NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-17-01KHMQX1GM9M8H8A4XFCF8X3HP
Run Details
Model:
Z.AI GLM 4.7
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
1m 25s
Cost:
$0.013669
Provider:
Venice
Evaluation summary
Score
Evaluator
Details Link
73.02%
Adverbs in dialogue tags
(details)
76.35%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
55.65%
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)
33.33%
Name drop frequency
(details)
57.41%
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)
93.37%
Passive voice overuse
(details)
4.88%
Past progressive (was/were + -ing) overuse
(details)
29.33%
Em-dash & semicolon overuse
(details)
100.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
46.76%
Sentence opener variety
(details)
95.24%
Adverb-first sentence starts
(details)
79.05%
Pronoun-first sentence starts
(details)
12.38%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
65.22%
Technical jargon density
(details)
41.67%
Useless dialogue additions
(details)
7.14%
Dialogue tag variety (said vs. fancy)
(details)
72.3592%
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 air beneath Camden was
heavy, smelling of wet soot, river mud, and the metallic tang of the Thames that seeped up
through
the old brickwork.
Detective Harlow Quinn adjusted the
cuffs of her coat, the leather of her watchband cool against her wrist as she checked the time. 02:14. Late enough for the city to quiet, early enough that the underground things felt safe to come out.
She ducked under the yellow
police tape, the fluorescence of the crime scene lights bouncing off the curved, soot-stained tiles of the abandoned Tube station.
It was a place the
London Underground maps had forgotten decades ago, a dead end swallowed by urban decay. "Detective Quinn,"
a voice called out
.
She didn't need to turn
to know it was DC Renner.
He was young, eager, and
currently standing next to a body that looked like it had
been discarded
with the trash. "Report, Renner," she said, her voice clipped, carrying the military precision that had defined her eighteen years on the force. "Male, Caucasian, mid-thirties,"
Renner said, stepping back to
give her room. "No wallet, no ID. Looks like an OD, or maybe a mugging gone wrong. We’ve got needle marks on his arm, but... the puncture wounds are weird. Dark. Like they were burned." Quinn crouched beside the corpse.
The man was lying on
his back, arms splayed
as if welcoming the darkness
.
He wore a tailored wool
coat, expensive but ruined by the grime of the tunnel floor.
She leaned in, her sharp
jawline set tight as she examined the marks.
Renner was right; they weren't
fresh injection sites.
They were necrotic, the edges
blackened as if cauterized by a chemical she couldn't identify. "ODs don't usually burn, Renner," she murmured. "And junkies don't wear cashmere coats to squat in abandoned tunnels." "Stolen property?"
Renner suggested, though his tone
lacked conviction. "Maybe." "Harlow."
The soft, hesitant voice came
from the shadows near the tunnel wall.
Quinn stood up, turning to
see a small figure clutching a worn leather satchel.
Eva Kowalski stepped into the
light of the portable work lamps.
Her curly red hair was
a
chaotic
halo around her pale face, and her round glasses slipped down her nose as she tucked a strand of hair
nervously
behind her left ear. "I didn't authorize a civilian consultant, Renner,"
Quinn said, though her tone wasn't harsh
.
She and Eva went back
too far for that. "I called her," Renner said
quickly
. "Look at the walls, Detective. You need to see what she sees." Quinn walked over to her friend. Eva looked out of place here—too academic, too fragile for the grit of a homicide scene—but the green eyes behind the lenses were focused and sharp. "What are you doing here, Evie?" "Look at the residue on the tiles," Eva whispered, pointing a trembling finger at the brickwork just inches from the victim's head. "It's not mold. It’s salt. Mixed with... ash and iron filings. A binding circle, or the remnants of one." Quinn looked. The dark smudges on the brick were subtle, easily mistaken for decay, but there was a geometric precision to the scattering that pricked at Quinn’s instinct for order. "A gang sign?" "A protection sigil,"
Eva corrected, her voice gaining strength
. "The layout of this station... it matches the descriptions in the restricted archives. This isn't just a tunnel, Harlow. It’s a locus point. The Veil Market moves, but it leaves traces." "The Veil Market," Quinn repeated. The term was
familiar
from old case files, the ones that had gotten her partner, DS Morris, killed. The files she wasn't supposed to read but did anyway. "The underground black market for the... unexplainable." "It moves every full moon," Eva said, opening her satchel to pull out a notebook. "But the energy lingers. This man wasn't just killed. He was harvested." Renner shifted his
weight
, looking uncomfortable. "With all due respect, Miss Kowalski, this looks like a drug deal. Ritual killings are messy. This is... clean. Too clean." Quinn held up a hand to
silence
him.
