NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHT0RF3XJ40DM622ST9FRDJK
Run Details
Model:
GPT-5.1
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
1m 20s
Cost:
$0.051961
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)
68.87%
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)
100.00%
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)
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)
70.38%
Sentence opener variety
(details)
21.23%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
87.39%
Subject-first sentence starts
(details)
63.69%
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)
93.0523%
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 old station swallowed sound.
Harlow took the last steps
down from street level and the hum of Camden at night thinned to a faint shiver through the brickwork.
Her torch beam caught flakes
of green paint curling from the handrail, then slid over cracked cream tiles and a rusted Underground roundel, the red almost gone. Two uniforms waited at the barrier. One shifted his
weight
when he saw her, boots scraping the grit. “Detective Quinn. Scene’s on the far platform. SOCO’s still working.” She ducked under the tape.
Her leather watch pinched her
wrist when she lifted the line; she didn’t adjust it.
The air grew colder past
the barrier, with a smell of old water and metal and something sharp beneath it, like burnt dust.
The concourse opened into the
disused ticket hall, wide and empty, except for stacks of old timetables sagging against a wall. Light rigs threw white pools across the floor, leaving the ceiling in shadow.
Graffiti climbed the tiles, fresh
colours over ghosted advertisements for films no-one watched anymore.
Amir Patel waited by the
stair down to the platforms. He rested against the rail, tie loose, scene suit only half-zipped. “Took your time.” “You pulled me across town for an old Tube station,”
Harlow walked past him, kept
going down. “Better be worth the petrol.” “You’ll love it. Proper ghost story for you.”
His trainers clacked behind her
as he followed.
The tunnel to the platforms
bent left.
The air grew wetter, the
smell of oil thicker, though the tracks ahead had no shine, just dust and the dark thread of old grease. “Power to the line’s been cut for years,”
Patel
’s voice bounced off the tunnel. “No trains. No squatters. No bloody reason for anyone to come down here at all.” “So how did he get in.” “Good question. Gate upstairs was locked and chained when response units arrived. Had to cut it.” “Keys?” “Nothing on him. You’ll see.”
The tunnel spat them out
onto the platform. Light rigs glared off the white tiles and turned dust into drifting veils.
The tracks beside the platform
slept under a film of grime broken by a few scuffed patches where boots had stepped.
The body lay ten metres
down, in the middle of the platform, inside a ring of black.
Forensics clustered around it in
white suits, masks up, gloved hands moving in small, precise arcs. A camera flashed. Harlow stopped at the edge of the circle. The black stain spread across the tiles in an almost
perfect
loop, a band the width of her palm, edges crisp. Not spattered. Not smeared.
Just there, painted by something
that had no brush.
Patel
came to stand opposite her on the other side of the ring. “Male, thirties. No wallet. No phone. No obvious ID. SOCO’s still digging.”
She swept the beam of
her torch along the circle. The stain wasn’t paint. The glaze on the tiles had crazed under it, hairline fractures spidering toward the grout. In a few spots, the ceramic had bubbled. “Fire?”
He pointed to the light
rig. “If it was, it burned fast. No soot on the ceiling. Nothing outside the circle. Clothes aren’t charred.”
She stepped around the ring
to the gap the pathologist had left. The man lay on his back, arms at his sides, fingers half-curled.
His jeans held one tear
at the knee. Black hoodie, unbranded. Trainers cheap but new. Skin waxy and tight, lips pulled back a fraction from his teeth. His eyes had gone. The sclera and iris had collapsed into two black pits, edges glassy.
As if someone had set
a match inside the sockets and let it burn out. Harlow straightened, the muscles between her shoulder blades knotting. “Electrocution?”
Patel
’s mouth twitched. “That’s the working theory. Lines may be cut but there’s still power down here. Emergency lighting. Comms. You know the old boys who nick copper out of live substations.” “He doesn’t look fried.” “Burns on the soles of his feet. Clothes dry. No external bleeding. Medical examiner reckons current went up through his shoes, cooked him inside. Popped his eyes.” She looked at the tracks. No cable. No sign of any panel forced. The dust lay unbroken except for that thin trail of footprints from the tunnel mouth to the ring and away along the edge where the first uniforms had moved. “Where did he touch?”
