NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY8JKSPTAZ69Q399GHBS0NN
Run Details
Model:
Gemma 3 12B
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
44.9s
Cost:
$0.000254
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
53.66%
AI-ism adverb frequency
(details)
80.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
19.97%
AI-ism word frequency
(details)
66.67%
Cliché density
(details)
100.00%
Emotion telling (show vs. tell)
(details)
78.51%
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)
26.71%
Em-dash & semicolon overuse
(details)
98.17%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
66.40%
Sentence opener variety
(details)
66.67%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
50.00%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
25.00%
Dialogue tag variety (said vs. fancy)
(details)
74.3915%
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 neon green of The
Raven’s Nest bled into the rain-slicked pavement outside, a sickly glow against the grey London evening.
Rory shivered, pulling her worn
delivery jacket tighter.
Another Golden Empress order, another
scramble through the city’s veins.
She pushed open the heavy
oak door, the
familiar
scent of stale beer, aged wood, and something faintly metallic, like old coins, washing over her. Silas was behind the bar, polishing a glass with a practiced circular motion.
His auburn hair, threaded with
silver, gleamed faintly under the low lighting, and she noticed the slight hitch in his step as he moved, the permanent
reminder
of that Prague operation she’d only ever heard whispers about. “Rory,”
he said, his hazel eyes
crinkling at the corners. “Late run?” “Yu-Fei’s dumplings are always worth the wait,”
she replied, dropping her delivery
bag onto a nearby stool. “Rough night out there. Feels like the whole city's weeping.”
He chuckled, a dry, quiet
sound. “London has a way of doing that. What can I get you?” “Just a pint of something dark.” She leaned against the bar, grateful for the relative
warmth
.
The bar wasn’t busy; a
couple of older men nursing whiskeys in a corner booth, a
solitary
figure hunched over a newspaper. The usual Thursday night crowd.
She took a long swallow
of the stout, the bitter taste settling comfortably at the back of her throat. Then she saw her. Across the room, near the fireplace, a woman
was laughing
.
A low, throaty laugh that
tugged at something deep within Rory’s memory.
The woman turned, her face
illuminated by the flickering light, and Rory felt the pint she’d just drunk abruptly harden in her
stomach
. It was
Elara
.
Elara
Davies.
They hadn’t spoken in fifteen
years. Fifteen years since that summer in Cardiff, since whispered secrets and shared dreams, since… everything.
Rory hadn’t even known if
she was still alive.
Elara
was… different. Gone was the messy, vibrant tangle of auburn curls, replaced with a sleek, sculpted bob the color of polished obsidian.
Her clothes – a tailored
pantsuit of deep indigo – were expensive, impeccable. No trace remained of the vintage dresses and Doc Martens that had defined her.
The hesitant, almost apologetic posture
she’d always carried
was gone
, replaced by a radiating confidence, a stillness that suggested money and power.
She was talking animatedly to
a man in a suit that probably cost more than Rory’s entire flat.
He was handsome, in a
severe, polished way – the kind of man who smiled with his teeth, not his eyes. Rory felt a strange, detached observation settle over her.
It was like looking at
a photograph of someone she used to know, a person from a past life. Silas noticed her staring. “Old acquaintance?”
he asked, his voice low
. Rory nodded, unable to speak. “She seems to have… flourished,”
Silas observed, his gaze following Elara’s
. Flourished. That was one way to put it. Transformed was probably closer to the truth.
Elara
caught Rory’s eye. For a moment, she simply looked, her expression
unreadable
.
Then a slow, almost hesitant
smile spread across her face.
She excused herself from the
man in the suit and
began to
walk toward them. Rory’s heart hammered against her ribs. The crescent-shaped scar on her left wrist
throbbed
, a
familiar
ache triggered by sudden anxiety.
She gripped the pint glass
tighter. “Rory?”
Elara
asked, her voice deeper, more resonant than Rory remembered. There was a slight accent, unfamiliar, layered. Not the Welsh
lilt
of their childhood. “
Elara
,” Rory
managed to
say, the word sounding foreign on her tongue. “It’s been… a long time,”
Elara
said, extending a hand. Her nails were
perfectly
manicured, a deep crimson. Rory shook it, the brief contact sending a jolt through her. “It has,” Rory agreed. “You… you look good.” A pathetic, inadequate compliment.
Elara
’s smile widened. “And you. Still delivering, I see.” There was a slight… amusement in her tone. Not unkind, but… distant. “Pays the bills,” Rory said, forcing a shrug. “What about you? What brings you to The Raven’s Nest?” “Business,”
Elara
said, vaguely. “I’m in London for a conference. A rather… lucrative conference.” She glanced at her companion, who
seemed to
be engaged in a rather intense conversation on his phone. “Lucrative how?”
Rory pressed, the question escaping before she could filter it
. She immediately regretted it. Too intrusive. Too… Rory.
Elara
’s
eyes narrowed
slightly
. “That’s not
really
something I discuss with old acquaintances, Rory.” The air thickened. The easy familiarity of their youth, a phantom limb, vanished. Rory felt a
pang
of something sharp and bitter— regret, perhaps? “Right,” Rory mumbled, taking another gulp of her stout. “Sorry.” “It’s lovely to see you,”
Elara
said, her voice
carefully
neutral. “It
really
is. But I must be going. This conference…” “So, you’re… what do you do now?” Rory asked, clinging to the remnants of their past connection.