She turned back to the
body. Something about the scene gnawed at her. The logic of a mugging didn't fit the victim's posture. The logic of a ritual killing didn't fit the lack of mess.
She knelt again, this time
focusing on the victim's right hand. The fingers
were curled
tight, the knuckles white even in death. " rigor mortis hasn't set in
completely
," she noted. "He died recently."
She reached into her pocket
and snapped on a latex glove.
Gently, she pried the fingers
open. The resistance was stiff, but the hand popped open. Resting in the dead man's palm was an object that gleamed dull green in the harsh light. "What is that?" Renner leaned in. Quinn picked it up.
It was heavy, a small
brass compass with a thick patina of verdigris coating its casing.
It looked ancient, the kind
of thing you’d find in a museum case rather than a corpse's hand. She turned it over. The face
was etched
with strange, angular markings—sigils, Eva had called them. They weren't numerals.
They looked like mathematical formulas
drawn by a madman. "The needle isn't moving," Quinn said.
She rotated the compass in
her hand. The needle remained locked, pointing not north, but directly at the solid brick wall of the tunnel behind the body. "It’s a Veil Compass," Eva breathed, stepping closer. "I've read about these. Crafted by Shade artisans. They don't point north. They point toward the nearest supernatural rift." "It points at a wall," Quinn said flatly. "Exactly," Eva replied. Quinn stared at the compass. The needle was steady,
unwavering
.
It wasn't malfunctioning; it was
reacting to something she couldn't see. She looked at the wall. Old London brick, patched with concrete, damp with condensation. She walked over to the wall. The compass needle swung
slightly
as she moved, tracking her position relative to the
structure
. It
wasn't just pointing
at the surface; it
was pointing
*
through
* it. "Renner, give me the UV light," Quinn commanded. The young detective frowned but unclipped the black light from his belt. Quinn clicked it on, bathing the section of brick in purple fluorescence. At first, nothing.
Just wet mortar and crumbling
brick.
Then, Quinn swept the light
closer to the floor. There, scrawled in a substance that fluoresced a violent, sickly violet, was a symbol. It matched the
etching
on the compass casing. "The salt wasn't a circle,"
Quinn said, her mind racing to connect the dots
. "It was a barrier. To keep something in, or keep something out." Eva nodded vigorously. "The Market requires payment. Not just money. Bone, blood, memories. The token..." "Bone token," Quinn murmured. She looked back at the victim's neck. There was a small, jagged tear in the skin just above the collarbone. Not a knife wound. A bite mark. Or a tear. She held up the compass again. "This man had a key. The compass. He tried to open the market, or maybe he was running from it." Renner scoffed. "You're telling me a magic compass led this guy to a magic door in a wall, and he died of fright?" "I'm saying the evidence doesn't support your drug theory,"
Quinn countered, her voice hardening
. "No needle tracks that burn like that. No defensive wounds. He died with the compass in his hand, facing the wall. He wasn't running away. He was waiting." She looked at the ground beneath the victim. She moved the flashlight beam closer, sweeping the dirt. "Renner, look at the dust." "What dust?" "Exactly," Quinn said. "There is none." She pointed to the victim’s shoes, then to the surrounding floor. The entire tunnel
was coated
in a thick layer of gray dust and grit, disturbed by their
footsteps
. But the area immediately surrounding the body— a
