NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HCD251S34VMWZY2Z2B4X84
Run Details
Model:
Qwen 3.7 Flash (Reasoning)
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
47.7s
Cost:
$0.000773
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
93.73%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
40.40%
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)
77.42%
Name drop frequency
(details)
89.02%
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)
95.31%
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)
74.19%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
89.17%
Subject-first sentence starts
(details)
41.67%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
91.67%
Useless dialogue additions
(details)
50.00%
Dialogue tag variety (said vs. fancy)
(details)
91.4191%
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 rain fell hard enough
to drum against the corroded iron grates above, but down here in the abandoned Chalk Farm spur, it was nothing but a memory soaked into the concrete.
Detective Harlow Quinn stepped over
the yellow crime scene tape and felt the
familiar
shift in her spine, shoulders drawing back, chin lifting. Eighteen years at the Met had carved her posture into steel.
Salt-and-pepper hair sat tight against
her skull, frizz
restrained
by sheer force of habit, and her sharp jaw set itself against the damp
chill
.
She tapped the worn leather
strap on her left wrist without looking down. The
watch
was cheap now, replaced years ago, but she kept wearing it out of muscle memory rather than sentiment. Three years since DS Morris. Three years since the files went quiet and the official report settled into bureaucratic static.
Forensics had finished their initial
sweep. Two uniforms stood near a derelict ticket machine, speaking in hushed, confused tones.
A body lay curled against
the metal grating, suit jacket torn, shirt dark with dried fluid. Thirty yards away, another corpse rested near a rusted turnstile, throat opened cleanly.
The rest of the team
treated it like any other street homicide, though the geometry of the deaths refused to align.
Harlow ignored the chatter and
walked the center line of the platform, boots clicking against grimy track-ballast and cracked ceramic tile. She counted steps. Twelve to the first body. Nine to the second. The spacing was deliberate. Murder was rarely spaced.
A uniform stepped forward, clipboard
already out. “Detective. We’ve got signs of a struggle near the east platform. Wallets taken, but not emptied. Laptop forced open near the western staircase. Looks like a gang territory dispute turned messy.”
Harlow stopped beside the man
against the ticket machine.
She didn’t reach for gloves
yet. Observation came before contamination. “Shoes,” she said. “Footwear?”
The officer blinked
. “The shoes. Look at the heels.” Polished. Resoled within the month. Leather soft from careful conditioning. Beneath the violence of the scene, the man wore the attire of someone who guarded his appearance.
Harlow crouched, running a penlight
across the collarbone. The defensive wounds were shallow, glancing.
He hadn’t been trying to
stop an attacker. He’d been running. Or waiting. “You’re looking for a sniper?” the officer asked. “I’m looking for a lie,” Harlow replied. She stood. Blood oxidized to brown-black in under ten minutes. The pool beneath the second victim sat wet,
gleaming
under the work lamps, but the edges had formed a pale,
crystalline
ring. No spatter. No drag marks.
Just a perfect circle of
cooling dust. “Heat source,” came a calm voice from the platform stairs. Eva Kowalski descended three steps at a time, wool scarf pulled tight against the damp, a heavy leather satchel swinging against her hip. The satchel
was overstuffed
, bulging at the seams where reference volumes and field notebooks leaked out.
Her round glasses fogged slightly
in the humid air, and she pushed them up the bridge of her nose with a knuckle dusted in chalk. Green eyes
scanned
the room with the detached focus of a historian examining
fractured
pottery.
She tucked a curl of
red hair behind her left ear, a nervous tic she couldn’t
quite suppress when the stakes shifted
. “Academic consultant,” the uniform muttered under his breath, though he stepped aside anyway. Eva ignored him, moving past Harlow to the ash-ringed corpse.
She didn’t flinch at the
damage. Years in the British Museum’s restricted archives had taught her that paper decayed slower than human patience. “Sage, yes, but mixed with ground mica and trace sulfur,” she said. “Burnt in a bronze brazier. Probably. The heat displaced the moisture, evaporated the hemoglobin, left the salts behind. Whoever killed him wanted the floor sterile. Or they wanted the room sealed off from whatever tracked scent.” Harlow watched her. “You think this was ritual.” “I think it was protocol.” Eva unzipped her satchel, bypassing the textbooks, and withdrew a small brass instrument. The casing
was weathered
, creeping with a fine patina of verdigris across the rim. The face
was etched
with interlocking protective
sigils that seemed to catch the light wrong, bending it inward rather than reflecting it outward
.