She met Patel’s eyes
. He shrugged. “Maybe he tried to jump down, grabbed something. They’re still
tracing
it.” “There’s no disturbance on the ballast.” “So he didn’t jump.” “Then the current came to him.”
Patel
rubbed the back of his neck, slicking the collar of his shirt. “You hear yourself?” She crouched beside the body. The man’s hoodie bunched at his shoulder, revealing a line of ink along his collarbone. Not gang script. Not elaborate. Four straight strokes like the points of a compass, joined at the centre.
Her torch picked something at
his hip. A thin cord trailed from his pocket. The SOCO nearest shifted his boots out of her way. “In his front left,” he murmured through his mask, then went back to his evidence markers.
She eased the pocket open
with the edge of her glove. A small brass disc lay inside, attached to the cord.
She used a forceps one
of the techs handed her without comment and lifted it into the light. A compass. Palm-sized, brass casing eaten with green in the grooves. The cover bore a shallow
etching
, lines and curls that at first looked random, then
resolved
into shapes that teased memory. Not letters. Not any she recognised.
She flicked the lid with
her thumb.
It opened with a faint
rasp. The glass over the face had a crack from edge to centre, like a single thin lightning strike. The needle shook, then settled. Not north. It pointed along the platform, into the tunnel at the far end, away from the stairs and the way out.
Patel
watched her hand. “Tourist tat. Camden stall job.” “Tourists don’t bring tat down here.” “Maybe he worked a stall topside. Knick-knack fallen into the pocket of a hoodie. Doesn’t scream murder weapon.” Her gaze returned to the ring. “What time did control get the call?” “Twenty-three twenty. Anonymous. Male voice, sounded local. Gave the station name, said, ‘He’s down there, he’s not right,’ and hung up.” “No CCTV.”
Patel
’s mouth went thin. “Place hasn’t had cameras since the eighties. Closest working ones cover the street entrance. Nothing but a fox passing through an hour before response units.” She closed the compass and handed it back to the tech for bagging. Her eyes moved over the platform again, slow now, slicing the scene into sections. White tile. Black ring. Body. Light rigs. Tripods. Beyond the light, further down the platform where the rigs didn’t reach, darkness thickened. Something broke the straight line of the wall down there. Stalls. Shapes. Piles of… crates? “Amir.” He’d already turned to follow her gaze. “Yeah. That’s new on the Underground. Thought I’d walk you down.” They skirted the evidence markers and moved along the wall. The tiles here carried more graffiti, layered until colours bled. Between two tags in fat, dripping letters, someone had scratched lines straight into the glaze. Circles, triangles, a six-point star. Not gang work. Too careful. “You get our neighbourhood kids with compasses now,”
Patel
snorted. “Upgrade from spray cans.” Her fingers rested over the marks without touching. The scratches matched the faint patterns on the compass lid. Same hand? Same habit of line. Deep enough to chip the tile, not enough to flake it. Recent. “How old d’you reckon these are.” “Fresh chips on the floor. I’d say last few days.” “At least we know our victim wasn’t the only one down here.” “That,”
Patel
kicked a loose bottle cap off the edge with his boot, “already goes without saying.” The darkness ahead
resolved
into
structure
. Rough wooden tables jammed together, some with stained cloths still hanging from the edges. Crates sat stacked three high, many open and empty, a few with shredded paper inside. A makeshift bar, cobbled from planks and old Underground signs, leaned at an angle. Harlow paused at the first table. Rings on the surface marked where jars had stood. Something greasy stained one corner, spread in thumbprints toward the floor. The smell here changed, undercutting the dust and metal. Herbs. Bitter, resinous, sharp enough to sting her nostrils. “Rave set-up?”
