NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHTR1N1CSBCKFXVRXVN2G6ZP
Run Details
Model:
Mistral NeMO
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
8.8s
Cost:
$0.000365
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
80.95%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
42.86%
AI-ism word frequency
(details)
66.67%
Cliché density
(details)
86.54%
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)
100.00%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
55.10%
Paragraph length variance
(details)
99.87%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
94.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
58.02%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
42.22%
Pronoun-first sentence starts
(details)
15.56%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
30.95%
Dialogue tag variety (said vs. fancy)
(details)
77.4245%
Overall
Model input
System
You are an expert fiction writer. Always keep the following rules in mind: - Write in past tense and use General English spelling, grammar, and colloquialisms/slang. - Write in active voice - Always follow the "show, don't tell" principle. - Avoid adverbs and cliches and overused/commonly used phrases. Aim for fresh and original descriptions. - Convey events and story through dialogue. - Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. - Skip "he/she said said" dialogue tags and convey people's actions or face expressions through their speech - Avoid mushy dialog and descriptions, have dialogue always continue the action, never stall or add unnecessary fluff. Vary the descriptions to not repeat yourself. - Put dialogue on its own paragraph to separate scene and action. - Reduce indicators of uncertainty like "trying" or "maybe" When writing text: - NEVER conclude the scene on your own, follow the beat instructions very closely. - NEVER end with foreshadowing. - NEVER write further than what I prompt you with. - AVOID imagining possible endings, NEVER deviate from the instructions. - STOP EARLY if the continuation contains what was required in the instructions. You do not need to fill out the full amount of words possible.
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <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> Continue the story using the following instructions: <instructions> 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. </instructions>
Model response
Messages
Meta
AI
In the heart of Soho, The Raven's Nest hummed with a quiet weekday evening buzz.
The air was thick with
the scent of aged wood and the murmur of hushed conversations. Behind the worn mahogany bar, Silas Blackwood, his hazel eyes reflecting the dim glow of the green neon sign outside, poured a pint of ale with
practiced ease
.
His silver signet ring glinted
under the amber light as he set the drink down in front of a regular, a nod the only exchange between them.
The door creaked open, letting
in a gust of cool London air and a young woman with straight shoulder-length black hair and bright blue eyes.
Aurora Carter, known to most
as Rory, stepped inside, her gaze sweeping the room. She was a
familiar
face, yet tonight, there was a
tension
in her shoulders, a wariness in her eyes that hadn't been there before.
Silas looked up, his eyes
meeting hers.
A flicker of recognition
crossed his face, followed by a moment of hesitation. Then, he smiled, a warm, welcoming smile that crinkled the corners of his eyes. "Rory,"
he said, his voice a
low rumble, "It's been a while."
Rory hesitated, then returned the
smile, though it didn't reach her eyes. "Silas,"
she acknowledged, stepping up to
the bar. "I didn't expect to see you here." Silas raised an
eyebrow
. "This is my bar, Rory. Where else would I be?"
He poured her a drink
without asking, a glass of red wine, her usual. "You look... different,"
he observed, pushing the glass
towards her.
Rory wrapped her fingers around
the stem of the glass, her small crescent-shaped scar on her left wrist catching the light. "It's been what, three years?"
she said, avoiding the question
. "People change, Silas." Silas leaned against the bar, his left leg bearing most of his
weight
, the old knee injury making itself known in the slight limp. "Indeed, they do,"
he agreed, his gaze steady
on her. "Some for the better, others... not so much."
Rory took a sip of
her wine, her eyes flicking away from his intense stare. "I've heard you've been busy,"
she said, changing the subject
. "The Nest has become quite the hub for... interesting people."
Silas chuckled, a low sound
that held a hint of irony. "You could say that. Business has been good."
He paused, then added
, "But I've missed our chats, Rory. You had a way of cutting through the bullshit." Rory smiled, a genuine one this time, though it
was tinged
with sadness. "And you had a way of making me see things from different angles, Silas. I miss that." Silas reached out, his hand covering hers on the bar.
His thumb brushed over her
scar, a silent acknowledgment of the past. "What's been happening, Rory?"
he asked softly
. "You've got shadows under your eyes, and you're jumpy as a cat in a room full of rocking chairs." Rory pulled her hand away, wrapping both hands around her wine glass.
She looked down into the
dark red liquid, her reflection staring back at her. "Life happens, Silas,"
she said, her voice barely
above a
whisper
. "Some of it good, some of it... not so much." Silas nodded, understanding more than she
was saying
. He knew about her past, about the abusive ex she'd left behind in Cardiff.
