NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-25-01KJ9543NMN5A3EDZY2JK14V6P
Run Details
Model:
Gemini 2.5 Flash (Reasoning)
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
20.8s
Cost:
$0.010227
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
94.74%
Adverbs in dialogue tags
(details)
66.98%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
25.70%
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)
50.00%
Name drop frequency
(details)
68.48%
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)
89.90%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
86.67%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
51.45%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
72.07%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
25.00%
Dialogue tag variety (said vs. fancy)
(details)
81.0327%
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 rapid response vehicle shuddered
to a halt, rattling its windows in the cavernous space. Detective Harlow Quinn exited first, the heels of her practical boots
echoing
a sharp staccato against the grimy concrete.
The air, thick with the
damp-earth tang of the London Underground, held something else too: the cloying sweetness of unfamiliar incense, the sharp tang of something metallic, and an unmistakable, ancient scent, like dried blood and fear.
She cataloged it all, even
as her eyes, the colour of rich earth, swept the scene with military precision. This wasn’t a crime scene. Not
really
. Not in the way she knew. This was an unearthed secret.
The abandoned Tube station beneath
Camden sprawled before her, a forgotten cathedral of grimy tiles and rusted iron.
Floodlights, hastily erected by the
forensics team, chased away some of the encroaching
gloom
, starkly illuminating the impossible. Stalls, some still laden with bizarre goods, stood crookedly against the tunnel walls.
Jars of shimmering dust, intricate
cages holding unseen things, leathery bundles, and
wickedly
curved blades gleamed under the harsh light.
A single, overturned cart spilled
iridescent scales onto the platform. Uniformed officers moved through it all, their expressions a mix of awe and bewildered professionalism, like tourists in an alien museum. “Detective Quinn.”
Sergeant Miller, a young, earnest
man, met her halfway across the platform, a forensics mask hanging uselessly from one ear.
He scrubbed a hand over
his crew cut. “Didn’t think we’d get you out for this one.” Harlow merely raised an
eyebrow
.
Her closely cropped salt-and-pepper hair
caught the floodlight, tiny silver threads
glinting
. “Something tells me this isn’t your average mugging.” She glanced at the entrance, a gaping
maw
in the tunnel wall, where a scatter of small, bleached bone tokens lay discarded on the ground. Entry fee, she thought. To where? “No, ma’am. Definitely not.” Miller swallowed. “Victim’s just ahead. Professor Kowalski’s already had a look.”
Harlow’s sharp jaw tightened almost
imperceptibly at the mention of the name. Eva Kowalski.
The Met had brought the
'occult expert' in after Morris.
Harlow remembered her perfectly, a
nervous but brilliant young woman, thick round glasses perched on her nose, a satchel perpetually overflowing with ancient texts.
A research assistant from the
British Museum, no less. But a consultant couldn't be a colleague, not in the way Miller meant.
She was an outsider, something
Harlow never forgot even as she’d
been forced
to acknowledge the truth of Kowalski’s insights, however outlandish.
She moved with an almost
silent gait, heading towards the gathering of forensic technicians and a figure with curly red hair she knew instantly. The platform sloped towards an old service tunnel, where the crime scene tape glowed orange in the artificial light. The victim lay slumped against the arched entrance of the tunnel, a male, early forties, well-dressed, but now
utterly
still.
His eyes stared vacantly at
the grimy ceiling. No obvious signs of struggle. No bullet wounds, no stab wounds. He looked… drained. The only overt injury was a dark, bruised mark on his neck, like a handprint applied with unnatural force. Eva Kowalski looked up from where she knelt beside the body, her green eyes widening
slightly
behind her round glasses.
She wore a pristine white
forensics suit, an absurd contrast to her perpetually rumpled appearance and the worn leather satchel slung over her shoulder, even inside the protective gear.