Patel
walked ahead, hands on his hips. “Pop-up market. Kids sneak down, flog pills and bootlegs, make it look edgy. This end’s out of our usual patrol routes.” “Music decks?” “No decks. No cans. No glow sticks. But lots of tables to sell things from.” He nudged a crate with his foot. Inside, scraps of grey cloth and black glass winked in her torch beam. Bottles, round-bottomed, smashed in transit or under a boot. Some still held crusted residue at the neck, white as bone ash. Harlow picked up a shard with tweezers from a SOCO’s box. The inside had a film of something
crystalline
, too coarse for sugar, too dull for salt. “What’s your poison,” she lifted the shard and let the torch catch it.
Patel
scratched his jaw. “New designer nonsense. I’ve sent samples up. My money’s on party favours. Explains why you’d hold an underground market in an abandoned station. Hidden, atmospheric, feeds the legend.” “Legend?” “You know. London under London. Secret tunnels. Ghost trains. Charge double for a pill if you sell it somewhere daft enough.” Harlow’s torch skimmed more tables. Burn marks. Circular stains
etched
into the wood, as if hot plates had sat there. Scorching never spread outside the neat outlines. “SOCO get prints?” “Partial, all over. Gloves most of the time. A few nice, clear latents on the bar and the stair rail. Already on their way to IDENT. My guess, our victim’s prints will be in the mix.” She stopped near the end of the platform. A chalk line marked a square on the flagstones, the chalk thick, re-
traced
several times. Within the square, the tiles looked cleaner. No dust, no scuffs. Two small dark flecks rested in the centre. She lowered herself, knees near the chalk. The flecks gleamed a dull brown. “Blood,”
Patel
’s boots crunched the grit behind her. “We found that before the rig came in. Only spot apart from anything under him.” “Swabs?” “Already gone. Lab will tell us whose.” “Trail?” “Nothing. No drips, no smears. Just those.” Her torch picked out the edges of the chalk lines. They met at neat right angles. At each corner, a small circle, blackened like the ring around the corpse. “You ever see squatters put this much work into decorating floor space.” “Squatters? No. Dealers? Maybe they like a bit of theatre. Pentagram chic.” “Marking out a stall makes sense.” She stood and looked back down the platform toward the body, from this end now. The black ring hugged the centre line, equidistant from both edges. Perfect shape. No flat spots. Beyond it, in the distance, the compass-faced graffiti on the wall lined up with the dead man’s feet. From here, the lines pointed straight through him. “Harlow.”
Patel
watched her. “You’re frowning. That look normally ends with more paperwork for me.” “Your anonymous caller. Voice stressed? Calm?” “Middle. No panic. No shouting. Like he’d already seen it once.” “Or caused it.” “If he did, why wait around to call? Why not vanish, let the cleaners find the body in a decade.” She stared at the ring again. The fractures in the tile caught the light, each tiny crack running inward, toward a point under the corpse’s spine. “How long from call to first unit on scene.” “Seven minutes. Cars were close.” “And the body?” “Still warm, according to first medic.
Not much, but enough
.” She ran the numbers without a
watch
. Twenty-three twenty call. Seven minutes. Arrival. Allow a minute for them to force the gate. Time of death…
if he’d just gone, they
should’ve found smell of burned fabric, lingering heat in the air, some
echo
of whatever had done this. The air now held that sharp, burned-dust smell, but faint. Not seven minutes faint. Older. It sat in the brick, the tiles, soaked in. “Any reports of power surges on the grid.” “Already checked with Transport. Nothing flagged.” “So a man cooks himself from the inside in a dead station, with stable power, no cables, inside a
perfect
ring, right under a compass scratched on a wall and carrying another in his pocket, next to a pop-up market that packs up neat enough to leave chalk squares and empty bottles, and someone up top thinks it’s worth a seven-minute-fast call but not worth giving a name.” He winced at the list. “Sounds messy when you put it like that.” “It is messy.” She walked back toward the body, letting her torch trace every change in the floor. Halfway along the platform, the dust pattern broke. A set of prints smaller than uniform boots, tread narrower, cut across from the platform edge to the wall, then vanished at the black ring. She knelt, touched the air above them. Trainers, not steel-toes. Deeper at the heel, like someone had paused there, pushed off. The final step landed right at the ring’s boundary. No imprint inside. She pointed.