perfect
circle three feet in diameter—was
pristine
. The tiles were visible, clean, as if the dust had been... repelled. "Static electricity?" Renner offered weakly. "Magnetic repulsion," Quinn corrected, though she knew that wasn't right either. "The air here feels different. Heavier." "It’s the pressure," Eva said
softly
. "When the Veil thins, the atmospheric pressure drops. It plays havoc with the inner ear." Quinn stepped into the clean circle. She felt a sudden, sharp
pang
of nausea, a pressure behind her eyes that mimicked the onset of a migraine. She ignored it, crouching one last time. She looked at the compass in her hand. The needle
was spinning
now, wild and erratic, reacting to her proximity to whatever anomaly lay beyond the brick. "This isn't a crime scene in the traditional sense," Quinn said, standing up and slipping the compass into an evidence bag. "We’re looking at the
aftermath
of a transaction gone wrong." She looked at Renner. "Bag the body. Full toxicology, but tell the lab to look for unknown chemical compounds. Not just drugs." "And the wall?" "We cordon it off. Nobody touches this section of brick." She turned to Eva. "You said this market moves?" "Yes. Every full moon. It's a mobile bazaar. If this was an entrance, it's sealed now." "Good," Quinn said, slipping the evidence bag into her pocket. She looked at the dead man one last time, the face frozen in a look of ecstatic terror. She thought of Morris, of the file on her desk, of the things the Metropolitan Police refused to acknowledge. "Harlow," Eva said, touching her arm
gently
. "Be careful. The Market doesn't like thieves." Quinn checked her
watch
again. 02:19. "I'm not a thief, Evie. I'm a detective. And this case just went from a suspicious death to an active investigation into unregistered importation." She started walking back toward the tunnel exit, the compass heavy in her pocket. "Renner, get the vic to the morgue. And call me the moment the lab screams about unknown compounds." "You
really
think there's a door behind that brick?" Renner asked, sounding spooked. Quinn paused at the top of the stairs, looking back into the dark. "I think the compass points there. And in this job, you follow the evidence, even when it points at a wall."
created_at
"2026-02-17T02:48:30.786107+00:00"
2/17/2026, 2:48:30 AM
model
"z-ai/glm-4.7-20251222"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
556
moderation_latency
(null)
generation_time
84907
tokens_prompt
923
tokens_completion
5484
native_tokens_prompt
814
native_tokens_completion
4989
native_tokens_completion_images
(null)
native_tokens_reasoning
2887
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
"stop"
usage
0.01366855
router
(null)
provider_responses
0
id
"chatcmpl-RInIq3EuigTXrYK3DSmHt62T"
status
200
is_byok
false
latency
556
endpoint_id
"f99f5dca-50a5-4169-a758-60b2cd09d599"
provider_name
"Venice"
model_permaslug
"z-ai/glm-4.7-20251222"
api_type
"completions"
id
"gen-1771296425-BbPr74hnrsOhlUgJzL6L"
upstream_id
"chatcmpl-RInIq3EuigTXrYK3DSmHt62T"
total_cost
0.01366855
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Venice"
Evaluation details
Result
Evaluator
Details
Meta Data
73.02%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
30
adverbTagCount
4
adverbTags
0
"Renner said quickly [quickly]"
1
"Quinn said flatly [flatly]"
2
"Renner offered weakly [weakly]"
3
"Eva said softly [softly]"
dialogueSentences
63
tagDensity
0.476
leniency
0.952
rawRatio
0.133
effectiveRatio
0.127
76.35%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1691
totalAiIsmAdverbs
8
found
0
adverb
"nervously"
count
1
1
adverb
"quickly"
count
1
2
adverb
"completely"
count
