NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HHTVTNH8M6XVP89GHA77D
Run Details
Model:
GPT-6 Sol
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
59.1s
Cost:
$0.032340
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
95.86%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
89.65%
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)
0.00%
Name drop frequency
(details)
100.00%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
100.00%
Paragraph length variance
(details)
87.36%
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)
51.08%
Sentence opener variety
(details)
37.66%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
41.92%
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)
86.7844%
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
Detective Harlow Quinn reached the
sealed entrance beneath Camden just after six, with rain in the cuffs of her coat and a paper cup of coffee gone cold in her hand.
A uniform held aside the
plywood panel that concealed the stairs. Beyond it, a tiled passage descended into darkness. “Victim’s down on the platform,”
the constable said
. “Mind the last step. It’s broken.” Quinn looked at him. “Who found the entrance?” “Network Rail contractor. He saw the door open when he came to check a leak.” “Did he go down?” “No. He called it in.”
She glanced at the padlock
hanging from the doorframe.
The hasp had been torn
out of rotten wood, but the lock itself was closed.
Someone had pulled the door
open without unlocking it, then left the lock for the police to find.
She set her coffee on
a dry patch of concrete and went down.
The station had been shut
long enough for the name on its wall to lose half its letters.
Water traced black lines through
cream tile. Old advertisements peeled in strips above a platform crowded with folding tables, canvas awnings, and narrow wooden stalls. Most had
been stripped
bare. A few held abandoned objects: a brass bell, empty glass jars, a tray lined with blue
velvet
.
Paper lanterns hung from the
ceiling without any visible wiring.
Their light gave the place
the strained, unreal look of a photograph taken a second before the flash.
A market in a closed
Tube station.
Camden had offered Quinn stranger
crime scenes, but rarely this well furnished. She ducked under the tape.
The air smelled of damp
brick, candle wax, and something sharp that caught at the back of her throat.
DS Lena Voss waited near
the platform edge, notebook in hand. “Male, approximately fifty. No ID. First officers got here at five twelve. Ambulance pronounced him at five twenty-three.”
Quinn saw the body between
two stalls.
He lay on his back
in a dark wool coat, arms at his sides.
His boots pointed toward the
tracks. Blood had dried in a narrow fan beneath his head. “Blunt-force injury?” she asked. “Looks like it. Pathologist’s on her way. There’s a brick by the track.” “Of course there is.” Voss
knew that tone
. “It has blood on it.” “Then let’s hope it has his.” Quinn crouched beside the dead man.
His hair was wet at
the temples, though the platform around him was dry. There was a cut above his right ear, deep enough to have bled freely. His hands were clean. Beneath his nails, she could see no grit, no torn skin. The coat
was buttoned
one button wrong. “Maybe he ran into whoever opened this place,” Voss said. “They kill him, clear out before the contractor sees the door.” “Clear out a whole market?” “Plenty of time if it happened overnight.” Quinn looked down the length of the platform. Awnings stood square, table legs locked. A cloth draped over a stall near the tunnel had
been folded
neatly at one corner. The vendors might have removed their stock, but they hadn’t fled.
She touched the outside of
the man’s sleeve with a gloved finger. The wool was damp at the shoulder and dry at the cuff. “Any CCTV?” “Nothing in here. Street camera caught two people going into the alley at four thirty-eight. No clear faces. One came back out at four forty-six.” “Which one?” “Hard to tell. Both wore dark coats.” Quinn examined the man’s boots. Mud clung to the soles in a pale, gritty crust. The station floor held only the fine black dust of old rail tunnels. Someone had carried him, or he had walked here from somewhere with different ground underfoot. A young scene examiner stood over the brick, camera raised. Quinn waited until he took his photograph, then crossed to the platform edge. The brick sat on the ballast below, its exposed corner marked with dark blood.
She looked back at the
body. There were no drops between him and the edge. “Where’s the rest?” she asked. Voss followed her gaze. “The rest of what?” “Blood from moving the brick.” “It could have been thrown.” “From beside his head, across three metres, onto the track.” Quinn looked at the stall nearest the body. “Without touching any of these legs.” Voss closed her notebook. “You think someone placed it there.” “I think we’ve been given a brick to look at.” Behind them, a woman’s voice said, “That’s not what killed him.” Quinn turned. At the foot of the stairs stood a young woman with curly red hair, round glasses, and a leather satchel held so
tightly
against her hip that the strap bowed. A constable hovered at her shoulder. “I told her to wait upstairs,” he said. “She said she knew the victim,” Voss replied. The woman’s face went white when she saw the body.
