NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-17-01KHMPB71J4NJNKJ847TY2YGSA
Run Details
Model:
Mistral NeMO
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
30.4s
Cost:
$0.000468
Evaluation summary
Score
Evaluator
Details Link
0.00%
Adverbs in dialogue tags
(details)
97.24%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
3.26%
AI-ism word frequency
(details)
100.00%
Cliché density
(details)
100.00%
Emotion telling (show vs. tell)
(details)
87.49%
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)
100.00%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
48.50%
Paragraph length variance
(details)
88.94%
Passive voice overuse
(details)
42.34%
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)
30.88%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
24.65%
Pronoun-first sentence starts
(details)
84.03%
Subject-first sentence starts
(details)
100.00%
Subordinate conjunction sentence starts
(details)
65.40%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
77.4248%
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="4417" name="Tomás Herrera" aliases="Tommy, Tomás, Herrera" pronouns="he/him" species="Human" storyRole="Support"> <eyeColor>warm brown</eyeColor> <hair>short curly dark brown</hair> <height>5'10"</height> <age>29</age> <skinTone>olive skin</skinTone> <scar>scar running along his left forearm from a knife attack</scar> <medallion>Saint Christopher medallion around his neck</medallion> <birthplace>Seville, Spain</birthplace> <description>A former paramedic who provides off-the-books medical care for the clique.</description> <backstory>Born in Seville, Spain. He moved to London to work for the NHS but lost his license after administering unauthorized treatments to supernatural patients.</backstory> </character> <location id="854" name="The Raven's Nest" aliases="the Nest, Raven, Silas' bar" realm="Earth"> <signColor>distinctive green neon sign above the entrance</signColor> <secretRoom>hidden back room accessible through a bookshelf, used for clandestine meetings</secretRoom> <description>A dimly lit bar in Soho, London. The walls are covered with old maps and black-and-white photographs.</description> </location> <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> </codex> Write a fully fleshed out scene of at least 1000 words in the thriller genre. A detective is pursuing a suspect through rain-soaked city streets at night. The chase takes them from the street level down into an underground market. The detective must decide whether to follow the suspect into unfamiliar and potentially dangerous territory. 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 was a relentless
drumbeat against Detective Harlow Quinn's trench coat, each drop a tiny, cold fist
pounding
at her shoulders.
The city lights reflected off
the slick cobblestones, turning London's streets into a labyrinth of wet, shimmering mirrors.
She'd been tracking Tomás Herrera
for hours, the former paramedic's olive skin and dark hair blending with the night, making him a slippery target. But Quinn was a hunter, and she never lost her prey.
Her breath misted in the
chill
air as she rounded a corner, her worn leather
watch
glinting
under the streetlamp.
The sharp pain in her
side was a
familiar
companion, a
reminder
of the years she'd spent chasing shadows like this one.
She'd lost count of how
many times she'd chased suspects through these streets, but she'd never lost one yet. Herrera darted into an alley, his shoes splashing in the puddles.
Quinn followed, her heart pounding
in her chest.
The alley was narrow, the
buildings on either side
looming
like monoliths, their windows dark and empty.
She could hear Herrera's ragged
breath up ahead,
see
the faint glow of his cigarette lighter as he paused to catch his breath.
Quinn slowed, her hand resting
on the grip of her service revolver.
She'd been after Herrera for
weeks, ever since she'd found evidence linking him to the clique, a secret society she suspected
was involved
in criminal activity. But Herrera wasn't just a suspect; he was a key, a door to a world she'd only glimpsed at the edges of her vision.
A world of shadows and
secrets, of things that went bump in the night.
She rounded the corner, her
eyes
scanning
the darkness.
Herrera was gone, but there
was a faint glow coming from a grate in the ground.
Quinn approached, her boots echoing
in the
silence
. The grate was old, rusted, but it
was unlocked
.
She could hear voices coming
from below, muffled and indistinct.
Quinn hesitated, her hand still
on her gun. She'd followed Herrera this far, but going down there was a different story.
She was a cop, not
a spy, and she'd never set foot in a place like this before. But she was close now, closer than she'd ever been to understanding what had
happened to
her partner, DS Morris, three years ago. Closer to finding out why he'd died under circumstances that defied explanation. She took a deep breath, the scent of damp earth and something else, something acrid and unfamiliar, filling her nostrils. Then she holstered her gun, grabbed the edge of the grate, and pulled herself down into the darkness. The tunnel was narrow, the ceiling low, forcing Quinn to duck her head as she made her way forward. The voices were louder now,
echoing
off the walls, a
cacophony
of languages and accents.
She could see a faint
light up ahead, hear the murmur of a crowd.
She stepped out into a
cavernous space, her eyes widening in disbelief.