1
3
adverb
"gently"
count
2
4
adverb
"slightly"
count
1
5
adverb
"softly"
count
1
6
adverb
"really"
count
1
highlights
0
"nervously"
1
"quickly"
2
"completely"
3
"gently"
4
"slightly"
5
"softly"
6
"really"
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)
55.65%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1691
totalAiIsms
15
found
0
word
"chaotic"
count
1
1
word
"familiar"
count
1
2
word
"weight"
count
1
3
word
"silence"
count
1
4
word
"etched"
count
1
5
word
"unwavering"
count
1
6
word
"structure"
count
1
7
word
"etching"
count
1
8
word
"racing"
count
1
9
word
"footsteps"
count
1
10
word
"perfect"
count
1
11
word
"pristine"
count
1
12
word
"magnetic"
count
1
13
word
"pang"
count
1
14
word
"aftermath"
count
1
highlights
0
"chaotic"
1
"familiar"
2
"weight"
3
"silence"
4
"etched"
5
"unwavering"
6
"structure"
7
"etching"
8
"racing"
9
"footsteps"
10
"perfect"
11
"pristine"
12
"magnetic"
13
"pang"
14
"aftermath"
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
118
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
0
narrationSentences
118
filterMatches
0
"watch"
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
151
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
32
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
1
markdownWords
1
totalWords
1688
ratio
0.001
matches
0
"through"
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
26
unquotedAttributions
0
matches
(empty)
33.33%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
62
wordCount
1138
uniqueNames
13
maxNameDensity
2.28
worstName
"Quinn"
maxWindowNameDensity
4
worstWindowName
"Quinn"
discoveredNames
Camden
1
Thames
1
Harlow
1
Quinn
26
Tube
1
London
2
Underground
1
Renner
11
Kowalski
1
Eva
13
Morris
2
Metropolitan
1
Police
1
persons
0
"Harlow"
1
"Quinn"
2
"Underground"
3
"Renner"
4
"Kowalski"
5
"Eva"
6
"Morris"
7
"Police"
places
0
"Thames"
1
"London"
globalScore
0.358
windowScore
0.333
57.41%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
81
glossingSentenceCount
3
matches
0
"looked like it had been discarded with th"
1
"as if welcoming the darkness"
2
"looked like mathematical formulas drawn b"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.592
wordCount
1688
matches
0
"not north, but directly at the solid brick wall of the tunnel behind the bo"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
151
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
65
mean
25.97
std
16.67
cv
0.642
sampleLengths
0
68
1
44
2
6
3
32
4
20
5
43
6
71
7
18
8
9
9
1
10
1
11
69
12
23
13
18
14
32
15
6
16
41
17
33
18
40
19
40
20
27
21
27
22
43
23
34
24
26
25
17
26
6
27
38
28
28
29
33
30
27
31
8
32
3
33
35
34
33
35
8
36
24
37
18
38
22
39
26
40
15
41
34
42
26
43
23
44
42
45
17
46
5
47
2
48
6
49
56
93.37%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
4
totalSentences
118
matches
0
"been discarded"
1
"were curled"
2
"was etched"
3
"was coated"
4.88%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
6
totalVerbs
205
matches
0
"was lying"
1
"was reacting"
2
"wasn't malfunctioning"
3
"was pointing"
4
"wasn't just pointing"
5
"was spinning"
29.33%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
5
semicolonCount
3
flaggedSentences
6
totalSentences
151
ratio
0.04
matches
0
"Renner was right; they weren't fresh injection sites."
1
"Eva looked out of place here—too academic, too fragile for the grit of a homicide scene—but the green eyes behind the lenses were focused and sharp."
2
"The face was etched with strange, angular markings—sigils, Eva had called them."
3
"It wasn't malfunctioning; it was reacting to something she couldn't see."
4
"It wasn't just pointing at the surface; it was pointing *through* it."