She took one step toward
him and stopped. Quinn approached her. “Name?” “Eva Kowalski.” “How do you know him?” Eva swallowed. “I don’t know his name.” “You just said you knew him.” “I said I’d seen him.”
Her fingers found a curl
and tucked it behind her left ear. “Yesterday. Here.” Voss looked at Quinn. The constable shifted his
weight
. Quinn kept her eyes on Eva. “You were in a sealed, abandoned station yesterday.” “Yes.” “What brought you down?” Eva looked past her at the stalls. “Someone was selling something I needed to see.” Quinn had spent eighteen years listening to people
decide
which piece of a lie they could bear to tell. Eva sounded frightened, but she had come back. That counted for something. “What did you need to see?” “A compass.” “Where is it?” “I didn’t buy it.” Quinn waited. Eva glanced toward the dead man. “He did.” The victim’s coat had
been searched
. Quinn had seen the turned lining of the left pocket and the way the wrong button pulled at his chest. “What sort of compass?” “Brass. Small enough to fit in your palm. Green around the edges, like it had been kept somewhere damp.” Eva’s eyes met hers. “There were marks cut into the face.” “Initials?” “No. Protective sigils.” Voss made a small sound. Eva heard it. “I work in the British Museum’s restricted archives. I know what I saw.” “And why would anyone use a compass down here?” Quinn asked. “Not for north.” “That’s useful.” “I’m trying to be.” Eva pressed her satchel closer. “It belonged to a seller at the far end. When that man bought it, they argued. The seller said it would only show him the nearest opening. The man said there was one under the station already.” An opening. Quinn looked toward the black tunnel. She thought of DS Morris, who had vanished during a case three years earlier.
His last call had come
from a service passage that every plan in the building showed ending at a brick wall. The search team had found the wall intact. She set the memory aside.
It had no place in
her notes. “Did you see this seller today?”
she asked Eva
. “No. When I came in, the stalls were empty.” “How did you get in?” Eva’s hand moved to the satchel flap. “Miss Kowalski.” “I had a token.”
She drew out a small
pale disc. It looked like polished bone, drilled near one edge. “You show it at the entrance. Usually someone’s there.” The constable leaned closer. Quinn took the disc with a gloved hand.
Its surface had been worn
smooth by use. She passed it to Voss for a photograph. “Why return this morning?” Eva looked at the dead man again. “I wanted to ask him what he’d found.” “You said you didn’t know his name.” “I thought he’d be here.” It was thin, but not impossible. Quinn moved back toward the body. “Stay where the officer can see you.” At the stall beyond the dead man, she found a shallow wooden drawer shoved beneath the table. Inside lay scraps of tissue paper, a length of string, and a round impression in the dust. The missing object had been roughly the size Eva described. The tabletop held a second clean circle, smaller and sharper, on a layer of grime thick enough to
show that something
had sat there until recently. Quinn bent lower. A smear of pale mud marked the table leg. Beside it, at knee height, dark fabric had snagged on a splinter. “Voss. Come here.” Voss joined her. Quinn pointed first to the mud, then to the victim’s boots. “He stopped at this stall,” Voss said. “He was on the ground when his leg touched that wood. Look at the height.” Quinn indicated the snag. “Someone dragged him past it.” Voss
measured
the distance with her eye. “His coat would have caught too.” “Unless they carried him feet first and lowered him.” They looked toward the body. His arms lay straight at his sides. His coat had
been buttoned
after death, badly, by someone standing over him. A drip struck the tile near Quinn’s shoe. She looked up. A dark line ran along the ceiling from the tunnel mouth, gathering at a cracked joint. She followed it through the lantern light. Farther down, a puddle shone on the platform beside a locked maintenance gate. The man’s wet hair. His damp shoulder. The mud on his boots. “Get photographs before we move anything,” she told Voss. “Then I want the gate checked.” The keyhole had
been stuffed
with wax. Quinn didn’t touch it. She crouched to study the floor instead. Water had washed the dust clean in a narrow band leading out from the gate. At its edge lay half a footprint, heel deep in pale grit. Several more crossed it, older and less distinct. One fresh mark pointed away from the gate, toward the body. Beyond the bars, the service passage sloped into darkness. A draught touched Quinn’s face, cold enough to carry a smell of rain-soaked earth. No vent showed on the plans Voss had brought down. “Maintenance access?” Voss asked. “According to the council, it was bricked up in 1986.” Voss looked through the bars. “Someone reopened it.” “Maybe.” Quinn stood and checked her worn leather
watch
. Eva had said she’d arrived to find the stalls empty. The contractor had found the door open. Whatever had happened here, someone had had time to pack up and leave. They had also taken care to leave a body where the police would find it
quickly
. She returned to Eva. “What time did you come down yesterday?” “About nine in the evening.” “Was the market busy?” Eva hesitated. “Yes.” “How busy?” “Dozens of people.” “Anyone see your argument?” “Probably.” “And no one’s come forward.” Quinn watched her face. “Who runs this place?” “It moves.” “The management?” “The whole market. Every full moon.” Eva spoke quietly now, as if the empty stalls might hear her. “This is where it is this month.” Quinn could hear Voss behind her, speaking into a radio, asking for the gate specialist.
