NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXPSA7P6BHEDVJGQQHDYRFN
Run Details
Model:
Mistral Small 3.2 24B
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
27.0s
Cost:
$0.000543
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
0.00%
Adverbs in dialogue tags
(details)
70.21%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
0.00%
AI-ism word frequency
(details)
100.00%
Cliché density
(details)
96.59%
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)
36.36%
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)
100.00%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
91.15%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
57.05%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
52.43%
Pronoun-first sentence starts
(details)
41.08%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
83.33%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
79.2739%
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="4412" name="Aurora Carter" aliases="Rory, Laila, Aurora, Carter, Malphora" pronouns="she/her" species="Human" storyRole="Protagonist"> <eyeColor>bright blue</eyeColor> <hair>straight shoulder-length black</hair> <height>5'6"</height> <age>25</age> <scar>small crescent-shaped scar on her left wrist from a childhood accident</scar> <description>Aurora, referred to by her friends as Rory, is cool-headed, intelligent, and known for quick out-of-the-box thinking.</description> <backstory>Born in Cardiff to an Irish barrister father (Brendan Carter) and Welsh teacher mother (Jennifer Carter née Ellis), Rory reluctantly pursued Pre-Law at Cardiff University. She fled to London at the behest of her childhood friend Eva after leaving an abusive ex named Evan. By day, Rory works part-time as a delivery person for Yu-Fei Cheung's Golden Empress restaurant. She lives in a flat above Silas' bar.</backstory> </character> <character id="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</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> </codex> Write a fully fleshed out scene of at least 1000 words in the literary fiction genre. Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret. 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 distinctive green neon sign
of The Raven's Nest cast a soft glow on the rain-slicked pavement as Aurora Carter, her black hair damp from the evening drizzle, pushed open the heavy wooden door. The bar was dimly lit, the air thick with the scent of aged whiskey and the low hum of conversation.
She scanned the room, her
bright blue eyes taking in the
familiar
yet foreign atmosphere.
It had been years since
she'd set foot in this place, years since she'd seen him.
Silas Blackwood stood behind the
bar, his hazel eyes
scanning
the room with quiet authority.
His grey-streaked auburn hair was
neatly combed, matching the neatly trimmed beard that framed his face.
He wore a simple black
shirt, the sleeves rolled up to his elbows, revealing forearms corded with strength and age.
A silver signet ring glinted
on his right hand as he polished a glass, his movements practiced and precise.
He looked up as the
door swung shut, his gaze meeting hers. For a moment, time
seemed to
stand still.
Then, a slow smile spread
across his face, transforming his stern features into something almost boyish. "Well, well,"
he said, his voice a
deep rumble that carried easily across the room. "If it isn't little Rory Carter."
Aurora felt a flush creep
up her cheeks, a mixture of embarrassment and something else, something she couldn't
quite name
. She walked towards the bar, her boots clicking against the worn wooden floor. "Hi, Silas,"
she said, her voice steady
despite the butterflies in her
stomach
. "It's been a while."
Silas nodded, setting the glass
down on the bar. "Too long," he said. "What brings you to my neck of the woods?"
Aurora shrugged, sliding onto a
barstool. "Just passing through," she said. "Thought I'd stop in, see if the old place was still standing."
Silas chuckled, a warm sound
that
seemed to
fill the room. "Still standing," he said. "Though I can't say the same for some of our old friends." He leaned against the bar, his gaze searching her face. "You've changed, Rory."
Aurora looked down at her
hands, the small crescent-shaped scar on her left wrist catching the light. "We all change, Silas,"
she said softly
.
Silas studied her for a
moment longer, then straightened up. "What can I get you?"
he asked, his voice back
to its usual gruffness. "Whiskey," Aurora said. "Neat." Silas raised an
eyebrow
but didn't comment.
He turned to the shelves
behind him, reaching for a bottle of amber liquid. As he poured, Aurora looked around the bar. The walls were covered with old maps and black-and-white photographs, some of them
familiar
, most of them not.
It was as if the bar had become a museum of a life she'd left behind
. Silas set the glass in front of her, the liquid catching the light. Aurora picked it up, taking a sip. The whiskey burned her throat, but she welcomed the sensation, the way it grounded her in the present. "So," Silas said, leaning against the bar again. "What have you been up to all these years?" Aurora took another sip of her whiskey before answering. "This and that,"
she said vaguely
. "I moved to London a few years back. Work part-time at a restaurant, deliver food mostly." Silas nodded, his gaze never leaving her face. "And the rest of the time?" Aurora shrugged. "I read, I write, I try to stay out of trouble." Silas chuckled. "That's my girl," he said. "Always the dreamer." Aurora smiled, but there was a sadness to it that hadn't been there before. "Not as much as I used to be,"
she said softly
.
