NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HYSC5C8969QD6NDJNCZN8
Run Details
Model:
GPT-6 Sol
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
57.7s
Cost:
$0.032940
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
97.99%
AI-ism adverb frequency
(details)
80.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
91.95%
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)
37.73%
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)
87.89%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
82.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
52.27%
Sentence opener variety
(details)
55.56%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
68.33%
Subject-first sentence starts
(details)
83.33%
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)
91.2353%
Overall
Model input
System
You are an expert novelist with a gift for vivid, immersive prose. You write in tight third-person limited point of view with a strong narrative voice. Your prose is clean, precise, and engaging — you favor strong verbs, concrete details, and natural-sounding dialogue. You will be given a story bible (codex) containing canonical details about characters, locations, items, and lore. Use these details to ground your writing in the established world. Stay consistent with the codex. Write only the prose of the scene. Do not include titles, chapter headings, markdown formatting, or any commentary before or after the scene.
User/Human
<codex> <character id="4416" name="Detective Harlow Quinn" aliases="Quinn, Detective Quinn, Harlow" pronouns="she/her" species="Human" storyRole="Antagonist"> <eyeColor>brown</eyeColor> <hair>closely cropped salt-and-pepper</hair> <height>5'9"</height> <age>41</age> <jawline>sharp jaw</jawline> <watch>worn leather watch on her left wrist</watch> <bearing>military precision</bearing> <description>A Metropolitan Police detective with 18 years of decorated service who suspects the clique is involved in criminal activity.</description> <backstory>She lost her partner, DS Morris, during a case three years ago under unexplained circumstances that had supernatural origins she doesn't yet understand.</backstory> </character> <character id="4414" name="Eva Kowalski" aliases="Eva, Evie" pronouns="she/her" species="Human" storyRole="Best Friend"> <eyeColor>green</eyeColor> <hair>curly red</hair> <height>5'4"</height> <age>26</age> <glasses>round glasses</glasses> <satchel>worn leather satchel full of books</satchel> <freckles>freckled complexion</freckles> <nervousHabit>tucking hair behind her left ear</nervousHabit> <description>Aurora's childhood friend and an occult researcher.</description> <backstory>Moved to London two years before Aurora and works as a research assistant at the British Museum's restricted archives. She holds a master's degree in Ancient History from Oxford.</backstory> </character> <location id="856" name="The Veil Market" aliases="Veil Market, the Market, underground market" realm="Earth"> <currentLocation>abandoned Tube station beneath Camden</currentLocation> <entryRequirement>bone token</entryRequirement> <schedule>moves locations every full moon</schedule> <description>A hidden supernatural black market that sells enchanted goods, banned alchemical substances, and information.</description> </location> <item id="2004" name="Veil Compass" aliases="the Compass, shadow compass" type="Tool" origin="The Veil Market"> <casingMaterial>small brass compass</casingMaterial> <faceMarkings>face etched with protective sigils</faceMarkings> <needle>points toward the nearest supernatural rift or portal</needle> <patina>casing has a patina of verdigris</patina> <creator>crafted by a Shade artisan</creator> <description>A compass attuned to supernatural energy.</description> </item> </codex> Write a fully fleshed out scene of at least 1000 words in the mystery genre. A detective arrives at a crime scene in an unusual location. Something is wrong — the evidence doesn't add up. A colleague is present, offering a different interpretation. Through careful observation and deduction, the detective begins to see what others have missed. Use the codex entries above as your world reference for characters and setting. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
The call had said burglary, one injured suspect, possible weapons.
By the time Detective Harlow
Quinn reached the old Tube entrance beneath Camden, the injured suspect had become a dead man and the burglary had become a room nobody could explain.
A constable stood beside a
locked service gate, rain shining on the shoulders of his high-vis jacket. Beyond him, tiled steps descended into darkness. “Who found him?” Quinn asked. “Council maintenance crew. Came to check a report of water in the tunnels. They found the gate open and called it in.” “Was it open when you arrived?”
He glanced at the padlock
hanging from its chain. “Maintenance locked it after they came back up.”
Quinn took the key he
offered.
The lock was wet on
one side, dry beneath the shackle. Fresh scratches scored the painted gatepost.
Downstairs, the station smelled of
damp stone, hot wiring and something sweeter that had already gone stale.
Battery lamps stood at intervals
along the platform.
Their light picked out the
old roundel on the wall, half buried beneath soot and mineral bloom. On the tracks, a shallow film of black water held a trembling reflection of the ceiling.