She looked back at the
platform: the folded awning, the wiped tables, the bright false clue on the track. The killer had counted on the place itself to discredit anyone who
tried to
explain it. A secret market, a compass that didn’t point north. Easier to report a man beaten to death in an abandoned station. “The man who bought the compass,” Quinn said. “Did he leave while you were here?” “I don’t know. I left first.” “Did he seem afraid?” Eva thought for a moment. “He seemed angry. He kept looking toward the tunnel.” Quinn
followed that line
of sight. The fresh print in the pale grit pointed toward the body. The older prints went the other way. She went back to the victim and crouched at his boots. There was a thin red thread caught beneath one lace, wet but not bloodied. She
traced
its color to the canvas awning above the nearest stall. No tear showed there.
Then she saw the thread
had a waxed finish, more like cord than cloth. “Evidence bag,” she said. Voss brought one. Quinn eased the thread free. At its end clung a fleck of verdigris. The compass had
been tied
to him, perhaps around his neck or wrist. Someone had cut it away. Not at this staged resting place, though. She inspected the victim’s collar and found a short rubbed line where a cord had pressed the skin. Water had softened it but not erased it. “His injury may be real,” she told Voss. “But he was killed elsewhere. Likely beyond that gate. The brick has blood because someone put it against the wound. They wanted us to stop at the platform.” “Why bring him out at all?” Quinn looked at Eva. “Because he knew where the opening was.” Eva’s hand rose to her left ear and stayed there. A faint metal sound came from the far end of the platform. Everyone turned. One of the paper lanterns swayed, though the air around Quinn was still. Beneath it, the maintenance gate stood shut. Water dripped from its lower bar, pattering onto the clean strip of tile. Then a second drop fell, leaving a small dark mark beside the fresh footprint. Quinn crossed to it before anyone else moved. The mark spread in the dust. Not water. Oil. She raised her light and aimed it at the gate. On the inside of the top bar, just within reach of anyone working the lock, a brass-colored smear caught the beam. The wax in the keyhole was newly pressed, its surface ridged by a thumb. “Someone used this gate after the contractor called us,” she said. Voss’s radio was in her hand at once. Quinn heard her ordering officers to cover every exit they could find. Quinn stayed by the gate. A person beyond it could hear them. She could hear nothing back but the drip of water and, farther away, a low scrape that might have been a shoe on stone. She lifted her torch toward the dark passage. In its narrow light, the old brick wall marked on the plans was visible about twenty yards in. It looked solid. The pale grit of several footprints ran straight to it and stopped. Quinn held the beam steady. The wall’s lower course was damp. Across the middle, at shoulder height, a clean circular patch interrupted decades of grime, no wider than the base of a brass compass.