She tucked a wayward curl
of red hair behind her left ear, a tell-tale nervous habit. “Detective Quinn,”
Eva said, her voice a little breathless
. “Good, you’re here. This is… quite something.” “So I see.” Harlow knelt, keeping a respectful distance from the body, letting her gaze sweep over every detail. The victim’s hands
were splayed
, unusually flat. Near his left hand, partially obscured by his sleeve, was a small, ornate compass.
Its brass casing showed a
green patina of verdigris, and the face
was etched
with strange,
intricate
sigils.
Its needle, however, wasn’t pointing
north.
It quivered, pointing erratically towards
the darkness of the service tunnel. Eva followed her gaze. “Ah, that. It’s an antique of some sort. The forensics team
scanned
it. Seems to be a type of… shadow compass, perhaps. Not
standard
navigation. But decorative, mostly, I’d wager.”
She paused, then added
, “Could be a trinket he purchased here. The market is known for exotic curios.” “You’re
familiar
with this market, Professor?” Harlow’s tone was
carefully
neutral. Eva ducked her head
slightly
. “Through my research, yes. The Veil Market. It’s a travelling underground network. Specialises in… esoteric goods. Legend has it it moves locations every full moon. Apparently, this abandoned station was its last stop.” “So, ‘esoteric goods’ might include whatever drained this man?” Harlow’s voice was low, cutting through the hum of generator lights. Eva shifted, her freckled complexion seeming a shade paler under the harsh lights. “The primary cause of death, according to the preliminary assessment, seems to be cardiac arrest. Possibly induced by extreme panic or some kind of rapid toxin. There’s a faint residue found on the neck, where that contusion is. Forensics are testing it, but it’s… unusual. Nothing in their
standard
database
.” Harlow touched the worn leather
watch
on her left wrist, a habitual gesture. “And the compass?” “As I said, a curio. I believe the sigils are protective in nature, common in various ancient cultures intended to ward off malign presences.” Eva’s voice was becoming more assured, falling into lecture mode. “Many belief systems hold that such symbols can influence energy fields, or even direct spiritual essence, but primarily in a passive-defensive capacity.” Harlow studied Eva. The young woman’s interpretation was so… *
academic
*.
So rational, even when discussing
the irrational. It was almost too neat.
She was presenting a story
that fit her field, but perhaps
deliberately
excluded the more unsettling, active possibilities. Harlow had seen enough after Morris’s death to know better.
She leaned closer to the
victim, ignoring Eva’s nervous cough. The handprint on the neck. It was dark, almost black, and the skin around it was unnaturally cold. But it wasn’t just a print. There were minute, almost invisible striations radiating out from the main impression, like tiny threads pulling at the skin, or
etched
into it. “And these marks, Professor?” Harlow indicated the delicate tracery with her chin.
They were barely visible, requiring
a keen eye. Forensics might miss them, or dismiss them as incidental. Eva peered closer, her forehead creasing. “Hmm. I… I hadn’t noticed those. Very faint. Suggestive of scarring, or perhaps a residual burn? Again, possibly linked to the toxin.” “Or something else entirely.” Harlow’s gaze swept the surrounding area. The crime scene tape had been set up to encompass the victim and a small radius around him. But Harlow looked beyond it, at the strange stalls, at the shadows just outside the floodlight’s reach. The floor around the body was clean, almost unnaturally so. No footprints except those of the responding officers. No struggle. No signs of anything
being dragged
. “He died here, against this wall,
precisely
where he was found,”
Eva stated, as if anticipating Harlow’s thought process
