to the narrow fan beneath Eva’s head. “Nothing disturbed it by her left side. Whoever took the bag did so before she fell.”
Patel
took out his notebook. “Dacre may have invented the strap.” “Ask him what colour it was.” “Why?” “Her card shows brown leather. If he says brown, he may have seen her before he claims. If he guesses black, we learn something else.” He wrote it down. Quinn followed the clean rectangle on the coat lining to the pocket seam. A few threads hung loose, cut rather than torn. The missing object had been small and flat. Not a phone; the pocket was too shallow. “Did you find a wallet?” “In her inside pocket. Cash untouched. Forty-six pounds and coins.” “Robbery keeps losing pieces.”
Patel
closed his notebook. “You want a different interpretation, fine. She came for a transaction. Someone took a book from her bag, hit her with a drawer, staged an accident, then cleared the market before the guard’s rounds.” “Your transaction requires them to know the guard’s rounds.” “Dacre could be in on it.” “He could.” Quinn stood and looked at the floor again. “But Eva didn’t walk in through the service tunnel. The dry grit on her shoes came from somewhere else, and the narrow prints outside were made after she died. Somebody wanted us to believe she walked towards the tracks.” “Why?” “Let’s look where they point.”
They passed the ticket office
and went back down the stairwell. At the bottom, the rail gave way to a tiled wall and an old enamel sign: DANGER. LIVE RAIL. The tracks below had rusted decades ago. Water pooled between the sleepers, black enough to swallow Quinn’s torch beam. A strip of paper lay caught under the lowest step. Quinn bent until she could read it without touching it. The paper had torn from a page filled with notes in compact handwriting. One line remained intact: “Bone admits one. No substitute accepted.”
Patel
read it, then looked up at the market. “Some kind of club?” Quinn examined the tear. The paper bore no water stain, though the floor around it was wet. Someone had dropped it after the flood rose or placed it beneath the step to keep it dry. The photographer descended behind them. Quinn directed a shot of the paper in place, then one of the step and the prints above. The narrow impressions ended at the landing; none continued down the stairs. “They wanted us to stop here,” she said.
Patel
studied the dead rail. “A fall onto the tracks?” “No. They wanted us looking at the tracks.” Quinn lifted her torch towards the bricked arch. The little brass compass under the stairs still aimed at it. From this angle she could see a fresh scratch across one of the damp bricks, at the height of a hand holding a key. She stepped to the wall. One brick carried a smear of white dust across its centre, and the mortar beneath it had fallen into a fine pile on the dry ledge. “Get the masonry photographed before anyone touches it,”
she told the scene officer
. “Then I want a structural engineer.”
Patel
joined her at the arch. “You think there’s a room behind it?” “I think someone opened this wall recently and closed it again.” “Where does it go?” Quinn glanced back at the wet footprints ending at the stair landing, then at the note still trapped beneath the step. “That’s what we need to find out. First, ask Dacre about the satchel. Don’t mention the wall.”
created_at
"2026-09-23T16:36:37.158Z"
9/23/2026, 4:36:37 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2945
moderation_latency
(null)
generation_time
59685
tokens_prompt
1112
tokens_completion
3810
native_tokens_prompt
1009
native_tokens_completion
3130
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)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
service_tier
"default"
usage
0.033318
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790181397-1EjBNCw2JuHyPz40de2W"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790181397-BEw4gf4LnVTBGraUX7MW"
upstream_id
"resp_0a982a16405bc12e016ab4001546f887d1804e4263208c183c"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_0a982a16405bc12e016ab4001546f887d1804e4263208c183c"
is_byok
false
latency
658
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.033318
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
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
18
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
103
tagDensity
0.175
leniency
0.35
rawRatio
0
effectiveRatio
0
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2484
totalAiIsmAdverbs
0
found
(empty)
highlights
(empty)
80.00%
AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions
(empty)
found
0
"Patel"
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
93.96%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2484
totalAiIsms
3
found
0
word
"velvet"
count
1
1
word
"weight"
count
1
2
word
"traced"
count
1
highlights
0
"velvet"
1
"weight"
2