created_at
"2026-09-23T16:28:32Z"
9/23/2026, 4:28:32 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2487
moderation_latency
(null)
generation_time
59051
tokens_prompt
896
tokens_completion
3651
native_tokens_prompt
835
native_tokens_completion
3067
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
0.03234
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790180912-Ye6wOIsu5uhEPasVSiZQ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790180912-LV2TGhmglmjfQ91dXIHu"
upstream_id
"resp_01f91e9949aa34ee016ab3fe3019c087d185bc13af7d30864d"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_01f91e9949aa34ee016ab3fe3019c087d185bc13af7d30864d"
is_byok
false
latency
577
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.03234
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
23
adverbTagCount
1
adverbTags
0
"Eva spoke quietly [quietly]"
dialogueSentences
106
tagDensity
0.217
leniency
0.434
rawRatio
0.043
effectiveRatio
0.019
95.86%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2415
totalAiIsmAdverbs
2
found
0
adverb
"tightly"
count
1
1
adverb
"quickly"
count
1
highlights
0
"tightly"
1
"quickly"
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)
89.65%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2415
totalAiIsms
5
found
0
word
"traced"
count
2
1
word
"velvet"
count
1
2
word
"weight"
count
1
3
word
"measured"
count
1
highlights
0
"traced"
1
"velvet"
2
"weight"
3
"measured"
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
196
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
2
hedgeCount
1
narrationSentences
196
filterMatches
0
"decide"
1
"watch"
hedgeMatches
0
"tried to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
278
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
37
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2415
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
26
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
87
wordCount
1750
uniqueNames
9
maxNameDensity
2.17
worstName
"Quinn"
maxWindowNameDensity
5
worstWindowName
"Eva"
discoveredNames
Harlow
1
Quinn
38
Camden
2
Tube
1
Lena
1
Voss
20
Eva
19
Morris
1
Water
4
persons
0
"Harlow"
1
"Quinn"
2
"Camden"
3
"Lena"
4
"Voss"
5
"Eva"
6
"Morris"
7
"Water"
places
(empty)
globalScore
0.414
windowScore
0
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
134
glossingSentenceCount
1
matches
0
"looked like polished bone, drilled near o"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
2415
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
3
totalSentences
278
matches
0
"knew that tone"
1
"show that something"
2
"followed that line"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
136
mean
17.76
std
17.89
cv
1.007
sampleLengths
0
50
1
14
2
8
3
15
4
4
5
5
6
55
7
93
8
19
9
24
10
29
11
37
12
4
13
13
14
4
15
9
16
6
17
56
18
21
19
5
20
7
21
41
22
24
23
2
24
25
25
2
26
7
27
43
28
52
29
5
30
8
31
5
32
5
33
24
34
10
35
10
36
11
37
38
38
8
39
8
40
18
41
4
42
2
43
5
44
7
45
6
46
19
47
9
48
14
49
1
87.36%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
10
totalSentences
196
matches
0
"been torn"
1
"been shut"
2
"been stripped"
3
"was buttoned"
4
"been folded"
5
"been searched"
6
"been worn"
7
"been buttoned"
8
"been stuffed"
9
"been tied"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
286
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
278
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1752
adjectiveStacks
0
stackExamples
(empty)
adverbCount
41
adverbRatio
0.023401826484018264
lyAdverbCount
12
lyAdverbRatio
0.00684931506849315
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
278
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
278
mean
8.69
std
5.77
cv
0.664
sampleLengths
0
31
1
11
2
8
3
8
4
6
5
4
6
4
7
15
8
4
9
5
10
9
11
15
12
18
13
13
14
18
15
7
16
18
17
5
18
17
19
10
20
18
21
7
22
12
23
5
24
19
25
11
26
18
27
7
28
14
29
6
30
10
31
4
32
13
33
4
34
4
35
5
36
6
37
6
38
14
39
14
40
4
41
11
42
7
43
10
44
11
45
5
46
7
47
8
48
6
49
16
51.08%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
8
diversityRatio
0.3237410071942446
totalSentences
278
uniqueOpeners
90
37.66%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
2
totalSentences
177
matches
0
"Then she saw the thread"
1
"Then a second drop fell,"
ratio
0.011
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
41
totalSentences
177
matches
0
"She glanced at the padlock"
1
"She set her coffee on"
2
"Their light gave the place"
3
"She ducked under the tape."
4
"He lay on his back"
5
"His boots pointed toward the"
6
"His hair was wet at"
7
"His hands were clean."
8
"She touched the outside of"
9
"She looked back at the"
10
"She took one step toward"
11
"Her fingers found a curl"
12
"She thought of DS Morris,"
13
"His last call had come"
14
"She set the memory aside."
15
"It had no place in"
16
"she asked Eva"
17
"She drew out a small"
18
"It looked like polished bone,"
19
"Its surface had been worn"
ratio
0.232
41.92%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
148
totalSentences
177
matches
0
"Detective Harlow Quinn reached the"
1
"A uniform held aside the"
2
"the constable said"
3
"Quinn looked at him."
4
"She glanced at the padlock"
5
"The hasp had been torn"
6
"Someone had pulled the door"
7
"She set her coffee on"
8
"The station had been shut"
9
"Water traced black lines through"
10
"Paper lanterns hung from the"
11
"Their light gave the place"
12
"A market in a closed"
13
"Camden had offered Quinn stranger"
14
"She ducked under the tape."
15
"The air smelled of damp"
16
"DS Lena Voss waited near"
17
"Quinn saw the body between"
18
"He lay on his back"
19
"His boots pointed toward the"
ratio
0.836
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
177
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
23
uselessAdditionCount
1
matches
0
"Eva spoke quietly, as if the empty stalls might hear her"
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
18
fancyCount
2
fancyTags
0
"Eva pressed (press)"
1
"Eva spoke quietly (speak)"
dialogueSentences
106
tagDensity
0.17
leniency
0.34
rawRatio
0.111
effectiveRatio
0.038
86.7844%