. “How do you know that, Professor?” Eva hesitated. “Well, the blood spatter analysis indicates he was in this position when the trauma occurred. It’s a clean fall backwards.” Harlow stood, turning her back to the body for a moment, letting her eyes graze the rest of the abandoned market. The floor. The concrete floor of the platform showed subtle variations in texture. Near the victim, it was
pristine
. Farther away, it was grimy, wet with an oily sheen. But then, as her eyes travelled to a section closer to the entrance, just outside the marked-off scene, she saw a darker patch. A damp, black footprint. Too big for a human. Too fluid in its edges. Animal? No, something else. And then another, faintly luminous, just beyond a discarded stall selling what
looked like skeletal remains
. No, the victim hadn't just *
fallen
*. Someone had put him there. “This market,” Harlow turned back to Eva, her brown eyes intense. “It’s a black market, you said. What do they trade in? Ancient texts? Or something… more potent?” Eva fidgeted with her glasses. “They trade in enchanted goods, banned alchemical substances, information…”
She trailed off, avoiding Harlow’s
gaze. “And what about extraction? Extraction of… essences?” Eva’s head snapped up. Her green eyes met Harlow’s, a
flicker
of something she
tried to
hide behind
academic
detachment. Alarm. Fear, perhaps. “The marks on his neck aren’t burns, Professor,” Harlow continued, her voice gaining a quiet edge, “They’re suction marks. Like something *
fed
* on him. And that compass isn't just a curio. It’s twitching. Why? Because something supernatural happened here. Something
very
unnatural. And it’s still here. That tunnel.” She pointed to the black
maw
behind the victim. The Veil Compass
quivered
again, its ancient needle now jabbing insistently towards the darkness. Eva opened her mouth, then closed it. Her usual nervous energy had coalesced into something rigid. The easy
academic
explanations had evaporated. “You said protective sigils,” Harlow pressed. “Perhaps they were meant to protect from what’s beyond that tunnel. Or from whatever crafted that compass in the first place.” She remembered the intel reports she’d
been given
on the Veil Market, from a source that had vanished shortly after. She’d dismissed most of it then. But Morris… he’d believed. He’d seen things. Unexplained circumstances. Supernatural origins. Harlow took a deep breath, the strange scents of the market filling her lungs. The metallic tang grew stronger.
Not just old blood, but fresh purpose
. She had a feeling she knew what was through that service tunnel. A rift. A portal. And whatever had drained the victim had likely retreated there. “And you, Professor,” Harlow said, her voice dropping, “Why didn’t you want us to look too closely?” She didn’t wait for an answer.
Instead, she took a powerful
flashlight from one of the forensics techs, ignoring his startled expression. She stared at the service tunnel, then back at the victim.
Then at Eva, whose eyes
were wide and unblinking behind her glasses. The compass on the ground spun violently, then settled, its needle pointing directly into the blackness. The air grew colder. “Sergeant Miller,”
Harlow called, her voice echoing
. “Secure this area. No one goes in or out. And I want a full sweep of the entire station. I want to know what’s been moving in these shadows. Every inch.” She
flicked
on the flashlight, its powerful beam cutting through the dense
gloom
of the service tunnel. The light
was swallowed
almost instantly by the
profound
darkness. But for a split second, something had glimmered at the
very
edge of the beam, something that wasn't metal or stone. Something that
looked like a pair of watching eyes
. Harlow took a step forward, towards the tunnel, her
resolve
hardening. The military precision returned to her bearing. She wouldn't let this be another Morris. Not again.
