NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY8D8THYCBNPE7804FS6G9H
Run Details
Model:
Gemma 3 12B
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
24.8s
Cost:
$0.001253
Provider:
Cloudflare
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
74.77%
AI-ism adverb frequency
(details)
80.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
11.69%
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)
0.00%
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)
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)
94.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
66.37%
Sentence opener variety
(details)
36.63%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
14.95%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
71.05%
Dialogue tag variety (said vs. fancy)
(details)
78.3152%
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 green neon sign of
The Raven’s Nest bled a sickly light onto the rain-slicked pavement of Soho. Rory pulled her collar higher, the damp
chill
seeping through her thin jacket.
Another delivery for the Golden
Empress, another hurried drop-off, another few pounds closer to rent. She hated these late shifts.
The city felt different at
night, sharper, more predatory.
She pushed open the heavy
oak door, the
familiar
scent of stale beer, polished wood, and something indefinably older washing over her.
Silas would be at the
bar, no doubt, nursing a whiskey and watching the world through eyes that had seen far too much. She nodded to the bartender, a young man with a shaved head and multiple piercings, and headed towards the
familiar
counter. Then she saw her. Across the room, bathed in the amber glow of a table lamp, sat a woman she hadn’t seen in fifteen years.
Elara
.
Rory stopped dead, the delivery
bag bumping against her leg. Fifteen years. It felt like a lifetime.
Elara
had been the sun in their small, Cardiff world. Bright, laughing, effortlessly cool.
Rory, the quiet observer, content
to orbit around her.
They’d sworn they’d conquer London
together, become artists, writers, something dazzling. Life, as it often did, had other plans.
Elara
hadn’t aged badly. Not at all. She was…transformed. The girl with the wild, auburn curls and paint-stained fingers
was gone
. In her place sat a woman sculpted from ice and diamonds. Her hair was a sleek, dark bob, pulled back from a face that was all sharp angles and expensive bone
structure
.
She wore a tailored black
suit, the kind that cost more than Rory’s entire wardrobe.
A single, flawless emerald ring
glittered on her left hand.
She was talking to a
man in a suit even more expensive than hers, his face obscured by shadow. Rory felt a sudden, inexplicable
pang
of…loss.
Not just for the girl she’d known, but for the girl she’d imagined they’d both become
. Silas, ever observant, caught her eye from behind the bar.
He raised an eyebrow, a
silent question. Rory nodded almost imperceptibly, then forced herself to move forward. “
Elara
?”
she said, her voice sounding
thin and reedy even to her own ears. The woman turned, her eyes – the same vibrant green Rory remembered – narrowed
slightly
. Recognition
flickered
across her face,
quickly
replaced by a
carefully
constructed
mask of polite indifference. “Rory? Rory Carter? My goodness. I hardly recognized you.” The accent was different, too. Sharper, more precise, with a hint of something foreign. “It’s been a while,” Rory managed, feeling awkward and out of place in her worn jeans and delivery jacket. “Indeed,”
Elara
said, her gaze sweeping over Rory’s clothes with a subtle, almost imperceptible disdain. “What brings you to The Raven’s Nest?” “Delivery,” Rory said, gesturing to the bag. “Golden Empress. You?”
Elara
’s lips curved into a brittle smile. “Business. Always business.”
She gestured to the man
beside her. “This is Mr. Volkov. He’s a…client.” Mr. Volkov offered a curt nod, his expression
unreadable
. Rory didn’t linger on him.
She focused on Elara, searching
for a
flicker
of the girl she remembered. “You look…well,” Rory stammered, hating how clumsy she sounded. “Different.”
Elara
laughed, a short, humorless sound. “Different is an understatement, I think. Life has a way of changing things, doesn’t it?” “It does,” Rory agreed, remembering Evan, the abusive ex she’d escaped, the years spent drifting, the quiet desperation of scraping by. “So, what have you been up to?”
Elara
asked, her voice
carefully
neutral. Rory hesitated. “Not much. Delivery work. Living above Silas’ bar.”
She gestured vaguely
. “You know.”
Elara
’s eyes
flickered
to Silas, then back to Rory. “Above Silas’ bar. How…quaint.” The word dripped with a condescension that stung. Rory felt a
familiar
defensiveness rising within her. “It’s a roof over my head,”
she said, her voice sharper
than she intended.
Elara
raised an
eyebrow
. “Of course. Well, I’m involved in…international finance now. Acquisitions, mergers, that sort of thing.” “Sounds…complicated,” Rory said, picturing spreadsheets and boardrooms and a world she could never understand. “It is,”
Elara
agreed. “But rewarding. Very rewarding.” She glanced at her
watch
, a thick gold band encrusted with diamonds. “I’m afraid I have a meeting. It was…pleasant seeing you, Rory.” “You too,
Elara
,” Rory said, the words tasting like ash in her mouth. As
Elara
rose to leave, Mr. Volkov placed a hand on her arm, his grip surprisingly firm.