She set it on the
damp tile between them. The needle didn’t swing north.
It shuddered, then locked onto
a collapsed section of wall near the eastern staircase, where condensation wept down exposed brick. The hand
trembled
against the housing, pressing downward as if gravity had doubled. “Shadow compass,” Eva said quietly. “Crafted by a Shade artisan. Attuned to residual ley lines and thin places in the architecture. It doesn’t point to
magnetic
poles. It points to the nearest tear.” Harlow’s
pulse
ticked against her ribs. “Tear in what.” “In the world. In the veil. Whatever you call it.” Eva’s voice stayed steady, but her free hand drifted to her satchel strap, fingers worrying the stitched leather. “This isn’t a crime scene, Harlow. It’s a trading post. The Veil Market. Moves every full moon. Currently anchored in infrastructure the public forgot existed. Abandoned tubes, disused warehouses, sub-basements behind closed libraries. They sell banned alchemical compounds, archived secrets, and artifacts that don’t belong in this century. Entry requires a bone token. Signature recognition. A toll paid in something personal.” Harlow followed the compass needle to the wall. Brickwork had been recently disturbed. Mortar scraped clean. A narrow gap yawned behind a fallen support beam, wide enough for a person to slip through. The air drifting from the fissure carried a metallic tang, older than the rain, sharper than ozone. “And the dead?” “Collateral. Merchants, couriers, enforcers. People who know the routes and forget the rules.” Eva stepped closer, lowering her voice. “The marketplace doesn’t tolerate theft without consequence. If someone tried to move product without paying the toll, they get cleaned. Quietly. Efficiently. By people who understand that money changes form down here.” Harlow didn’t answer immediately. She let the
silence
stretch,
measured
the drip of water, the hum of the generator, the distant wail of sirens fading toward street level.
Her training demanded chains of
custody, photographic documentation, ballistic matching. But the evidence laid out before her resisted classification. Shoes too clean. Blood evaporated too fast. Ash arranged in geometric perfection. A compass needle pressing against reality like a thumb against a windowpane.
She walked to the eastern
staircase. Boots
echoed
too loudly in the hollow station. Behind the collapsed beam, the floor dropped away into a maintenance shaft lined with old signal boxes and coiled cable. At the bottom, half-buried in grit, lay a leather pouch stitched with gut thread. Harlow knelt. Pried it loose. Dug inside. Her fingers closed around bone. Smooth. Whitewashed. Drilled at one end, strung on braided hemp. A molar. Etched along the crown was a sequence of numerals, precise as a typewriter strike. “Receipt,” Eva murmured, appearing at her shoulder.
Her breath warmed the back
of Harlow’s neck. “Or invitation. Depends on who holds it next.” Harlow turned the tooth over. The engraving matched a pattern she’d seen buried in case files she wasn’t supposed to read. Three missing researchers from university departments. Two stolen folios from restricted municipal records. A string of encrypted messages routed through dead drops.
All pointing toward a network
operating in the blind spots of institutional oversight. A clique. Organized. Patient. Cruel in its precision. For three years, she’d chased phantoms. Morris had gone dark after following a lead into a warehouse district that showed up on satellite imagery as empty lots. No gunfire. No broken locks.
Just a single scorch mark
on concrete and a pair of boots left neatly by the door. The inquiry folded. The files sealed.
She’d been promoted to keep
her quiet. Now the quiet had teeth. “Superintendent wants an initial report by dawn,”
said a technician from the platform, voice tinny through a radio headset
. “He’s calling it gang retaliation. Pushing for arrest warrants on known associates in Southwark.” Harlow didn’t stand.
She slid the molar into
a clear evidence sleeve, sealed it, and pressed it flat against her palm. The brass compass whined faintly, needle vibrating as if struck by a tuning fork. The pull toward the shaft deepened. The air grew heavier, thick with the scent of crushed herbs and aged iron.