Detective Sergeant Nisha Patel waited
near the far end of the platform, blue overshoes bright against the grime.
She held a notebook open
in one hand. “You’ll want to see the body before they move him,”
Patel
said. “I’m told it was a burglary.” “I think someone used the place for dealing. He came to collect, there was an argument, and someone put a blade in him.”
She looked down the platform
. “Possibly more than one someone.” Quinn followed her gaze. Temporary stalls had
been assembled
along both walls: folding tables, timber crates, lengths of dark cloth strung from exposed pipes. Most had
been stripped
. One table held an empty
velvet
-lined case; another, a neat row of unstoppered brown bottles. Beneath a lamp, a chalkboard advertised prices in three currencies Quinn recognised and four she did not.
The floor told a livelier
story than the abandoned stalls.
Mud, spilled powder and hundreds
of shoeprints crossed the tiles.
Someone had carried away merchandise
in a hurry. “You didn’t call uniforms in?” Quinn asked. “Two came down with the maintenance men. I sent them back to the gate. Forensics are on their way.” “Good.”
Patel
stopped beside a ticket booth whose glass had
been painted
black from the inside.
A man lay in the
narrow gap between booth and wall.
He was perhaps thirty, dressed
in a wool coat too fine for the damp.
A knife protruded from his
chest.
His right hand rested open
against the tiles. Quinn crouched without touching him.
His shoes were clean along
the upper leather, muddy at the soles. There was blood on his shirt, on the knife handle, and in a dark pool beneath his ribs. None marked the wall behind him.
Patel
turned a page. “No wallet. No phone. Maintenance found him at six forty. The crew supervisor says the station’s been sealed for years. He’s offered to show us the paperwork.” “He needn’t. Someone’s been paying for electricity.”
Patel
looked up at the working lamps. “The crew says those weren’t here.” “They’re battery-powered. I mean the wiring.” Quinn pointed to a thin cable running above the stalls.
Its insulation had been cut
neatly, then twisted into the station’s original circuit. “That splice has tape on it. Recent tape.” “Not necessarily recent.” “The tape is still blue.”
Patel
made a note. Quinn leaned closer to the dead man.
His open palm had a
pale circular patch in its centre, the size of a ten-pence piece, while the rest of his skin was stained with fine grey dust. Two flecks clung to the web of his thumb. “Did you find anything in his hand?” “No.” “He was holding something.” “His killer took it.” “Maybe.” Quinn stood. “Who moved him?” “No one.” “He didn’t fall here.”
Patel
glanced at the blood. “He was stabbed and staggered into the gap.” “With the knife still in him? There’s no blood on the wall, and it’s too narrow to miss if he stumbled through. Look at his coat.” A chalky line crossed the back of the man’s left shoulder. At the same height, a smear marked the wall opposite. Not a glancing touch: his coat had dragged along it for nearly a metre. “He was carried,”
Patel
said. “Or pulled.” Quinn looked at the man’s shoes again. “Soles touched the floor. Heels first, by the marks. Someone brought him in here after he died.”
Patel
closed her notebook halfway. “That still sounds like a deal gone wrong.” “It might be. Who was here when maintenance came down?” “No one. They heard movement on the platform, but by the time they reached it, the place was empty.” “Which direction?” “Down the east tunnel. That’s where they thought the water leak was.” Quinn took a lamp from its stand and walked toward the tunnel mouth.
Its beam slid over torn
paper, a smashed bottle and a little white disc lying beside the rail. She crouched. Bone, polished by handling, carved with a shallow notch through its centre.
She had seen its likeness
in photographs recovered from a Camden flat last month: a set of twelve kept in a biscuit tin, with no buyer or seller willing to say what they were for. “
Patel
.”
Patel
came over. Quinn showed her the disc without lifting it. “A gaming counter?”
Patel
said. “Or admission.” “To what?” Quinn looked back at the stalls. “This.” The east tunnel opened into a section of track screened by a tarpaulin. Behind it stood a makeshift barrier of steel shelving and pallets. Someone had knocked the central pallets aside, leaving a gap just wide enough to pass through. “They ran this way,”
Patel
said. “Maintenance heard them.” “Perhaps.” Quinn swung the light down. Footprints converged on the opening, muddied at their toes. Past it, she could see only a few more metres of track before the tunnel bent out of sight. She stepped through. Water soaked the edge of her overshoe. On the far side, the dust lay undisturbed.