They disappeared into the London
night, swallowed by the rain and the shadows. Rory turned back to the bar, feeling a strange hollowness in her chest. Silas
was watching
her, his hazel eyes filled with a quiet understanding. “Well?”
he asked, polishing a glass
with a practiced hand. “She’s…changed,” Rory said, stating the obvious. “People do,”
Silas said, his voice low
. “Especially when they chase different stars.” “Did she ever…did she ever do any of the things we talked about?”
Rory asked, the question hanging in the air
. The art, the writing, the dazzling life they’d dreamed of. Silas paused, his gaze fixed on a point beyond Rory’s shoulder. “She had a talent, yes. But talent alone isn’t enough. It needs…direction. And sometimes, the direction people choose isn’t the one you expect.” Rory nodded, the
unspoken
regret settling heavily on her. She’d chosen a different path, a quieter one. A path that had kept her safe, but also…small. “She seemed…distant,”
Rory said, more to herself than to Silas
. “She’s built walls, Rory,”
Silas said, his voice soft
. “High walls. It’s a good way to protect yourself. A lonely way, but effective.”
He slid a glass of
whiskey across the bar. “On the house.” Rory took a sip, the burn a welcome distraction. She looked around the bar, at the old maps and black-and-white photographs, at the
familiar
faces of the regulars. This was her world. A world of quiet routines and small comforts. A world far removed from the glittering life
Elara
now inhabited. “Do you ever…regret anything, Silas?” Rory asked, surprising herself with the question. Silas’s face darkened
slightly
, a
flicker
of pain crossing his features. He looked down at the silver signet ring on his right hand, a silent
testament
to a past he rarely spoke of. “Regret is a luxury I can’t afford, Rory,”
he said, his voice tight
. “But I’ve learned that sometimes, the choices you don’t make are just as important as the ones you do.” He paused, then looked at her, his eyes filled with a weary wisdom. “Don’t waste your time wondering what might have been, Rory. Focus on what is.” Rory finished her whiskey, the taste bitter on her tongue. She looked back towards the door, half expecting to see
Elara
reappear, to offer some explanation, some apology. But the rain continued to fall, washing away the last traces of her presence. She picked up the delivery bag, the
weight
of it
familiar
and
comforting
. Another delivery. Another few pounds closer to rent. Another night in her quiet, ordinary world. A world that, despite its limitations, was undeniably hers. And maybe, just maybe, that was enough.
created_at
"2026-02-20T19:28:44.378Z"
2/20/2026, 7:28:44 PM
model
"google/gemma-3-12b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
512
moderation_latency
(null)
generation_time
24625
tokens_prompt
892
tokens_completion
1955
native_tokens_prompt
850
native_tokens_completion
1707
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
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
0.00125342
router
(null)
provider_responses
0
endpoint_id
"5aef2a85-3d1c-4659-a522-98bbb5272c6a"
is_byok
false
latency
71
model_permaslug
"google/gemma-3-12b-it"
provider_name
"Crusoe"
status
429
1
endpoint_id
"08ebad49-bed1-4149-850c-d24e3c1d2084"
id
"id-1771615724858"
is_byok
false
latency
450
model_permaslug
"google/gemma-3-12b-it"
provider_name
"Cloudflare"
status
200
api_type
"completions"
id
"gen-1771615724-BKGCYW0MK27leqcqiUk9"
upstream_id
"id-1771615724858"
total_cost
0.00125342
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Cloudflare"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
23
adverbTagCount
1
adverbTags
0
"She gestured vaguely [vaguely]"
dialogueSentences
38
tagDensity
0.605
leniency
1
rawRatio
0.043
effectiveRatio
0.043
74.77%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1189
totalAiIsmAdverbs
6
found
0
adverb
"slightly"
count
2
1
adverb
"quickly"
count
1
2
adverb
"carefully"
count
2
3
adverb
"very"
count
1
highlights
0
"slightly"
1
"quickly"
2
"carefully"
3
"very"
80.00%
AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0
"Blackwood"
found
0
"Elara"
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
11.69%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1189
totalAiIsms
21
found
0
word
"chill"
count
1
1
word
"familiar"
count
5
2
word
"structure"
count
1
3
word
"flawless"
count
1
4
word
"pang"
count
1
5
word
"eyebrow"
count
2
6
word
"flickered"
count
2
7
word
"constructed"
count
1
8
word
"unreadable"
count
1
9
word
"flicker"
count
2
10
word
"unspoken"
count
1
11
word
"testament"
count
1
12
word
"weight"
count
1
13
word
"comforting"
count
1
highlights
0
"chill"
1
"familiar"
2
"structure"
3
"flawless"
4
"pang"
5
"eyebrow"
6
"flickered"
7
"constructed"
8
"unreadable"
9
"flicker"
10
"unspoken"
11
"testament"
12
"weight"
13
"comforting"
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
98
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
0
narrationSentences
98