Somewhere beyond the crack in
the wall, a mechanism clicked. A door unlocked. Or a trap sprang. “Tell him to hold the warrants,” Harlow said, voice even, edged with the iron discipline that had kept her alive through shootouts, interrogations, and funerals. “And tell him to bring a specialist from the antiquities division. And a radiology team. We’re done with
standard
triage.” The radio crackled. Protest. Compliance. Fade. “Harlow,” Eva warned, hand resting
lightly
on Harlow’s forearm. Skin warm,
pulse
quick. “You step down that ladder, you leave the jurisdiction of the Crown. You leave the protection of the statute. What waits for you down there doesn’t care about your badge.” “Guilt doesn’t,” Harlow replied.
She rose, joints popping, spine
locking into alignment. She adjusted her
watch
. The leather cuff rubbed her wrist. “And neither do I.” She shouldered past the beam, boots finding purchase on slick stone. The compass needle held steady, pointing deeper into the dark. The tunnel exhaled cold air against her face. Shadows pooled in the corners, long and fluid, refusing to match the light sources. Harlow drew her sidearm, checked the chamber, and fed it home. Her breathing slowed. Heart rate steadied. Three years of
silence
ended in a single step forward. She descended.
created_at
"2026-09-02T15:39:33.418Z"
9/2/2026, 3:39:33 PM
model
"qwen/qwen3.7-flash-20260727"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
431
moderation_latency
(null)
generation_time
47578
tokens_prompt
896
tokens_completion
6620
native_tokens_prompt
905
native_tokens_completion
5738
native_tokens_completion_images
(null)
native_tokens_reasoning
3584
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
"stop"
service_tier
(null)
usage
0.00077309
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788363573-8wtsfqpnPwXYDyUFaXWJ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788363573-kGf246kad3DTw4LapQC2"
upstream_id
"chatcmpl-e10d5d7c-bf82-93f8-a8a0-a5c909cb9c82"
provider_responses
0
endpoint_id
"5a9a0ee6-874a-4d03-92be-e5094c0df4e7"
id
"chatcmpl-e10d5d7c-bf82-93f8-a8a0-a5c909cb9c82"
is_byok
false
latency
430
model_permaslug
"qwen/qwen3.7-flash-20260727"
provider_name
"Alibaba"
status
200
total_cost
0.00077309
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
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
15
adverbTagCount
1
adverbTags
0
"Eva said quietly [quietly]"
dialogueSentences
30
tagDensity
0.5
leniency
1
rawRatio
0.067
effectiveRatio
0.067
93.73%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1594
totalAiIsmAdverbs
2
found
0
adverb
"slightly"
count
1
1
adverb
"lightly"
count
1
highlights
0
"slightly"
1
"lightly"
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)
40.40%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1594
totalAiIsms
19
found
0
word
"familiar"
count
1
1
word
"restrained"
count
1
2
word
"chill"
count
1
3
word
"gleaming"
count
1
4
word
"crystalline"
count
1
5
word
"perfect"
count
1
6
word
"scanned"
count
1
7
word
"fractured"
count
1
8
word
"etched"
count
2
9
word
"trembled"
count
1
10
word
"magnetic"
count
1
11
word
"pulse"
count
2
12
word
"silence"
count
2
13
word
"measured"
count
1
14
word
"echoed"
count
1
15
word
"standard"
count
1
highlights
0
"familiar"
1
"restrained"
2
"chill"
3
"gleaming"
4
"crystalline"
5
"perfect"
6
"scanned"
7
"fractured"
8
"etched"
9
"trembled"
10
"magnetic"
11
"pulse"
12
"silence"
13
"measured"
14
"echoed"
15
"standard"
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
141
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
1
narrationSentences
141
filterMatches
0
"watch"
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
155
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
61
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1594
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
12
unquotedAttributions
0
matches
(empty)
77.42%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
41
wordCount
1240
uniqueNames
13
maxNameDensity
1.45
worstName
"Harlow"
maxWindowNameDensity
2.5
worstWindowName
"Harlow"
discoveredNames
Chalk
1
Farm
1
Harlow
18
Quinn
1
Met
1
Morris
2
Polished
1
Eva
8
Kowalski
1
British
1
Museum
1
Skin
1
Three
4
persons
0
"Harlow"
1
"Quinn"
2
"Morris"
3
"Eva"
4
"Kowalski"
5
"Museum"
places
0
"Chalk"
1
"Farm"
2
"British"
globalScore
0.774
windowScore
0.833