Patel
followed. “They could have gone through the water.” “It’s an inch deep. There’s silt on top.” Quinn set the lamp low. A thin skin of grit floated there, intact except where a slow drip struck it from above. “Nobody crossed this way.” “Then they went back over the platform before the crew saw them.” “Possibly. Why break the barrier?”
Patel
had no answer. Neither did Quinn, yet.
She returned to the dead
man. From the tunnel mouth, she could
see that his
coat hem was wet. The drag marks ended three feet short of his body, where the floor became clean tile.
Whoever had moved him had
lifted him for those last few steps. A crime scene officer arrived with a camera and began photographing the body. Quinn directed her to the drag marks, then went to the nearest stall. The
velvet
-lined case had a small circular indentation in its centre, flecked green around the rim. Beside it lay a card with one word written in block capitals: COMPASS.
Patel
read it over her shoulder. “Someone stole the merchandise.” “From a room where everyone else left theirs behind?” “They took what was valuable.” Quinn surveyed the empty tables. “Those bottles were uncorked before anyone knocked them over. And look at the cloth.” A length of fabric hung from a pipe above them, its cut edge straight. Six other lengths around the platform had
been taken
down in the same way, leaving loops of string tied to the pipes. Traders had packed what they could carry. They hadn’t
been robbed
. “Something sent them running,” Quinn said.
Patel
’s gaze returned to the dead man. “Him?” Quinn remembered the open hand, its clean circle. “Maybe what he was carrying.” The crime scene officer waved her closer. “Detective. There’s something beneath his sleeve.” Quinn stepped to the body. The officer eased back the cuff with forceps, exposing a leather strap caught beneath the man’s watchband. A broken thread hung from it. Beside the cuff, half hidden under the coat, was a smear of green. “Photograph it first,” Quinn said.
While the camera flashed, she
looked at her own worn leather
watch
. Six fifty-eight. The dead man’s
watch
, an expensive steel model, had stopped at 6:12. Its glass was unbroken. Water had seeped under the face. “Maintenance heard movement at six forty,”
Patel
said. “If that
watch
stopped when he got wet—” “He was wet before they arrived.” Quinn pointed to the hem. “But the platform floor is dry here. The east tunnel water’s black with silt. His coat’s wet with clean water.”
Patel
looked toward the tracks. “Where would he get clean water?” Quinn turned
slowly
, following the cable above the stalls to a maintenance door set into the wall. The paint on its handle was worn bright. Beneath it, a narrow tide mark ran along the tiles and vanished under a mat laid in front of the door.
She lifted the edge of
the mat. The tiles beneath were wet. “Here.” The door opened onto an old staff washroom. A tap stood over a deep
porcelain
sink, its basin clean except for one dark drop near the drain. Water shone on the floor. Someone had wiped down the counter but missed the underside of its lip, where a thin reddish line remained.
Patel
leaned in. “They cleaned up after moving him.” “Before. Look at the floor.” The wet shoeprints ran out of the washroom toward the booth. At the threshold, the first print was sharp enough to show a crescent cut in the heel. Each successive print grew fainter. Quinn had seen the same cut at the edge of the dead man’s left shoe.
He had walked out of
the washroom. “He went in there alive,” Quinn said. “With blood on him.” “Then someone stabbed him at the sink?” “The knife’s in his chest. You’d expect blood in the basin if they stabbed him here and washed up. There’s barely any.” She examined the faucet. Grey dust had settled around its base, except for a clean oval where an object had rested. A green stain marked one edge. The compass. The man had put it beside the sink, then taken it up again. Quinn went back to his body. The knife had entered below his breastbone, its handle angled toward his right shoulder.
His shirt was cut around
the blade, but the wool coat was not. “He was stabbed before he put his coat on,” she said.
Patel
stared at her. “Why would he put his coat on with a knife in him?” “He wouldn’t.” Quinn crouched. The coat
was buttoned
wrong: the lowest button strained in the second-lowest hole. The man’s shirt collar had
been pulled
crooked, and one lapel covered part of the knife handle. Someone had dressed him after the stabbing. The coat hem had got wet when they dragged him out of the washroom. “He bled here, then,”
Patel
said. “They moved him, dressed him, and tried to make it look as if he’d been stabbed in the booth.” “Why?” The question sat between them. Quinn looked at the narrow gap, the open palm, the clean circle where something round had rested. Someone had placed an object in the man’s hand after they brought him here. Later, someone had taken it.
She searched the tiles around
the body. A faint line of pale dust ran from his fingertips toward the ticket booth door. It ended beneath the door’s metal sill. Quinn asked the crime scene officer to photograph the line.