She was in an abandoned
Tube station, but it was like no station she'd ever seen. The walls
were lined
with stalls, their tables groaning under the
weight
of strange,
otherworldly
objects. There were people everywhere, their faces a blur of colors and shapes, their eyes
gleaming
in the dim light. Quinn hesitated, her hand instinctively going to her gun. But she didn't draw it, not yet.
She was out of her
depth here, she knew that, but she also
knew that she
was close. Close to Herrera, close to the truth.
She pushed her way through
the crowd, her eyes
scanning
the stalls. There were potions and powders, crystals and charms, things that defied explanation and understanding.
She saw a woman with
scales instead of skin, a man with antlers growing from his forehead.
She saw creatures that looked
like spiders, like snakes, like nothing she'd ever seen before. And then she saw Herrera, standing at a stall at the far end of the market.
He was talking to a
man with a face like a raven, his eyes
gleaming
black and beady. Quinn hesitated, her heart
pounding
in her chest. She could arrest Herrera now, take him in for questioning. But she'd lose this, lose the chance to understand what
was really going
on here. She took a deep breath, her eyes
scanning
the market. She needed a disguise, something to blend in with the crowd. She spotted a stall selling clothes, robes and cloaks and hats in every color of the rainbow. She grabbed a cloak, a hooded thing in deep purple, and pulled it on over her trench coat. She pulled the hood up, hiding her face in the shadows, and made her way towards Herrera. The man with the raven face
was talking
now, his voice a harsh, grating sound that made Quinn's skin crawl. She couldn't hear what he
was saying
,
not over the din of the market, but she could see Herrera's face, see the way he was listening
, his eyes wide and intent. Quinn hesitated, her hand going to her gun. She could arrest them both now, take them in for questioning. But she didn't. She stood there, in the shadows, and she watched. The man with the raven face reached into his pocket and pulled out a small, stoppered bottle. He handed it to Herrera, who took it with a nod.
Then he turned and walked
away, disappearing into the crowd. Quinn hesitated, her heart
pounding
in her chest. She could follow Herrera,
see
where he went, what he did with the bottle. Or she could follow the raven-faced man, find out who he was, where he came from. She took a deep breath, her eyes
scanning
the market. Then she made her choice. She followed the raven-faced man. He led her through the market, past stalls selling things she couldn't even
begin to
understand. She saw a stall selling what
looked like human teeth, another selling
what the sign claimed were dragon scales.
She saw a woman with
wings, her feathers shimmering in the dim light, and a man with hooves instead of feet. The raven-faced man led her to a door at the back of the market, a door that
was guarded
by two men with guns. They nodded as he approached, their eyes
scanning
the crowd. Quinn hung back, her heart
pounding
in her chest. She could
see
Herrera now, standing at the edge of the market, the bottle clutched in his hand. She hesitated, her hand going to her gun. She could arrest him now, take him in for questioning. But she didn't. She stood there, in the shadows, and she watched. The raven-faced man disappeared through the door, the guards closing it behind him. Quinn waited a moment, then made her way towards Herrera. He
was still standing
there, the bottle clutched in his hand, his eyes
scanning
the market. Quinn approached him, her hand going to her gun. "Herrera,"
she said, her voice low and dangerous
. "You're under arrest." Herrera turned to face her, his eyes widening in surprise. Then he smiled, a slow, dangerous smile that made Quinn's blood run cold. "Detective Quinn,"
he said, his voice a low purr
. "I've been expecting you." Quinn hesitated, her hand tightening on her gun. "You have the right to remain silent,"
she said, her voice steady and calm
. "Anything you say can and will be used against you in a court of law. You have the right to an attorney. If you cannot afford an attorney, one will be appointed for you. Do you understand these rights as I have read them to you?" Herrera laughed, a harsh, grating sound that made Quinn's skin crawl. "You don't understand, Detective,"
he said, his eyes gleaming in the dim light
. "You don't understand at all." Quinn hesitated, her heart
pounding
in her chest.
Then she reached out, her
hand closing around Herrera's arm. "You're under arrest,"
she said again, her voice steady and calm
. "Come with me." Herrera didn't resist as she led him away, through the market and back up the tunnel. He walked beside her, his head held high, his eyes
scanning
the crowd. Quinn
could feel
the
tension
in his arm, the way he
was coiled
, ready to spring. She led him out into the alley, the rain still
pounding
against the cobblestones. She could
see
the patrol car waiting at the end of the alley, its lights flashing in the darkness. She could
see
the uniforms, their hands on their guns, their eyes watching her, waiting for her signal. She turned to Herrera, her hand still on his arm. "You have the right to remain silent,"
she said again, her voice steady and calm
. "Anything you say can and will be used against you in a court of law. You have the right to an attorney. If you cannot afford an attorney, one will be appointed for you. Do you understand these rights as I have read them to you?" Herrera smiled, a slow, dangerous smile that made Quinn's blood run cold. "I understand, Detective,"
he said, his voice a low purr
. "But you still don't understand. You still don't understand at all." Quinn hesitated, her heart
pounding
in her chest.