Patel
leaned in. “We clocked those. Could be his, before he dropped.” “He wouldn’t jump the ring if he didn’t know it was there. No scuff. No overlap. He stopped at the line.” “And?” “And he ended up in the middle.”
Patel
’s eyes
flicked
from the prints to the corpse, then to the compass bagged nearby on a tripod tray. “Maybe he stepped in, wiped them on the burn before it set. Maybe the surface… I don’t know, sealed over.” “You want to hang an explanation on ‘maybe’?” “You got a better one?” Her thumb tapped against her watchstrap. The faint smell in the air pressed at the back of her throat now, and under it something older, a memory of another warehouse, another ring scorched into concrete, a different body on its back with the same hollow eyes. Three years gone and still the image rose when she closed her eyes on a bad night. She opened them wider instead and looked at the compass again, the needle steady, pointing away from north and deeper into the dark tunnel. “Get me the grid maps for every disused station within a mile,” she spoke without turning. “Any reports of unauthorised access, trespass, abandoned gatherings. I want them tonight.”
Patel
blew out through his nose. “You think this is a pattern.” “I think this isn’t a one-off stunt for some rave kids.” “For all we know, he licked the wrong pill.” “Pills don’t make tiles crack.” She stepped over to the tripod and picked up the evidence bag with the compass. The plastic crinkled under her glove. Through it, the brass casing caught the light of the rigs, sigils on the lid
etched
deep and precise. She pinched the edge, turned it until the face looked straight up at her. The needle floated free inside, then swung again as if tugged by something beneath the floor. It settled, once more, pointing into the tunnel’s mouth.
created_at
"2026-02-19T03:58:04.934Z"
2/19/2026, 3:58:04 AM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3691
moderation_latency
(null)
generation_time
80037
tokens_prompt
1149
tokens_completion
5142
native_tokens_prompt
1009
native_tokens_completion
5070
native_tokens_completion_images
0
native_tokens_reasoning
1701
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
0.05196125
router
(null)
provider_responses
0
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
id
"resp_05d72f69e8ef61ca0169968a4d05f4819384327dd9002c503c"
is_byok
false
latency
210
model_permaslug
"openai/gpt-5.1-20251113"
provider_name
"OpenAI"
status
200
api_type
"completions"
id
"gen-1771473484-LgCprMhMMXNdMe9MlIqT"
upstream_id
"resp_05d72f69e8ef61ca0169968a4d05f4819384327dd9002c503c"
total_cost
0.05196125
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
12
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
87
tagDensity
0.138
leniency
0.276
rawRatio
0
effectiveRatio
0
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2570
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)
68.87%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2570
totalAiIsms
16
found
0
word
"weight"
count
1
1
word
"perfect"
count
3
2
word
"tracing"
count
1
3
word
"etching"
count
1
4
word
"resolved"
count
2
5
word
"flicked"
count
2
6
word
"structure"
count
1
7
word
"crystalline"
count
1
8
word
"etched"
count
2
9
word
"traced"
count
1
10
word
"echo"
count
1
highlights
0
"weight"
1
"perfect"
2
"tracing"
3
"etching"
4
"resolved"
5
"flicked"
6
"structure"
7
"crystalline"
8
"etched"
9
"traced"
10
"echo"
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
185
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
0
narrationSentences
185
filterMatches
0
"watch"
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
260
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
71
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2554
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
10
unquotedAttributions
0
matches
(empty)
100.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
30
wordCount
1703
uniqueNames
5
maxNameDensity
1
worstName
"Patel"
maxWindowNameDensity
2
worstWindowName
"Patel"