Then she pulled on fresh
gloves and opened the booth. Inside, the counter was bare except for a cracked fare ledger. At floor level, an old return slot had been cut into the wall. The metal flap hung loose. She put her lamp close. Behind the flap, something brass caught the light. “Don’t touch it,”
Patel
said. “I won’t.” The officer photographed it in place, then drew it out with padded forceps. It was a small brass compass with verdigris in its seams. Protective sigils had
been etched
around the face in lines too fine to read without magnification. The needle swung once, twice, and settled—
not north, but toward the tiled wall behind Quinn
.
Patel
watched it. “Magnet in the wall.” “Could be.” The officer carried it a few steps down the platform. The needle held its angle toward the same stretch of tile. Quinn followed its point to an old advertising panel. Its glass had
been painted
over. The frame sat flush at the top and stood proud at the bottom, where fresh mortar dust had gathered in a white ridge.
Patel
tried the panel’s edge. It moved beneath her fingers. “Wait for the photographer,” Quinn said.
Patel
withdrew her hand. They both stepped back while the officer documented the frame. Then Quinn eased it open. Behind the panel was no passage. A bricked recess held a square of black glass, roughly the size of a lift mirror. Quinn’s lamp made a hard white spot on its surface. She shifted the beam and saw the platform reflected behind her: the stalls, the lights,
Patel
standing at her shoulder. In the glass, the ticket booth door was open. The dead man was not there. Quinn turned. He lay exactly where they had left him, the officer kneeling beside him. The glass reflected the officer too, down to the camera strap at her neck. It simply omitted the body.
Patel
said nothing. Quinn held the lamp steady, though the worn leather of her
watch
strap had gone tight against her wrist. Three years earlier, DS Morris had vanished from a locked interview room. The video showed him going in and never coming out. Quinn had spent months
proving that cameras
could fail, doors could be forced, witnesses could lie. None of it had brought him back. The compass needle pointed into the glass. A sound came from the other side: a single, patient knock. Quinn lowered the lamp just enough to see her own reflection. Its mouth was closed. So was
Patel
’s. “Get everyone upstairs,” Quinn said. “Now.”
Patel
hesitated only long enough to look at the body once more.
Then she called to the
crime scene officer. Quinn stayed by the open panel. The market had emptied through a passage nobody could find. The man had reached the washroom alive and had
been killed
after he came out. Someone had dressed him, dragged him to the booth and put the compass in his hand. He had dropped it through the return slot—or someone had hidden it there for him. The glass showed her a vacant platform. In its reflection, the ticket booth door
began to
close. Quinn stepped aside. Behind her, the real door remained open.
created_at
"2026-09-23T16:35:36.469Z"
9/23/2026, 4:35:36 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2206
moderation_latency
(null)
generation_time
57686
tokens_prompt
896
tokens_completion
3765
native_tokens_prompt
835
native_tokens_completion
3127
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
0.03294
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790181336-pc7eIPJrzIGQi8xDGy64"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790181336-q6w5j37jR2Tg6xKDRr9y"
upstream_id
"resp_083108327f8f497c016ab3ffd8965087d1b7c6c1795d922720"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_083108327f8f497c016ab3ffd8965087d1b7c6c1795d922720"
is_byok
false
latency
488
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.03294
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
21
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
83
tagDensity
0.253
leniency
0.506
rawRatio
0
effectiveRatio
0
97.99%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2486
totalAiIsmAdverbs
1
found
0
adverb
"slowly"
count
1
highlights
0
"slowly"
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)
91.95%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2486
totalAiIsms
4
found
0
word
"velvet"
count
2
1
word
"porcelain"
count
1
2
word
"etched"
count
1
highlights
0
"velvet"
1
"porcelain"
2
"etched"
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
202
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
3
hedgeCount
1
narrationSentences
202
filterMatches
0
"watch"
hedgeMatches
0
"began to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
264
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
35
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
18
unquotedAttributions
0
matches
(empty)
37.73%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
84
wordCount
1915
uniqueNames
10
maxNameDensity
2.25
worstName
"Quinn"
maxWindowNameDensity
3.5
worstWindowName
"Quinn"
discoveredNames
Detective
2
Harlow
1
Quinn
43
Tube
1
Camden
2
Sergeant
1
Nisha
1
Patel
29
Morris
1
Water
3
persons
0
"Harlow"
1
"Quinn"
2
"Sergeant"
3
"Nisha"
4
"Patel"
5
"Morris"
6
"Water"
places
0
"Camden"
globalScore
0.377
windowScore
0.5
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
140
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 toward the tiled wall behind Quinn"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
2
totalSentences
264
matches
0
"see that his"
1
"proving that cameras"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
122
mean
20.36
std
18.27
cv
0.897
sampleLengths
0
41
1
24
2
5
3
22
4
6
5
17
6
23
7
58
8
26
9
12
10
6
11
33
12
60
13
28
14
7
15
19
16
1
17
54
18
41
19
31
20
7
21
13
22
37
23
3
24
5
25
49
26
7
27
1
28
4
29
4
30
6
31
2
32
4
33
13
34
26
35
35
36
5
37
26
38
13
39
10
40
19
41
2
42
12
43
80
44
1
45
11
46
5
47
2
48
2
49
7
87.89%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
10
totalSentences
202
matches
0
"been assembled"
1
"been stripped"
2
"been painted"
3
"been taken"
4
"been robbed"
5
"was buttoned"
6
"been pulled"
7
"been etched"
8
"been painted"
9
"been killed"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
310
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
2
semicolonCount
1
flaggedSentences
3
totalSentences
264
ratio
0.011
matches
0
"One table held an empty velvet-lined case; another, a neat row of unstoppered brown bottles."