Then she turned and led
Herrera towards the patrol car, her mind
racing
, her thoughts a whirlwind of questions and doubts and fears. She didn't understand, not yet. But she would. She would understand, no matter what it took.
No matter where it led
her.
No matter what she had
to do. She opened the door of the patrol car, her hand still on Herrera's arm. She could
see
the uniforms watching her, their eyes filled with questions, with concern. She could
see
the worry in their eyes, the way they
were looking
at her, at Herrera, at the world that had led them here. She pushed Herrera into the backseat, her hand on his head as he ducked to get in. Then she closed the door, her heart
pounding
in her chest. She stood there for a moment, her eyes
scanning
the alley, the city, the world.
Then she turned and walked
away, her mind
racing
, her thoughts a whirlwind of questions and doubts and fears. She didn't know what was going to happen next. She didn't know where this was going to lead her, what she was going to find, what she was going to have to do. But she knew one thing for sure. She was going to find out the truth. No matter what it took.
No matter where it led
her.
No matter what she had
to do. She was going to find out the truth. And she was going to bring them to justice. No matter what it took. No matter what it cost.
No matter what she had
to do.
total_cost
0.00046829999999999994
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
7
adverbTagCount
2
adverbTags
0
"she said again [again]"
1
"she said again [again]"
dialogueSentences
14
tagDensity
0.5
leniency
1
rawRatio
0.286
effectiveRatio
0.286
97.24%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1809
totalAiIsmAdverbs
1
found
0
adverb
"really"
count
1
highlights
0
"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)
3.26%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1809
totalAiIsms
35
found
0
word
"pounding"
count
9
1
word
"chill"
count
1
2
word
"glinting"
count
1
3
word
"familiar"
count
1
4
word
"reminder"
count
1
5
word
"looming"
count
1
6
word
"scanning"
count
8
7
word
"echoing"
count
2
8
word
"silence"
count
1
9
word
"cacophony"
count
1
10
word
"weight"
count
1
11
word
"otherworldly"
count
1
12
word
"gleaming"
count
3
13
word
"could feel"
count
1
14
word
"tension"
count
1
15
word
"racing"
count
2
highlights
0
"pounding"
1
"chill"
2
"glinting"
3
"familiar"
4
"reminder"
5
"looming"
6
"scanning"
7
"echoing"
8
"silence"
9
"cacophony"
10
"weight"
11
"otherworldly"
12
"gleaming"
13
"could feel"
14
"tension"
15
"racing"
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
2
narrationSentences
129
matches
0
"g in disbelief"
1
"g in surprise"
87.49%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
3
hedgeCount
2
narrationSentences
129
filterMatches
0
"watch"
1
"see"
hedgeMatches
0
"happened to"
1
"begin to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
136
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
46
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1809
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
10
unquotedAttributions
0
matches
(empty)
50.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
54
wordCount
1664
uniqueNames
8
maxNameDensity
1.56
worstName
"Herrera"
maxWindowNameDensity
3.5
worstWindowName
"Quinn"
discoveredNames
Detective
1
Harlow
1
Quinn
22
London
1
Tomás
1
Herrera
26
Morris
1
Tube
1
persons
0
"Harlow"
1
"Quinn"
2
"Tomás"
3
"Herrera"
4
"Morris"
places
0
"London"
globalScore
0.719
windowScore
0.5
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
120
glossingSentenceCount
2
matches
0
"looked like spiders, like snakes, like no"
1
"looked like human teeth, another selling"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.553
wordCount
1809
matches
0
"not over the din of the market, but she could see Herrera's face, see the way he was listening"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
136
matches
0
"knew that she"
48.50%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
36
mean
50.25
std
16.07
cv
0.32
sampleLengths
0
75
1
61
2
59
3
76
4
52
5
74
6
38
7
48
8
63
9
41
10
58
11
67
12
73
13
51
14
31
15
38
16
38
17
20
18
56
19
61
20
30
21
39
22
20
23
36
24
68
25
29
26
32
27
45
28
51
29
71
30
33
31
60
32
53
33
62
34
66
35
34
88.94%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
6
totalSentences
129
matches
0
"was involved"
1
"was gone"
2
"was unlocked"
3
"were lined"
4
"was guarded"
5
"was coiled"
42.34%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
7
totalVerbs
296
matches
0
"was talking"
1
"was really going"
2
"was talking"
3
"was saying"
4
"was listening"
5
"was still standing"
6
"were looking"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
1
flaggedSentences
1
totalSentences
136
ratio
0.007
matches
0
"But Herrera wasn't just a suspect; he was a key, a door to a world she'd only glimpsed at the edges of her vision."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1668
adjectiveStacks
0
stackExamples
(empty)
adverbCount
38
adverbRatio
0.022781774580335732
lyAdverbCount
4
lyAdverbRatio
0.002398081534772182
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
136
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
136
mean
13.3
std
6.96
cv
0.523
sampleLengths
0
22
1
18
2
24
3
11
4
20
5
22
6
19
7
11
8
8
9
17
10
23
11
12
12
26
13
24
14
14
15
9
16
16
17
8
18
9
19
10
20
8
21
13
22
18
23
23
24
12
25
20
26
18
27
19
28
15
29
14
30
12
31
16
32
16
33
19
34
9
35
7
36
18
37
7
38
12
39
14
40
17
41
15
42
16
43
18
44
8
45
10
46
15
47
10
48
11
49
17
30.88%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
26
diversityRatio
0.15441176470588236
totalSentences
136
uniqueOpeners
21
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
8
totalSentences
129
matches
0
"Then she holstered her gun,"
1
"Then he turned and walked"
2
"Then she made her choice."
