NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-17-01KHMPE18CHP9HQMKKHHRV7JHP
Run Details
Model:
Mistral NeMO
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
9.0s
Cost:
$0.000367
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
82.00%
AI-ism adverb frequency
(details)
80.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
14.49%
AI-ism word frequency
(details)
100.00%
Cliché density
(details)
100.00%
Emotion telling (show vs. tell)
(details)
99.13%
Filter word density
(details)
100.00%
Gibberish response detection
(details)
100.00%
Markdown formatting overuse
(details)
100.00%
Missing dialogue indicators (quotation marks)
(details)
48.83%
Name drop frequency
(details)
78.57%
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)
94.52%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
67.67%
Em-dash & semicolon overuse
(details)
94.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
39.47%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
44.18%
Pronoun-first sentence starts
(details)
58.90%
Subject-first sentence starts
(details)
100.00%
Subordinate conjunction sentence starts
(details)
93.02%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
0.00%
Dialogue tag variety (said vs. fancy)
(details)
79.8260%
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
Detective Harlow Quinn stepped off
the creaking lift, her worn leather boots
echoing
in the abandoned Tube station.
The air was damp and
heavy, laden with the scent of decay and something else—an acrid tang that prickled her nostrils.
She adjusted her watch, the
worn leather strap
familiar
under her fingers, and surveyed the scene.
The Veil Market, hidden beneath
Camden, was a labyrinth of stalls and alleyways, a supernatural black market that moved with the moon.
Tonight, it was bathed in
the cold glow of emergency lights, casting long,
dancing
shadows that seemed to writhe with a life of their own
. Quinn's partner, Detective Sergeant
Thompson
, was already there, his lanky frame hunched over a body sprawled on the grimy floor.
He looked up as she
approached, his glasses reflecting the harsh light. "Quinn,"
he acknowledged, straightening
. "You're late." Quinn ignored the jab.
She was never late, not
really
. But
Thompson
didn't know about her detour, the whispered conversation with an informant in a back alley, the exchange of a bone token for a tip about a body here.
She stepped closer, her sharp
jaw set in a grim line. The victim was a woman, her curly red hair fanned out around her like a halo.
Her eyes were closed, her
face peaceful, almost serene. Too peaceful, given the circumstances.
Quinn crouched down, her military
precision evident in her movements.
She noted the round glasses
askew on the bridge of the woman's nose, the worn leather satchel beside her, overflowing with books.
She reached out, gently tucking
a strand of hair behind the woman's left ear, revealing a freckled complexion. "Eva Kowalski,"
Quinn murmured, recognition dawning
. "Aurora's friend."
Thompson
nodded. "Yeah. Know her?"
Quinn stood, her gaze sweeping
the area. "Not personally. But I've seen her with Aurora. She's a researcher, works at the British Museum."
Thompson
consulted his notebook. "Evie, according to her ID. Any idea what she was doing here?"
Quinn didn't answer, her attention
drawn to the woman's hands.
They were clean, no signs
of struggle. No defensive wounds, no bruising.
She looked around again, her
brow
furrowing
. Something was off.
She could feel it, like
a prickle at the back of her neck.
She noticed it then, the
faint glow emanating from Eva's satchel.
She reached in, her fingers
brushing against leather-bound books, a tattered map, and then, a small brass compass.
It was old, the casing
etched
with protective sigils, the needle pointing
not north, but towards a dark corner of the market
. Towards a rift, according to the whispers she'd heard. "Quinn?"
Thompson
prompted, following her gaze. "What is it?" Quinn held up the compass, the patina of verdigris
glinting
under the lights. "This," she said, "is a Veil Compass. It's attuned to supernatural energy."
Thompson
scoffed. "Supernatural? Quinn, come on. We're talking about a murder here, not some ghost story." Quinn ignored him, her mind
racing
.
She'd seen one of these
before, three years ago, during the case that had taken Morris. The one she still couldn't explain. The one that had led her here, to the Veil Market, to Eva Kowalski's body.
She stood, her gaze sweeping
the area again. This time, she saw it—the faint shimmer in the air, the subtle distortion. A rift, barely visible, pulsating with energy.
She stepped closer, the compass
needle spinning wildly in her hand. "Quinn, what are you doing?"
Thompson
asked, concern
etched
on his face. "We should wait for backup." Quinn didn't respond. She couldn't. Not when she was so close.
She reached out, her fingers
brushing against the shimmer. It was cold, like ice, and it hummed under her touch.
She could feel it, the
energy pulsing, the
otherworldly
power. She looked back at Eva, her serene face, her unmarked body. She didn't struggle, Quinn thought. Because she didn't have to.
Because she'd gone through the
rift willingly. Quinn stepped back, her mind made up. "We're not dealing with a murder here,
Thompson
,"
she said, her voice steady
. "We're dealing with a disappearance."