Silas studied her for a
moment longer, then pushed off from the bar. "I'll be right back," he said. "Don't go anywhere." Aurora watched as he disappeared through a door behind the bar, her fingers
tracing
the rim of her glass.
She took another sip of
her whiskey, the liquid warming her from the inside out.
She could feel the weight
of the years between them, the
unspoken
regrets and missed opportunities. Silas returned a few moments later, carrying a tray with two glasses and a bottle of whiskey.
He set them down on
the bar, pouring them each a drink. "To old friends,"
he said, raising his glass
. Aurora raised her own glass, clinking it against his. "To old friends," she
echoed
.
They drank in silence for
a while, the
weight
of the years between them hanging heavy in the air.
Then, Silas set down his
glass and looked at her. "You know," he said, "I always thought you'd end up doing something big. Something important."
Aurora looked down at her
hands, the scar on her wrist catching the light. "I did,"
she said softly
. "For a while, at least." Silas nodded, understanding in his eyes. "And now?" Aurora took a deep breath, letting it out
slowly
. "Now," she said, "I'm just trying to figure out what comes next."
Silas studied her for a
moment longer, then reached out, his hand covering hers. His touch was warm,
comforting
. "Well," he said, "you're always welcome here, Rory. You know that, right?" Aurora looked up at him, her bright blue eyes meeting his hazel ones. "Thank you, Silas,"
she said softly
. "That means a lot."
They drank in silence for
a while longer, the
weight
of the years between them easing
slightly
.
Then, Silas pushed off from
the bar. "I'll be right back," he said. "Don't go anywhere." Aurora watched as he disappeared through the door behind the bar, her fingers
tracing
the rim of her glass.
She took another sip of
her whiskey, the liquid warming her from the inside out.
She could feel the weight
of the years between them, the
unspoken
regrets and missed opportunities. But for the first time in a long time, she felt a
sense of
peace. She was home, in a way she hadn't been in years. And maybe, just maybe, that was enough. Silas returned a few moments later, carrying a tray with two more glasses and another bottle of whiskey.
He set them down on
the bar, pouring them each a drink. "To second chances,"
he said, raising his glass
. Aurora raised her own glass, clinking it against his. "To second chances," she
echoed
. They drank in
silence
, the
weight
of the years between them easing
slightly
with each sip. And as the night wore on, Aurora felt
a sense of hope
, a
sense of
possibility. Maybe, just maybe, she thought, as she looked at the man sitting beside her, maybe it wasn't too late to start over.
Maybe it wasn't too late
to find her way back to the person she'd once been, the person she'd left behind all those years ago. And as the whiskey flowed and the night wore on, she felt a
sense of
peace,
a sense of belonging
. She was home, in a way she hadn't been in years. And maybe, just maybe, that was enough.
created_at
"2026-02-20T14:20:44.673Z"
2/20/2026, 2:20:44 PM
model
"mistralai/mistral-small-3.2-24b-instruct-2506"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2403
moderation_latency
(null)
generation_time
26921
tokens_prompt
867
tokens_completion
1692
native_tokens_prompt
826
native_tokens_completion
1535
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
320
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
0.0005431
router
(null)
provider_responses
0
endpoint_id
"23fd6b91-74d8-45fc-ac00-cf141ec7f4a5"
id
"70b6fcc5653e44e3adc96614f671241e"
is_byok
false
latency
2403
model_permaslug
"mistralai/mistral-small-3.2-24b-instruct-2506"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771597244-OamhzUtO1PpwJ9Neg30F"
upstream_id
"70b6fcc5653e44e3adc96614f671241e"
total_cost
0.0005431
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
24
adverbTagCount
5
adverbTags
0
"she said softly [softly]"
1
"she said vaguely [vaguely]"
2
"she said softly [softly]"
3
"she said softly [softly]"
4
"she said softly [softly]"
dialogueSentences
40
tagDensity
0.6
leniency
1
rawRatio
0.208
effectiveRatio
0.208
70.21%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1175
totalAiIsmAdverbs
7
found
0
adverb
"softly"
count
4
1
adverb
"slowly"
count
1
2
adverb
"slightly"
count
2
highlights
0
"softly"
1
"slowly"
2
"slightly"
100.00%
AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0
"Blackwood"
found
(empty)
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
0.00%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1175
totalAiIsms
28
found
0
word
"scanned"
count
1
1
word
"familiar"
count
2
2
word
"scanning"
count
1
3
word
"stomach"
count
1
4
word
"eyebrow"
count
1
5
word
"tracing"
count
2
6
word
"could feel"
count
2
7
word
"weight"
count
5
8
word
"unspoken"
count
2
9
word
"echoed"
count
2
10
word
"silence"
count
3
11
word
"comforting"
count
1
12
word
"sense of"
count
5
highlights
0
"scanned"
1
"familiar"
2