5
"But the area immediately surrounding the body— a perfect circle three feet in diameter—was pristine."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1143
adjectiveStacks
0
stackExamples
(empty)
adverbCount
36
adverbRatio
0.031496062992125984
lyAdverbCount
17
lyAdverbRatio
0.014873140857392825
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
151
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
151
mean
11.18
std
6.97
cv
0.624
sampleLengths
0
26
1
23
2
1
3
18
4
25
5
19
6
6
7
11
8
21
9
20
10
11
11
32
12
5
13
14
14
16
15
13
16
8
17
15
18
7
19
11
20
9
21
1
22
1
23
12
24
14
25
11
26
32
27
14
28
9
29
6
30
12
31
6
32
26
33
6
34
22
35
19
36
2
37
28
38
3
39
9
40
31
41
5
42
18
43
10
44
7
45
15
46
12
47
6
48
21
49
8
46.76%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
12
diversityRatio
0.3288590604026846
totalSentences
149
uniqueOpeners
49
95.24%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
3
totalSentences
105
matches
0
"Gently, she pried the fingers"
1
"Just wet mortar and crumbling"
2
"Then, Quinn swept the light"
ratio
0.029
79.05%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
37
totalSentences
105
matches
0
"She ducked under the yellow"
1
"It was a place the"
2
"She didn't need to turn"
3
"He was young, eager, and"
4
"she said, her voice clipped,"
5
"He wore a tailored wool"
6
"She leaned in, her sharp"
7
"They were necrotic, the edges"
8
"Her curly red hair was"
9
"She and Eva went back"
10
"She turned back to the"
11
"She knelt again, this time"
12
"She reached into her pocket"
13
"It was heavy, a small"
14
"It looked ancient, the kind"
15
"She turned it over."
16
"They weren't numerals."
17
"They looked like mathematical formulas"
18
"She rotated the compass in"
19
"It wasn't malfunctioning; it was"
ratio
0.352
12.38%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
94
totalSentences
105
matches
0
"The air beneath Camden was"
1
"Detective Harlow Quinn adjusted the"
2
"She ducked under the yellow"
3
"It was a place the"
4
"a voice called out"
5
"She didn't need to turn"
6
"He was young, eager, and"
7
"she said, her voice clipped,"
8
"Renner said, stepping back to"
9
"Quinn crouched beside the corpse."
10
"The man was lying on"
11
"He wore a tailored wool"
12
"She leaned in, her sharp"
13
"Renner was right; they weren't"
14
"They were necrotic, the edges"
15
"Renner suggested, though his tone"
16
"The soft, hesitant voice came"
17
"Quinn stood up, turning to"
18
"Eva Kowalski stepped into the"
19
"Her curly red hair was"
ratio
0.895
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
105
matches
(empty)
ratio
0
65.22%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
46
technicalSentenceCount
5
matches
0
"The air beneath Camden was heavy, smelling of wet soot, river mud, and the metallic tang of the Thames that seeped up through the old brickwork."
1
"He was young, eager, and currently standing next to a body that looked like it had been discarded with the trash."
2
"They were necrotic, the edges blackened as if cauterized by a chemical she couldn't identify."
3
"The term was familiar from old case files, the ones that had gotten her partner, DS Morris, killed."
4
"Resting in the dead man's palm was an object that gleamed dull green in the harsh light."
41.67%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
30
uselessAdditionCount
5
matches
0
"Renner suggested, though his tone lacked conviction"
1
"Quinn said, though her tone wasn't harsh"
2
"Eva corrected, her voice gaining strength"
3
"Quinn said, her mind racing to connect the dots"
4
"Quinn countered, her voice hardening"
7.14%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
24
fancyCount
9
fancyTags
0
"she murmured (murmur)"
1
"Renner suggested (suggest)"
2
"Eva whispered (whisper)"
3
"Eva corrected (correct)"
4
"Quinn repeated (repeat)"
5
"she noted (note)"
6
"Eva breathed (breathe)"
7
"Quinn murmured (murmur)"
8
"Quinn corrected (correct)"
dialogueSentences
63
tagDensity
0.381
leniency
0.762
rawRatio
0.375
effectiveRatio
0.286
72.3592%