created_at
"2026-02-25T01:02:57.211Z"
2/25/2026, 1:02:57 AM
model
"google/gemini-2.5-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1204
moderation_latency
(null)
generation_time
20756
tokens_prompt
923
tokens_completion
3973
native_tokens_prompt
883
native_tokens_completion
3985
native_tokens_completion_images
0
native_tokens_reasoning
1496
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
0.0102274
router
(null)
provider_responses
0
endpoint_id
"16c01e26-9b91-4d22-b487-ed35634b017d"
is_byok
false
latency
1204
model_permaslug
"google/gemini-2.5-flash"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771981377-vh6LqWB0CFJ3wPHOPxHm"
upstream_id
(null)
total_cost
0.0102274
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
94.74%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
19
adverbTagCount
2
adverbTags
0
"She paused then [then]"
1
"Harlow turned back [back]"
dialogueSentences
32
tagDensity
0.594
leniency
1
rawRatio
0.105
effectiveRatio
0.105
66.98%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1817
totalAiIsmAdverbs
12
found
0
adverb
"really"
count
1
1
adverb
"wickedly"
count
1
2
adverb
"perfectly"
count
1
3
adverb
"utterly"
count
1
4
adverb
"slightly"
count
2
5
adverb
"carefully"
count
1
6
adverb
"deliberately"
count
1
7
adverb
"very"
count
3
8
adverb
"precisely"
count
1
highlights
0
"really"
1
"wickedly"
2
"perfectly"
3
"utterly"
4
"slightly"
5
"carefully"
6
"deliberately"
7
"very"
8
"precisely"
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)
25.70%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1817
totalAiIsms
27
found
0
word
"echoing"
count
2
1
word
"cataloged"
count
1
2
word
"gloom"
count
2
3
word
"intricate"
count
2
4
word
"eyebrow"
count
1
5
word
"glinting"
count
1
6
word
"maw"
count
2
7
word
"pristine"
count
2
8
word
"etched"
count
2
9
word
"quivered"
count
2
10
word
"scanned"
count
1
11
word
"standard"
count
2
12
word
"familiar"
count
1
13
word
"database"
count
1
14
word
"anticipating"
count
1
15
word
"flicker"
count
1
16
word
"flicked"
count
1
17
word
"profound"
count
1
18
word
"resolve"
count
1
highlights
0
"echoing"
1
"cataloged"
2
"gloom"
3
"intricate"
4
"eyebrow"
5
"glinting"
6
"maw"
7
"pristine"
8
"etched"
9
"quivered"
10
"scanned"
11
"standard"
12
"familiar"
13
"database"
14
"anticipating"
15
"flicker"
16
"flicked"
17
"profound"
18
"resolve"
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
137
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
1
narrationSentences
137
filterMatches
0
"watch"
hedgeMatches
0
"tried to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
149
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
57
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
3
markdownWords
3
totalWords
1817
ratio
0.002
matches
0
"academic"
1
"fallen"
2
"fed"
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
11
unquotedAttributions
0
matches
(empty)
50.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
64
wordCount
1365
uniqueNames
17
maxNameDensity
1.83
worstName
"Harlow"
maxWindowNameDensity
3.5
worstWindowName
"Harlow"
discoveredNames
Harlow
25
Quinn
1
London
1
Underground
1
Tube
1
Camden
1
Miller
3
Entry
1
Kowalski
3
Met
1
British
1
Museum
1
Eva
17
Morris
3
Veil
2
Compass
1
Market
1
persons
0
"Harlow"
1
"Quinn"
2
"Underground"
3
"Camden"
4
"Miller"
5
"Kowalski"
6
"Met"
7
"Eva"
8
"Morris"
9
"Compass"
10
"Market"
places
0
"London"
1
"British"
globalScore
0.584
windowScore
0.5
68.48%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
92
glossingSentenceCount
3
matches
0
"as if anticipating Harlow’s thought process"
1
"looked like skeletal remains"
2
"looked like a pair of watching eyes"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.55
wordCount
1817
matches
0
"Not just old blood, but fresh purpose"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
149
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
41
mean
44.32
std
27.51
cv
0.621
sampleLengths
0
90
1
18
2
100
3
39
4
56
5
15
6
92
7
43
8
61
9
65
10
16
11
75
12
52
13
11
14
38
15
20
16
63
17
16
18
56
19
50
20
57
21
29