He'd seen the bruises, heard
the stories, and had offered his help then. But Rory had been stubborn,
determined
to face her demons alone.
He respected that, but it
didn't mean he had to like it. "You know you can talk to me, Rory,"
he said, his voice gentle
yet firm. "Whatever it is, whatever you've been through, it's not too late to turn things around." Rory looked up at him, her eyes shining with unshed tears. "Isn't it, Silas?"
she asked, her voice hoarse
. "Some things can't be undone. Some people can't be saved." Silas reached out again, this time cupping her cheek. "And some people can't save themselves until they're ready,"
he said, his thumb brushing
away a tear that had escaped. "But you're ready now, Rory. I can see it in your eyes." Rory leaned into his touch, her eyes closing briefly. When she opened them again, there was a determination in her gaze that hadn't been there before. "Maybe you're right, Silas,"
she said, her voice steady
. "Maybe it's time to start over." Silas smiled, a slow, warm smile that lit up his eyes. "I'm glad to hear you say that, Rory," he said, dropping his hand. "Because I have a feeling you're going to need a fresh start." Rory raised an
eyebrow
, a hint of her old self shining through. "Oh,
really
?" she asked, a challenge in her voice. "And why's that?" Silas leaned back, his eyes twinkling with mischief. "Because, my dear Rory," he said, "I have a job offer for you. And it's not the kind of offer you can refuse." Rory's
eyes widened
, surprise and curiosity warring in her expression. "A job offer?"
she repeated, her voice barely above a whisper
. Silas nodded, his gaze serious now. "A job that will take you places you've never been, introduce you to people you've never met, and give you a chance to make a real difference," he said. "But it won't be easy, Rory. It will test your skills, your courage, and your loyalty." Rory took a deep breath, her eyes never leaving Silas's.
Then, she nodded, a decisive
movement that spoke volumes. "I'm in,"
she said, her voice steady
. "Whatever it is, whatever it takes, I'm in." Silas smiled, a smile that held a promise of things to come. "Good," he said, standing up straight. "Because the world needs more people like you, Rory. People who aren't afraid to get their hands dirty, to fight for what's right, and to never give up, no matter the odds." Rory raised her glass, a small smile playing on her lips. "To new beginnings," she said, her voice
filled with hope
and determination. Silas clinked his glass against hers, his eyes reflecting the amber light of the bar. "To new beginnings,"
he echoed, a silent vow passing between them
. Whatever lay ahead, they would face it together. And that, in itself, was a promise of a brighter future.
total_cost
0.00036465
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
23
adverbTagCount
2
adverbTags
0
"He paused then [then]"
1
"he asked softly [softly]"
dialogueSentences
39
tagDensity
0.59
leniency
1
rawRatio
0.087
effectiveRatio
0.087
80.95%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1050
totalAiIsmAdverbs
4
found
0
adverb
"softly"
count
1
1
adverb
"barely above a whisper"
count
2
2
adverb
"really"
count
1
highlights
0
"softly"
1
"barely above a whisper"
2
"really"
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)
42.86%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1050
totalAiIsms
12
found
0
word
"practiced ease"
count
1
1
word
"familiar"
count
1
2
word
"tension"
count
1
3
word
"flicker"
count
1
4
word
"eyebrow"
count
2
5
word
"weight"
count
1
6
word
"tinged"
count
1
7
word
"whisper"
count
2
8
word
"determined"
count
1
9
word
"echoed"
count
1
highlights
0
"practiced ease"
1
"familiar"
2
"tension"
3
"flicker"
4
"eyebrow"
5
"weight"
6
"tinged"
7
"whisper"
8
"determined"
9
"echoed"
66.67%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
3
maxInWindow
2
found
0
label
"eyes widened/narrowed"
count
1
1
label
"air was thick with"
count
1
2
label
"flicker of emotion"
count
1
highlights
0
"eyes widened"
1
"The air was thick with"
2
"A flicker of recognition"
86.54%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
3
narrationSentences
65
matches
0
"d with sadness"
1
"filled with hope"
2
"d with hope"
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
65
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
81
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
32
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1048
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
21
unquotedAttributions
0
matches
(empty)