"traced"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"hung in the air"
count
1
highlights
0
"hung in the air"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
161
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
161
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
245
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
50
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2484
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
23
unquotedAttributions
0
matches
(empty)
49.94%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
74
wordCount
1599
uniqueNames
8
maxNameDensity
2
worstName
"Quinn"
maxWindowNameDensity
3.5
worstWindowName
"Quinn"
discoveredNames
Harlow
1
Quinn
32
Patel
23
Sayeed
4
British
1
Museum
1
Eva
9
One
3
persons
0
"Harlow"
1
"Quinn"
2
"Patel"
3
"Sayeed"
4
"Eva"
places
0
"One"
globalScore
0.499
windowScore
0.5
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
120
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.403
wordCount
2484
matches
0
"not north but across the tracks, towards a bricked-up arch"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
245
matches
0
"saw that it"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
128
mean
19.41
std
18.07
cv
0.931
sampleLengths
0
18
1
9
2
11
3
77
4
11
5
28
6
1
7
9
8
35
9
2
10
15
11
48
12
3
13
9
14
2
15
12
16
36
17
3
18
13
19
7
20
63
21
11
22
7
23
4
24
3
25
40
26
1
27
28
28
22
29
2
30
20
31
6
32
4
33
56
34
7
35
7
36
6
37
38
38
22
39
9
40
7
41
53
42
29
43
15
44
9
45
13
46
19
47
60
48
5
49
21
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
2
totalSentences
161
matches
0
"been drilled"
1
"been taken"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
245
matches
(empty)
96.21%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
4
flaggedSentences
4
totalSentences
245
ratio
0.016
matches
0
"One set belonged to the scene officers; numbered markers stood beside the impressions left before their arrival."
1
"The holes formed a rough triangle; around each, the surface had clouded."
2
"Not a phone; the pocket was too shallow."
3
"The narrow impressions ended at the landing; none continued down the stairs."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1602
adjectiveStacks
0
stackExamples
(empty)
adverbCount
31
adverbRatio
0.019350811485642945
lyAdverbCount
2
lyAdverbRatio
0.0012484394506866417
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
245
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
245
mean
10.14
std
7.08
cv
0.698
sampleLengths
0
18
1
9
2
10
3
1
4
23
5
14
6
18
7
11
8
11
9
11
10
28
11
1
12
9
13
13
14
9
15
13
16
2
17
9
18
6
19
7
20
19
21
5
22
17
23
3
24
9
25
2
26
12
27
4
28
14
29
18
30
3
31
4
32
9
33
7
34
10
35
14
36
19
37
10
38
10
39
9
40
2
41
7
42
4
43
3
44
5
45
35
46
1
47
6
48
7
49
2
60.27%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
4
diversityRatio
0.37142857142857144
totalSentences
245
uniqueOpeners
91
22.37%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
149
matches
0
"Once she cleared the sightline"
ratio
0.007
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
20
totalSentences
149
matches
0
"He stood beneath a tiled"
1
"Their frames filled the old"
2
"Its plastic sides stirred under"
3
"She wore a charcoal coat"
4
"Her curls had flattened where"
5
"Her left hand rested beneath"
6
"Its glass had cracked years"
7
"She leaned closer."
8
"It did not match the"
9
"She followed the prints past"
10
"They ended beside the stairs"
11
"It had turned inside out."
12
"She climbed down two steps."
13
"she told Patel"
14
"Her own curls had shed"
15
"She checked the staff-card photograph."
16
"He wrote it down."
17
"They passed the ticket office"
18
"She stepped to the wall."
19
"she told the scene officer"
ratio
0.134
43.89%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
124
totalSentences
149
matches
0
"Detective Harlow Quinn stepped off"
1
"Quinn looked down at her"
2
"He stood beneath a tiled"
3
"Their frames filled the old"
4
"Water dripped through a crack"
5
"Something sweet and medicinal hung"
6
"Patel waded towards her, his"
7
"Quinn swept her torch across"
8
"Rings of dust marked places"
9
"Whatever the sellers had carried"
10
"Patel pointed down the platform"
11
"A white forensic tent filled"
12
"Its plastic sides stirred under"
13
"Quinn stopped before the threshold."
14
"Quinn counted the impressions."
15
"A broad sole came from"
16
"Patel followed the beam."
17
"A woman lay on her"
18
"She wore a charcoal coat"
19
"Blood had dried beneath her"
ratio
0.832
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
149
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
75
technicalSentenceCount
0
matches
(empty)
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
18
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
11
fancyCount
1
fancyTags
0
"Quinn murmured (murmur)"
dialogueSentences
103
tagDensity
0.107
leniency
0.214
rawRatio
0.091
effectiveRatio
0.019
88.2215%