Thompson
stared at her, disbelief written all over his face. "A disappearance? Quinn, she's dead. We have a body." Quinn shook her head. "No, we don't. Not
really
. Not in the way you think." She looked at Eva again, her heart heavy. "She's not here,
Thompson
. She's gone. Through the rift."
Thompson
opened his mouth to argue, then closed it, his gaze flicking between Quinn and the rift. He sighed, running a hand through his hair. "Alright, Quinn. Let's say you're right. Let's say she went through willingly. Why? What's on the other side?" Quinn looked at the compass, the needle still spinning wildly. "I don't know," she admitted. "But I intend to find out." She took a deep breath, steeling herself. Then, before
Thompson
could protest, she stepped forward, into the shimmer. Into the rift. Into the unknown. The world around her shifted, the market dissolving into a
kaleidoscope
of colors and shapes. She
felt a tug
, a pull, like she was
being stretched
thin.
Then, as suddenly as it
had begun, it ended. Quinn stumbled, her boots sinking into soft earth. She looked around, her breath catching in her throat. She was in a forest, the trees ancient, their branches heavy with
leaves that seemed to absorb the light
.
The air was thick with
humidity, the scent of earth and something else—something sweet, almost intoxicating. She heard a rustle, a soft footstep. She turned, her hand going to her gun. But it wasn't Eva. It was a man, tall, his skin the color of moonlight. His eyes were black, bottomless, and he smiled at her, his teeth sharp. "Welcome, Detective," he said, his voice like
velvet
. "I've been waiting for you." Quinn's hand tightened on her gun, her heart
pounding
in her chest. "Where's Eva?"
she demanded, her voice steady despite the fear coiling in her gut
. The man's smile widened. "Eva?" he
echoed
. "Ah, yes. The researcher. She's here, Detective. She's waiting for you." Quinn's heart pounded louder. She
could feel
it now, the energy pulsing around her, through her. She
could feel
Eva, too, her presence like a
beacon
. She took a step forward, then another, her gaze locked on the man. "Quinn,"
he warned, his smile fading
. "You shouldn't—" But Quinn didn't stop. She couldn't. Not when she was so close. Not when she
could feel
Eva, so near, yet so far. She stepped forward, into the light. Into the unknown. Into the mystery that had led her here, to this place, to this moment. And she knew, as she took that final step, that her life would never be the same.
total_cost
0.0003675
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
12
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
28
tagDensity
0.429
leniency
0.857
rawRatio
0
effectiveRatio
0
82.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1111
totalAiIsmAdverbs
4
found
0
adverb
"really"
count
2
1
adverb
"gently"
count
1
2
adverb
"suddenly"
count
1
highlights
0
"really"
1
"gently"
2
"suddenly"
80.00%
AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions
(empty)
found
0
"Thompson"
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
14.49%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1111
totalAiIsms
19
found
0
word
"echoing"
count
1
1
word
"familiar"
count
1
2
word
"dancing"
count
1
3
word
"furrowing"
count
1
4
word
"could feel"
count
5
5
word
"etched"
count
2
6
word
"glinting"
count
1
7
word
"racing"
count
1
8
word
"otherworldly"
count
1
9
word
"kaleidoscope"
count
1
10
word
"velvet"
count
1
11
word
"pounding"
count
1
12
word
"echoed"
count
1
13
word
"beacon"
count
1
highlights
0
"echoing"
1
"familiar"
2
"dancing"
3
"furrowing"
4
"could feel"
5
"etched"
6
"glinting"
7
"racing"
8
"otherworldly"
9
"kaleidoscope"
10
"velvet"
11
"pounding"
12
"echoed"
13
"beacon"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"air was thick with"
count
1
highlights
0
"The air was thick with"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
1
narrationSentences
98
matches
0
"felt a tug"
99.13%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
2
narrationSentences
98
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
114
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
30
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1108
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
15
unquotedAttributions
0
matches
(empty)
48.83%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
48
wordCount
939
uniqueNames
12
maxNameDensity
2.02
worstName
"Quinn"
maxWindowNameDensity
3
worstWindowName
"Quinn"
discoveredNames
Harlow
1
Quinn
19
Tube
1
Veil
2
Market
2
Camden
1
Detective
2
Sergeant
1
Thompson
10
Eva
7
Morris
1
Kowalski
1
persons
0
"Harlow"
1
"Quinn"
2
"Market"
3
"Sergeant"
4
"Thompson"
5
"Morris"
6
"Kowalski"
places
0
"Veil"
globalScore
0.488
windowScore
0.667
78.57%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
70
glossingSentenceCount
2
matches
0
"shadows that seemed to writhe with a life of their own"
1
"leaves that seemed to absorb the light"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.903
wordCount
1108
matches
0
"not north, but towards a dark corner of the market"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
114
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
35
mean
31.66
std
16.73
cv
0.528
sampleLengths
0
55
1
47
2
38
3
51
4
80
5
8
6
5
7
23
8
16
9
45
10
60
11
9
12
25
13
16
14
43
15
39
16
17
17
41
18
28
19
25
20
19
21
32
22
43
23
21
24
24
25
36
26
52
27
43
28
13
29
26
30
18
31
39
32
8
33
23
34
40
94.52%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
3
totalSentences
98
matches
0
"was bathed"
1
"were closed"
2
"being stretched"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
164
matches
(empty)
67.67%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
3
semicolonCount
0
flaggedSentences
3
totalSentences
114
ratio
0.026
matches
0
"The air was damp and heavy, laden with the scent of decay and something else—an acrid tang that prickled her nostrils."