"scanning"
3
"stomach"
4
"eyebrow"
5
"tracing"
6
"could feel"
7
"weight"
8
"unspoken"
9
"echoed"
10
"silence"
11
"comforting"
12
"sense of"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
0
maxInWindow
0
found
(empty)
highlights
(empty)
96.59%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
3
narrationSentences
88
matches
0
"felt a flush"
1
"a sense of hope"
2
"a sense of belonging"
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
2
narrationSentences
88
filterMatches
(empty)
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
104
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
35
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1169
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
23
unquotedAttributions
0
matches
(empty)
50.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
38
wordCount
966
uniqueNames
6
maxNameDensity
1.86
worstName
"Aurora"
maxWindowNameDensity
3.5
worstWindowName
"Aurora"
discoveredNames
Raven
1
Nest
1
Aurora
18
Carter
1
Blackwood
1
Silas
16
persons
0
"Raven"
1
"Nest"
2
"Aurora"
3
"Carter"
4
"Blackwood"
5
"Silas"
places
(empty)
globalScore
0.568
windowScore
0.5
36.36%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
66
glossingSentenceCount
3
matches
0
"quite name"
1
"sound that seemed to fill the room"
2
"It was as if the bar had become a museum of a life she'd left behind"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1169
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
104
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
35
mean
33.4
std
20.02
cv
0.599
sampleLengths
0
85
1
82
2
45
3
50
4
22
5
23
6
40
7
24
8
24
9
4
10
63
11
38
12
17
13
31
14
14
15
13
16
10
17
25
18
22
19
50
20
37
21
14
22
44
23
24
24
8
25
21
26
31
27
23
28
33
29
50
30
33
31
38
32
14
33
79
34
38
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
88
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
166
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
104
ratio
0
matches
(empty)
91.15%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
971
adjectiveStacks
1
stackExamples
0
"small crescent-shaped scar"
adverbCount
42
adverbRatio
0.04325437693099897
lyAdverbCount
12
lyAdverbRatio
0.012358393408856848
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
104
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
104
mean
11.24
std
5.96
cv
0.53
sampleLengths
0
34
1
20
2
15
3
16
4
15
5
16
6
20
7
19
8
12
9
8
10
16
11
15
12
6
13
20
14
13
15
13
16
4
17
9
18
4
19
9
20
6
21
5
22
12
23
11
24
4
25
22
26
3
27
17
28
7
29
10
30
14
31
3
32
1
33
7
34
14
35
8
36
18
37
16
38
13
39
7
40
18
41
8
42
9
43
9
44
6
45
16
46
8
47
6
48
2
49
11
57.05%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
4
diversityRatio
0.36538461538461536
totalSentences
104
uniqueOpeners
38
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
5
totalSentences
74
matches
0
"Then, a slow smile spread"
1
"Then, Silas set down his"
2
"Then, Silas pushed off from"
3
"Maybe, just maybe, she thought,"
4
"Maybe it wasn't too late"
ratio
0.068
52.43%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
31
totalSentences
74
matches
0
"She scanned the room, her"
1
"It had been years since"
2
"His grey-streaked auburn hair was"
3
"He wore a simple black"
4
"He looked up as the"
5
"he said, his voice a"
6
"She walked towards the bar,"
7
"she said, her voice steady"
8
"He leaned against the bar,"
9
"she said softly"
10
"he asked, his voice back"
11
"He turned to the shelves"
12
"It was as if the"
13
"she said vaguely"
14
"she said softly"
15
"She took another sip of"
16
"She could feel the weight"
17
"He set them down on"
18
"he said, raising his glass"
19
"They drank in silence for"
ratio
0.419
41.08%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
62
totalSentences
74
matches
0
"The distinctive green neon sign"
1
"The bar was dimly lit,"
2
"She scanned the room, her"
3
"It had been years since"
4
"Silas Blackwood stood behind the"
5
"His grey-streaked auburn hair was"
6
"He wore a simple black"
7
"A silver signet ring glinted"
8
"He looked up as the"
9
"he said, his voice a"
10
"Aurora felt a flush creep"
11
"She walked towards the bar,"
12
"she said, her voice steady"
13
"Silas nodded, setting the glass"
14
"Aurora shrugged, sliding onto a"
15
"Silas chuckled, a warm sound"
16
"He leaned against the bar,"
17
"Aurora looked down at her"
18
"she said softly"
19
"Silas studied her for a"
ratio
0.838
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
74
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
46
technicalSentenceCount
1
matches
0
"His grey-streaked auburn hair was neatly combed, matching the neatly trimmed beard that framed his face."
83.33%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
24
uselessAdditionCount
2
matches
0
"she said, her voice steady despite the butterflies in her stomach"
1
"He leaned, his gaze searching her face"
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
21
fancyCount
0
fancyTags
(empty)
dialogueSentences
40
tagDensity
0.525
leniency
1
rawRatio
0
effectiveRatio
0
79.2739%