3
"Then he smiled, a slow,"
4
"Then she reached out, her"
5
"Then she turned and led"
6
"Then she closed the door,"
7
"Then she turned and walked"
ratio
0.062
24.65%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
63
totalSentences
129
matches
0
"She'd been tracking Tomás Herrera"
1
"Her breath misted in the"
2
"She'd lost count of how"
3
"She could hear Herrera's ragged"
4
"She'd been after Herrera for"
5
"She rounded the corner, her"
6
"She could hear voices coming"
7
"She'd followed Herrera this far,"
8
"She was a cop, not"
9
"She took a deep breath,"
10
"She could see a faint"
11
"She stepped out into a"
12
"She was in an abandoned"
13
"She was out of her"
14
"She pushed her way through"
15
"She saw a woman with"
16
"She saw creatures that looked"
17
"He was talking to a"
18
"She could arrest Herrera now,"
19
"She took a deep breath,"
ratio
0.488
84.03%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
97
totalSentences
129
matches
0
"The rain was a relentless"
1
"The city lights reflected off"
2
"She'd been tracking Tomás Herrera"
3
"Her breath misted in the"
4
"The sharp pain in her"
5
"She'd lost count of how"
6
"Herrera darted into an alley,"
7
"Quinn followed, her heart pounding"
8
"The alley was narrow, the"
9
"She could hear Herrera's ragged"
10
"Quinn slowed, her hand resting"
11
"She'd been after Herrera for"
12
"A world of shadows and"
13
"She rounded the corner, her"
14
"Herrera was gone, but there"
15
"Quinn approached, her boots echoing"
16
"The grate was old, rusted,"
17
"She could hear voices coming"
18
"Quinn hesitated, her hand still"
19
"She'd followed Herrera this far,"
ratio
0.752
100.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
8
totalSentences
129
matches
0
"No matter where it led"
1
"No matter what she had"
2
"No matter what it took."
3
"No matter where it led"
4
"No matter what she had"
5
"No matter what it took."
6
"No matter what it cost."
7
"No matter what she had"
ratio
0.062
65.40%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
83
technicalSentenceCount
9
matches
0
"A world of shadows and secrets, of things that went bump in the night."
1
"Closer to finding out why he'd died under circumstances that defied explanation."
2
"He was talking to a man with a face like a raven, his eyes gleaming black and beady."
3
"He handed it to Herrera, who took it with a nod."
4
"The raven-faced man led her to a door at the back of the market, a door that was guarded by two men with guns."
5
"Then he smiled, a slow, dangerous smile that made Quinn's blood run cold."
6
"She could see the uniforms, their hands on their guns, their eyes watching her, waiting for her signal."
7
"Herrera smiled, a slow, dangerous smile that made Quinn's blood run cold."
8
"She could see the worry in their eyes, the way they were looking at her, at Herrera, at the world that had led them here."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
7
uselessAdditionCount
7
matches
0
"she said, her voice low and dangerous"
1
"he said, his voice a low purr"
2
"she said, her voice steady and calm"
3
"he said, his eyes gleaming in the dim light"
4
"she said again, her voice steady and calm"
5
"she said again, her voice steady and calm"
6
"he said, his voice a low purr"
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
7
fancyCount
0
fancyTags
(empty)
dialogueSentences
14
tagDensity
0.5
leniency
1
rawRatio
0
effectiveRatio
0
77.4248%