1
"This time, she saw it—the faint shimmer in the air, the subtle distortion."
2
"The air was thick with humidity, the scent of earth and something else—something sweet, almost intoxicating."
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
943
adjectiveStacks
1
stackExamples
0
"against leather-bound books,"
adverbCount
34
adverbRatio
0.036055143160127257
lyAdverbCount
9
lyAdverbRatio
0.009544008483563097
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
114
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
114
mean
9.72
std
5.73
cv
0.589
sampleLengths
0
18
1
21
2
16
3
22
4
25
5
20
6
12
7
4
8
2
9
4
10
6
11
30
12
11
13
16
14
9
15
5
16
10
17
22
18
18
19
6
20
2
21
2
22
3
23
7
24
16
25
4
26
12
27
10
28
7
29
5
30
7
31
3
32
13
33
11
34
18
35
22
36
9
37
6
38
3
39
13
40
12
41
2
42
14
43
6
44
16
45
6
46
15
47
8
48
13
49
7
39.47%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
15
diversityRatio
0.3157894736842105
totalSentences
114
uniqueOpeners
36
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
3
totalSentences
91
matches
0
"Too peaceful, given the circumstances."
1
"Then, before Thompson could protest,"
2
"Then, as suddenly as it"
ratio
0.033
44.18%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
40
totalSentences
91
matches
0
"She adjusted her watch, the"
1
"He looked up as she"
2
"he acknowledged, straightening"
3
"She was never late, not"
4
"She stepped closer, her sharp"
5
"Her eyes were closed, her"
6
"She noted the round glasses"
7
"She reached out, gently tucking"
8
"They were clean, no signs"
9
"She looked around again, her"
10
"She could feel it, like"
11
"She noticed it then, the"
12
"She reached in, her fingers"
13
"It was old, the casing"
14
"She'd seen one of these"
15
"She stood, her gaze sweeping"
16
"She stepped closer, the compass"
17
"She reached out, her fingers"
18
"It was cold, like ice,"
19
"She could feel it, the"
ratio
0.44
58.90%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
73
totalSentences
91
matches
0
"Detective Harlow Quinn stepped off"
1
"The air was damp and"
2
"She adjusted her watch, the"
3
"The Veil Market, hidden beneath"
4
"Tonight, it was bathed in"
5
"Quinn's partner, Detective Sergeant Thompson,"
6
"He looked up as she"
7
"he acknowledged, straightening"
8
"Quinn ignored the jab."
9
"She was never late, not"
10
"She stepped closer, her sharp"
11
"The victim was a woman,"
12
"Her eyes were closed, her"
13
"Quinn crouched down, her military"
14
"She noted the round glasses"
15
"She reached out, gently tucking"
16
"Quinn murmured, recognition dawning"
17
"Quinn stood, her gaze sweeping"
18
"Thompson consulted his notebook."
19
"Quinn didn't answer, her attention"
ratio
0.802
100.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
2
totalSentences
91
matches
0
"Because she didn't have to."
1
"Because she'd gone through the"
ratio
0.022
93.02%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
43
technicalSentenceCount
3
matches
0
"The air was damp and heavy, laden with the scent of decay and something else—an acrid tang that prickled her nostrils."
1
"The Veil Market, hidden beneath Camden, was a labyrinth of stalls and alleyways, a supernatural black market that moved with the moon."
2
"Tonight, it was bathed in the cold glow of emergency lights, casting long, dancing shadows that seemed to writhe with a life of their own."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
12
uselessAdditionCount
5
matches
0
"Quinn murmured, recognition dawning"
1
"she said, her voice steady"
2
"She looked, her heart heavy"
3
"she demanded, her voice steady despite the fear coiling in her gut"
4
"he warned, his smile fading"
0.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
9
fancyCount
5
fancyTags
0
"he acknowledged (acknowledge)"
1
"Quinn murmured (murmur)"
2
"she admitted (admit)"
3
"she demanded (demand)"
4
"he warned (warn)"
dialogueSentences
28
tagDensity
0.321
leniency
0.643
rawRatio
0.556
effectiveRatio
0.357
79.8260%