filterMatches
0
"watch"
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
112
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
23
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1186
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
16
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
62
wordCount
954
uniqueNames
13
maxNameDensity
2.83
worstName
"Rory"
maxWindowNameDensity
5.5
worstWindowName
"Rory"
discoveredNames
Raven
1
Nest
1
Soho
1
Golden
1
Empress
1
Cardiff
1
London
2
Rory
27
Sharper
1
Elara
14
Mr
2
Evan
1
Silas
9
persons
0
"Raven"
1
"Nest"
2
"Rory"
3
"Elara"
4
"Mr"
5
"Evan"
6
"Silas"
places
0
"Soho"
1
"Cardiff"
2
"London"
globalScore
0.085
windowScore
0
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
76
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.843
wordCount
1186
matches
0
"Not just for the girl she’d known, but for the girl she’d imagined they’d both become"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
112
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
44
mean
26.95
std
17.71
cv
0.657
sampleLengths
0
60
1
66
2
4
3
22
4
59
5
97
6
23
7
27
8
14
9
30
10
23
11
19
12
22
13
10
14
23
15
27
16
10
17
21
18
21
19
13
20
15
21
13
22
30
23
18
24
14
25
31
26
13
27
30
28
25
29
10
30
6
31
13
32
31
33
34
34
26
35
10
36
35
37
51
38
12
39
33
40
32
41
27
42
42
43
44
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
98
matches
0
"was gone"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
2
totalVerbs
160
matches
0
"was talking"
1
"was watching"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
2
semicolonCount
0
flaggedSentences
1
totalSentences
112
ratio
0.009
matches
0
"The woman turned, her eyes – the same vibrant green Rory remembered – narrowed slightly."
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
957
adjectiveStacks
1
stackExamples
0
"same vibrant green Rory"
adverbCount
38
adverbRatio
0.03970741901776385
lyAdverbCount
15
lyAdverbRatio
0.01567398119122257
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
112
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
112
mean
10.59
std
5.58
cv
0.527
sampleLengths
0
18
1
13
2
15
3
5
4
9
5
22
6
23
7
21
8
4
9
21
10
1
11
10
12
2
13
5
14
10
15
4
16
9
17
11
18
8
19
4
20
3
21
2
22
12
23
11
24
21
25
15
26
10
27
19
28
7
29
16
30
10
31
7
32
10
33
14
34
15
35
15
36
14
37
9
38
19
39
15
40
7
41
7
42
3
43
7
44
10
45
6
46
1
47
8
48
5
49
13
66.37%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
4
diversityRatio
0.41964285714285715
totalSentences
112
uniqueOpeners
47
36.63%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
91
matches
0
"Then she saw her."
ratio
0.011
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
25
totalSentences
91
matches
0
"She hated these late shifts."
1
"She pushed open the heavy"
2
"She nodded to the bartender,"
3
"It felt like a lifetime."
4
"They’d sworn they’d conquer London"
5
"Her hair was a sleek,"
6
"She wore a tailored black"
7
"She was talking to a"
8
"He raised an eyebrow, a"
9
"she said, her voice sounding"
10
"She gestured to the man"
11
"She focused on Elara, searching"
12
"She gestured vaguely"
13
"she said, her voice sharper"
14
"She glanced at her watch,"
15
"They disappeared into the London"
16
"he asked, polishing a glass"
17
"She’d chosen a different path,"
18
"He slid a glass of"
19
"She looked around the bar,"
ratio
0.275
14.95%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
81
totalSentences
91
matches
0
"The green neon sign of"
1
"Rory pulled her collar higher,"
2
"Another delivery for the Golden"
3
"She hated these late shifts."
4
"The city felt different at"
5
"She pushed open the heavy"
6
"Silas would be at the"
7
"She nodded to the bartender,"
8
"Rory stopped dead, the delivery"
9
"It felt like a lifetime."
10
"Elara had been the sun"
11
"Rory, the quiet observer, content"
12
"They’d sworn they’d conquer London"
13
"Life, as it often did,"
14
"Elara hadn’t aged badly."
15
"The girl with the wild,"
16
"Her hair was a sleek,"
17
"She wore a tailored black"
18
"A single, flawless emerald ring"
19
"She was talking to a"
ratio
0.89
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
91
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
37
technicalSentenceCount
1
matches
0
"Her hair was a sleek, dark bob, pulled back from a face that was all sharp angles and expensive bone structure."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
23
uselessAdditionCount
7
matches
0
"Elara asked, her voice carefully neutral"
1
"she said, her voice sharper than she intended"
2
"Silas said, his voice low"
3
"Rory asked, the question hanging in the air"
4
"Rory said, more to herself than to Silas"
5
"Silas said, his voice soft"
6
"he said, his voice tight"
71.05%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
18
fancyCount
3
fancyTags
0
"Rory stammered (stammer)"
1
"Rory agreed (agree)"
2
"Elara agreed (agree)"
dialogueSentences
38
tagDensity
0.474
leniency
0.947
rawRatio
0.167
effectiveRatio
0.158
78.3152%