discoveredNames
Camden
1
Underground
2
Patel
17
Harlow
7
Light
3
persons
0
"Patel"
1
"Harlow"
places
0
"Light"
globalScore
1
windowScore
1
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
125
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.392
wordCount
2554
matches
0
"Not much, but enough"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
260
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
130
mean
19.65
std
15.25
cv
0.776
sampleLengths
0
5
1
51
2
18
3
10
4
43
5
48
6
21
7
3
8
22
9
8
10
40
11
29
12
6
13
16
14
1
15
5
16
42
17
36
18
42
19
13
20
12
21
37
22
1
23
24
24
51
25
4
26
27
27
9
28
1
29
32
30
4
31
27
32
42
33
8
34
14
35
6
36
4
37
6
38
16
39
38
40
24
41
16
42
39
43
38
44
36
45
2
46
20
47
9
48
6
49
18
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
185
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
252
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
1
flaggedSentences
1
totalSentences
260
ratio
0.004
matches
0
"Her leather watch pinched her wrist when she lifted the line; she didn’t adjust it."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1713
adjectiveStacks
0
stackExamples
(empty)
adverbCount
42
adverbRatio
0.024518388791593695
lyAdverbCount
1
lyAdverbRatio
0.0005837711617046118
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
260
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
260
mean
9.82
std
7.8
cv
0.794
sampleLengths
0
5
1
24
2
27
3
6
4
12
5
10
6
5
7
15
8
23
9
21
10
13
11
14
12
10
13
11
14
3
15
17
16
5
17
8
18
8
19
7
20
25
21
14
22
15
23
6
24
16
25
1
26
5
27
8
28
13
29
21
30
17
31
16
32
3
33
8
34
21
35
2
36
2
37
9
38
13
39
12
40
10
41
4
42
15
43
8
44
1
45
6
46
18
47
12
48
12
49
8
70.38%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
12
diversityRatio
0.45
totalSentences
260
uniqueOpeners
117
21.23%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
157
matches
0
"Just there, painted by something"
ratio
0.006
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
45
totalSentences
157
matches
0
"Her torch beam caught flakes"
1
"She ducked under the tape."
2
"Her leather watch pinched her"
3
"He rested against the rail,"
4
"His trainers clacked behind her"
5
"She swept the beam of"
6
"He pointed to the light"
7
"She stepped around the ring"
8
"His jeans held one tear"
9
"His eyes had gone."
10
"She looked at the tracks."
11
"She met Patel’s eyes"
12
"She crouched beside the body."
13
"Her torch picked something at"
14
"he murmured through his mask,"
15
"She eased the pocket open"
16
"She used a forceps one"
17
"She flicked the lid with"
18
"It opened with a faint"
19
"It pointed along the platform,"
ratio
0.287
87.39%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
117
totalSentences
157
matches
0
"The old station swallowed sound."
1
"Harlow took the last steps"
2
"Her torch beam caught flakes"
3
"She ducked under the tape."
4
"Her leather watch pinched her"
5
"The air grew colder past"
6
"The concourse opened into the"
7
"Graffiti climbed the tiles, fresh"
8
"Amir Patel waited by the"
9
"He rested against the rail,"
10
"Harlow walked past him, kept"
11
"His trainers clacked behind her"
12
"The tunnel to the platforms"
13
"The air grew wetter, the"
14
"Patel’s voice bounced off the"
15
"The tunnel spat them out"
16
"The tracks beside the platform"
17
"The body lay ten metres"
18
"Forensics clustered around it in"
19
"A camera flashed."
ratio
0.745
63.69%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
2
totalSentences
157
matches
0
"As if someone had set"
1
"if he’d just gone, they"
ratio
0.013
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
74
technicalSentenceCount
1
matches
0
"The needle floated free inside, then swung again as if tugged by something beneath the floor."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
12
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
2
fancyCount
2
fancyTags
0
"he murmured (murmur)"
1
"she spoke (speak)"
dialogueSentences
87
tagDensity
0.023
leniency
0.046
rawRatio
1
effectiveRatio
0.046
93.0523%