89.02%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
82
glossingSentenceCount
2
matches
0
"quite suppress when the stakes shifted"
1
"sigils that seemed to catch the light wrong, bending it inward rather than reflecting it outward"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1594
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
155
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
36
mean
44.28
std
33.31
cv
0.752
sampleLengths
0
143
1
110
2
38
3
22
4
4
5
6
6
54
7
8
8
51
9
10
10
101
11
13
12
81
13
8
14
64
15
38
16
33
17
9
18
89
19
53
20
51
21
71
22
55
23
31
24
23
25
64
26
62
27
5
28
33
29
72
30
45
31
6
32
43
33
26
34
70
35
2
95.31%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
4
totalSentences
141
matches
0
"was overstuffed"
1
"was weathered"
2
"was etched"
3
"been promoted"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
214
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
155
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1246
adjectiveStacks
0
stackExamples
(empty)
adverbCount
33
adverbRatio
0.026484751203852328
lyAdverbCount
10
lyAdverbRatio
0.008025682182985553
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
155
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
155
mean
10.28
std
8.86
cv
0.861
sampleLengths
0
32
1
23
2
11
3
24
4
13
5
20
6
5
7
15
8
6
9
13
10
16
11
13
12
21
13
21
14
3
15
5
16
4
17
4
18
4
19
7
20
31
21
9
22
6
23
4
24
3
25
4
26
6
27
1
28
4
29
5
30
17
31
8
32
6
33
8
34
3
35
2
36
8
37
7
38
2
39
8
40
22
41
2
42
3
43
7
44
10
45
23
46
16
47
25
48
15
49
22
74.19%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
10
diversityRatio
0.4838709677419355
totalSentences
155
uniqueOpeners
75
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
4
totalSentences
120
matches
0
"Just a perfect circle of"
1
"All pointing toward a network"
2
"Just a single scorch mark"
3
"Somewhere beyond the crack in"
ratio
0.033
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
21
totalSentences
120
matches
0
"She tapped the worn leather"
1
"She counted steps."
2
"She didn’t reach for gloves"
3
"He hadn’t been trying to"
4
"He’d been running."
5
"Her round glasses fogged slightly"
6
"She tucked a curl of"
7
"She didn’t flinch at the"
8
"She set it on the"
9
"It shuddered, then locked onto"
10
"She let the silence stretch,"
11
"Her training demanded chains of"
12
"She walked to the eastern"
13
"Her fingers closed around bone."
14
"Her breath warmed the back"
15
"She’d been promoted to keep"
16
"She slid the molar into"
17
"She rose, joints popping, spine"
18
"She adjusted her watch."
19
"She shouldered past the beam,"
ratio
0.175
89.17%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
89
totalSentences
120
matches
0
"The rain fell hard enough"
1
"Detective Harlow Quinn stepped over"
2
"Salt-and-pepper hair sat tight against"
3
"She tapped the worn leather"
4
"The watch was cheap now,"
5
"Forensics had finished their initial"
6
"A body lay curled against"
7
"The rest of the team"
8
"Harlow ignored the chatter and"
9
"She counted steps."
10
"The spacing was deliberate."
11
"Murder was rarely spaced."
12
"A uniform stepped forward, clipboard"
13
"Harlow stopped beside the man"
14
"She didn’t reach for gloves"
15
"Observation came before contamination."
16
"The officer blinked"
17
"Leather soft from careful conditioning."
18
"Harlow crouched, running a penlight"
19
"The defensive wounds were shallow,"
ratio
0.742
41.67%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
120
matches
0
"Now the quiet had teeth."
ratio
0.008
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
46
technicalSentenceCount
2
matches
0
"The face was etched with interlocking protective sigils that seemed to catch the light wrong, bending it inward rather than reflecting it outward."
1
"Morris had gone dark after following a lead into a warehouse district that showed up on satellite imagery as empty lots."
91.67%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
15
uselessAdditionCount
1
matches
0
"said a technician from the platform, voice tinny through a radio headset"
50.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
11
fancyCount
3
fancyTags
0
"the uniform muttered (mutter)"
1
"Eva murmured (murmur)"
2
"Eva warned (warn)"
dialogueSentences
30
tagDensity
0.367
leniency
0.733
rawRatio
0.273
effectiveRatio
0.2
91.4191%