22
28
23
71
24
19
25
6
26
22
27
107
28
11
29
28
30
20
31
7
32
23
33
71
34
22
35
64
36
52
37
39
38
43
39
95
40
27
89.90%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
6
totalSentences
137
matches
0
"been forced"
1
"were splayed"
2
"was etched"
3
"being dragged"
4
"been given"
5
"was swallowed"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
2
totalVerbs
213
matches
0
"wasn’t pointing"
1
"was presenting"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
149
ratio
0
matches
(empty)
86.67%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1116
adjectiveStacks
0
stackExamples
(empty)
adverbCount
61
adverbRatio
0.05465949820788531
lyAdverbCount
23
lyAdverbRatio
0.02060931899641577
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
149
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
149
mean
12.19
std
10.21
cv
0.838
sampleLengths
0
15
1
19
2
37
3
19
4
5
5
2
6
6
7
5
8
18
9
18
10
13
11
20
12
10
13
21
14
22
15
8
16
9
17
5
18
12
19
33
20
4
21
2
22
6
23
9
24
12
25
2
26
10
27
24
28
9
29
13
30
22
31
24
32
19
33
20
34
8
35
5
36
6
37
2
38
1
39
19
40
20
41
29
42
16
43
9
44
7
45
19
46
7
47
14
48
18
49
6
51.45%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
15
diversityRatio
0.3691275167785235
totalSentences
149
uniqueOpeners
55
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
5
totalSentences
116
matches
0
"So rational, even when discussing"
1
"Too big for a human."
2
"Too fluid in its edges."
3
"Instead, she took a powerful"
4
"Then at Eva, whose eyes"
ratio
0.043
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
28
totalSentences
116
matches
0
"She cataloged it all, even"
1
"He scrubbed a hand over"
2
"Her closely cropped salt-and-pepper hair"
3
"She glanced at the entrance,"
4
"She was an outsider, something"
5
"She moved with an almost"
6
"His eyes stared vacantly at"
7
"She wore a pristine white"
8
"She tucked a wayward curl"
9
"Its brass casing showed a"
10
"Its needle, however, wasn’t pointing"
11
"It quivered, pointing erratically towards"
12
"She paused, then added"
13
"It was almost too neat."
14
"She was presenting a story"
15
"She leaned closer to the"
16
"It was dark, almost black,"
17
"They were barely visible, requiring"
18
"She trailed off, avoiding Harlow’s"
19
"Her green eyes met Harlow’s,"
ratio
0.241
72.07%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
90
totalSentences
116
matches
0
"The rapid response vehicle shuddered"
1
"Detective Harlow Quinn exited first,"
2
"The air, thick with the"
3
"She cataloged it all, even"
4
"This wasn’t a crime scene."
5
"This was an unearthed secret."
6
"The abandoned Tube station beneath"
7
"Floodlights, hastily erected by the"
8
"Jars of shimmering dust, intricate"
9
"A single, overturned cart spilled"
10
"Sergeant Miller, a young, earnest"
11
"He scrubbed a hand over"
12
"Harlow merely raised an eyebrow."
13
"Her closely cropped salt-and-pepper hair"
14
"She glanced at the entrance,"
15
"Entry fee, she thought."
16
"Harlow’s sharp jaw tightened almost"
17
"The Met had brought the"
18
"Harlow remembered her perfectly, a"
19
"A research assistant from the"
ratio
0.776
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
116
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
52
technicalSentenceCount
1
matches
0
"She was presenting a story that fit her field, but perhaps deliberately excluded the more unsettling, active possibilities."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
19
uselessAdditionCount
6
matches
0
"Eva said, her voice a little breathless"
1
"Eva stated, as if anticipating Harlow’s thought process"
2
"Harlow turned back, her brown eyes intense"
3
"Harlow continued, her voice gaining a quiet edge,"
4
"Harlow said, her voice dropping,"
5
"Harlow called, her voice echoing"
25.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
7
fancyCount
4
fancyTags
0
"Eva stated (state)"
1
"Harlow continued (continue)"
2
"Harlow pressed (press)"
3
"She remembered (remember)"
dialogueSentences
32
tagDensity
0.219
leniency
0.438
rawRatio
0.571
effectiveRatio
0.25
81.0327%