1
"The needle swung once, twice, and settled—not north, but toward the tiled wall behind Quinn."
2
"He had dropped it through the return slot—or someone had hidden it there for him."
82.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1923
adjectiveStacks
3
stackExamples
0
"injured suspect, possible weapons."
1
"empty velvet-lined case;"
2
"hard white spot on its"
adverbCount
43
adverbRatio
0.02236089443577743
lyAdverbCount
8
lyAdverbRatio
0.004160166406656267
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
264
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
264
mean
9.41
std
6.03
cv
0.641
sampleLengths
0
10
1
31
2
17
3
7
4
5
5
22
6
6
7
9
8
8
9
6
10
11
11
6
12
17
13
8
14
17
15
16
16
18
17
8
18
12
19
6
20
28
21
5
22
4
23
20
24
4
25
15
26
17
27
10
28
10
29
8
30
7
31
19
32
1
33
15
34
11
35
14
36
6
37
8
38
5
39
12
40
18
41
6
42
4
43
27
44
7
45
7
46
6
47
16
48
13
49
8
52.27%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
7
diversityRatio
0.32954545454545453
totalSentences
264
uniqueOpeners
87
55.56%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
3
totalSentences
180
matches
0
"Then she pulled on fresh"
1
"Then Quinn eased it open."
2
"Then she called to the"
ratio
0.017
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
31
totalSentences
180
matches
0
"He glanced at the padlock"
1
"Their light picked out the"
2
"She held a notebook open"
3
"She looked down the platform"
4
"He was perhaps thirty, dressed"
5
"His right hand rested open"
6
"His shoes were clean along"
7
"Its insulation had been cut"
8
"His open palm had a"
9
"Its beam slid over torn"
10
"She had seen its likeness"
11
"She stepped through."
12
"She returned to the dead"
13
"They hadn’t been robbed."
14
"Its glass was unbroken."
15
"She lifted the edge of"
16
"He had walked out of"
17
"She examined the faucet."
18
"His shirt was cut around"
19
"She searched the tiles around"
ratio
0.172
68.33%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
141
totalSentences
180
matches
0
"The call had said burglary,"
1
"A constable stood beside a"
2
"He glanced at the padlock"
3
"Quinn took the key he"
4
"The lock was wet on"
5
"Downstairs, the station smelled of"
6
"Battery lamps stood at intervals"
7
"Their light picked out the"
8
"Detective Sergeant Nisha Patel waited"
9
"She held a notebook open"
10
"She looked down the platform"
11
"Quinn followed her gaze."
12
"The floor told a livelier"
13
"Mud, spilled powder and hundreds"
14
"Someone had carried away merchandise"
15
"Patel stopped beside a ticket"
16
"A man lay in the"
17
"He was perhaps thirty, dressed"
18
"A knife protruded from his"
19
"His right hand rested open"
ratio
0.783
83.33%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
3
totalSentences
180
matches
0
"By the time Detective Harlow"
1
"Whoever had moved him had"
2
"While the camera flashed, she"
ratio
0.017
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
91
technicalSentenceCount
0
matches
(empty)
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
21
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
15
fancyCount
0
fancyTags
(empty)
dialogueSentences
83
tagDensity
0.181
leniency
0.361
rawRatio
0
effectiveRatio
0
91.2353%