50.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
34
wordCount
704
uniqueNames
9
maxNameDensity
1.99
worstName
"Silas"
maxWindowNameDensity
3.5
worstWindowName
"Silas"
discoveredNames
Soho
1
Raven
1
Nest
1
Silas
14
Blackwood
1
London
1
Carter
1
Rory
13
Cardiff
1
persons
0
"Raven"
1
"Nest"
2
"Silas"
3
"Blackwood"
4
"Carter"
5
"Rory"
places
0
"Soho"
1
"London"
2
"Cardiff"
globalScore
0.506
windowScore
0.5
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
53
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1048
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
81
matches
(empty)
55.10%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
26
mean
40.31
std
13.82
cv
0.343
sampleLengths
0
86
1
63
2
46
3
27
4
38
5
34
6
42
7
35
8
38
9
30
10
48
11
47
12
58
13
30
14
29
15
41
16
41
17
36
18
24
19
31
20
21
21
51
22
34
23
50
24
23
25
45
99.87%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
65
matches
0
"was tinged"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
1
totalVerbs
123
matches
0
"was saying"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
81
ratio
0
matches
(empty)
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
706
adjectiveStacks
1
stackExamples
0
"small crescent-shaped scar"
adverbCount
20
adverbRatio
0.028328611898016998
lyAdverbCount
5
lyAdverbRatio
0.007082152974504249
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
81
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
81
mean
12.94
std
6.11
cv
0.472
sampleLengths
0
15
1
16
2
28
3
27
4
25
5
14
6
24
7
7
8
13
9
14
10
12
11
12
12
8
13
7
14
4
15
24
16
10
17
21
18
10
19
3
20
24
21
10
22
8
23
15
24
10
25
10
26
11
27
27
28
13
29
17
30
10
31
12
32
7
33
19
34
12
35
14
36
11
37
10
38
8
39
14
40
13
41
11
42
12
43
15
44
15
45
11
46
8
47
10
48
9
49
20
58.02%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
3
diversityRatio
0.37037037037037035
totalSentences
81
uniqueOpeners
30
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
2
totalSentences
63
matches
0
"Then, he smiled, a warm,"
1
"Then, she nodded, a decisive"
ratio
0.032
42.22%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
28
totalSentences
63
matches
0
"His silver signet ring glinted"
1
"She was a familiar face,"
2
"he said, his voice a"
3
"she acknowledged, stepping up to"
4
"He poured her a drink"
5
"he observed, pushing the glass"
6
"she said, avoiding the question"
7
"he agreed, his gaze steady"
8
"she said, changing the subject"
9
"He paused, then added"
10
"His thumb brushed over her"
11
"he asked softly"
12
"She looked down into the"
13
"she said, her voice barely"
14
"He knew about her past,"
15
"He'd seen the bruises, heard"
16
"He respected that, but it"
17
"he said, his voice gentle"
18
"she asked, her voice hoarse"
19
"he said, his thumb brushing"
ratio
0.444
15.56%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
56
totalSentences
63
matches
0
"The air was thick with"
1
"His silver signet ring glinted"
2
"The door creaked open, letting"
3
"Aurora Carter, known to most"
4
"She was a familiar face,"
5
"Silas looked up, his eyes"
6
"A flicker of recognition crossed"
7
"he said, his voice a"
8
"Rory hesitated, then returned the"
9
"she acknowledged, stepping up to"
10
"Silas raised an eyebrow."
11
"He poured her a drink"
12
"he observed, pushing the glass"
13
"Rory wrapped her fingers around"
14
"she said, avoiding the question"
15
"Silas leaned against the bar,"
16
"he agreed, his gaze steady"
17
"Rory took a sip of"
18
"she said, changing the subject"
19
"Silas chuckled, a low sound"
ratio
0.889
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
63
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
33
technicalSentenceCount
1
matches
0
"Then, he smiled, a warm, welcoming smile that crinkled the corners of his eyes."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
23
uselessAdditionCount
10
matches
0
"he said, his voice a low rumble,"
1
"He poured, a glass of red wine, her usual"
2
"he agreed, his gaze steady on her"
3
"she said, her voice barely above a whisper"
4
"he said, his voice gentle yet firm"
5
"he said, his thumb brushing away a tear that had escaped"
6
"she said, her voice steady"
7
"she repeated, her voice barely above a whisper"
8
"she said, her voice steady"
9
"he echoed, a silent vow passing between them"
30.95%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
21
fancyCount
5
fancyTags
0
"she acknowledged (acknowledge)"
1
"He poured (pour)"
2
"he observed (observe)"
3
"he agreed (agree)"
4
"she repeated (repeat)"
dialogueSentences
39
tagDensity
0.538
leniency
1
rawRatio
0.238
effectiveRatio
0.238
77.4245%