Elara
paused, considering. “I’m in asset management.” Asset management. Rory pictured spreadsheets, boardrooms, power lunches. A world away from the art history lectures and late-night talks about escaping Cardiff. “Right,” Rory said again, feeling
utterly
adrift. “That sounds… important.” “It is,”
Elara
said, her smile brittle. “Very important. It requires a certain… dedication.” There was a silent beat. Rory wondered if
Elara
, too, felt the
weight
of the years, the chasm that had opened up between them. “Do you… ever go back to Cardiff?”
Rory asked, desperate to find some common ground
.
Elara
’s expression clouded over briefly, a
flicker
of something
unreadable
in her eyes. “Not
really
. It’s… small. I’ve moved on.” The words
hung in the air
, cold and definitive. A
stark
declaration of their divergent paths. Rory
felt a shiver
crawl
down her spine
, unrelated to the London rain. “I see,” Rory said quietly.
Elara
glanced at her
watch
. “Well, I
really
must run. It was… nice seeing you.” “You too,”
Rory said, the words lacking any genuine warmth
.
Elara
offered a final, formal nod and turned to rejoin her companion. As she walked away, Rory noticed a flash of gold on her finger – a large,
intricate
ring. A ring that screamed wealth and status, a symbol of a life Rory couldn't even
begin to
imagine. Rory watched her go, a dull ache in her chest.
She thought of their shared
dreams, their whispered promises. Promises of changing the world, of escaping the mundane.
Elara
had escaped, alright. But had she changed the world, or simply traded one set of expectations for another? Silas cleared his throat. "She's a striking woman,”
he said, carefully
. Rory didn't respond. She stared into the dark
depths
of her stout, the bubbles rising like lost memories. The rain continued to beat against the windows, a relentless, melancholic rhythm. She thought of Evan, of why she’d left Cardiff in the first place. Of the quiet, simple life she’d built for herself in London. It wasn't glamorous. It wasn't lucrative. But it was hers. And
suddenly
, feeling the
weight
of fifteen years and the vast gulf between them, being Rory Carter, delivery person, felt a lot better than being
Elara
Davies, asset manager.
created_at
"2026-02-20T19:31:39.461Z"
2/20/2026, 7:31:39 PM
model
"google/gemma-3-12b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
415
moderation_latency
(null)
generation_time
44821
tokens_prompt
892
tokens_completion
1962
native_tokens_prompt
850
native_tokens_completion
1690
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
0.0002537
router
(null)
provider_responses
0
endpoint_id
"eb06dc92-5a16-47ec-a776-6ef956457c47"
id
"chatcmpl-RbNDbTUdetBs56FpeSHzEoGk"
is_byok
false
latency
53
model_permaslug
"google/gemma-3-12b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771615899-qtXvnpZNu80cxhAuSLfu"
upstream_id
"chatcmpl-RbNDbTUdetBs56FpeSHzEoGk"
total_cost
0.0002537
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
22
adverbTagCount
2
adverbTags
0
"Rory said again [again]"
1
"Rory said quietly [quietly]"
dialogueSentences
36
tagDensity
0.611
leniency
1
rawRatio
0.091
effectiveRatio
0.091
53.66%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1187
totalAiIsmAdverbs
11
found
0
adverb
"perfectly"
count
1
1
adverb
"slightly"
count
1
2
adverb
"really"
count
4
3
adverb
"carefully"
count
2
4
adverb
"utterly"
count
1
5
adverb
"very"
count
1
6
adverb
"suddenly"
count
1
highlights
0
"perfectly"
1
"slightly"
2
"really"
3
"carefully"
4
"utterly"
5
"very"
6
"suddenly"
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)
19.97%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1187
totalAiIsms
19
found
0
word
"familiar"
count
2
1
word
"reminder"
count
1
2
word
"warmth"
count
2
3
word
"solitary"
count
1
4
word
"stomach"
count
1
5
word
"unreadable"
count
2
6
word
"throbbed"
count
1
7
word
"lilt"
count
1
8
word
"pang"
count
1
9
word
"weight"
count
2
10
word
"flicker"
count
1
11
word
"stark"
count
1
12
word
"down her spine"
count
1
13
word
"intricate"
count
1
14
word
"depths"
count
1
highlights
0
"familiar"
1
"reminder"
2
"warmth"
3
"solitary"
4
"stomach"
5
"unreadable"
6
"throbbed"
7
"lilt"
8
"pang"
9
"weight"
10
"flicker"
11
"stark"
12
"down her spine"
13
"intricate"
14
"depths"
66.67%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
2
maxInWindow
2
found
0
label
"eyes widened/narrowed"
count
1
1
label
"hung in the air"
count
1
highlights
0
"eyes narrowed"
1
"hung in the air"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
1
narrationSentences
111
matches
0
"felt a shiver"
78.51%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
4
narrationSentences
111
filterMatches
0
"watch"
hedgeMatches
0
"began to"
1
"managed to"
2
"seemed to"
3
"begin to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
123
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
37
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1188
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
21
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
74
wordCount
1015
uniqueNames
18
maxNameDensity
3.05
worstName
"Rory"
maxWindowNameDensity
6
worstWindowName
"Rory"
discoveredNames
Raven
1
Nest
1
London
3
Golden
1
Empress
1
Prague
1
Thursday
1
Rory
31
Elara
19
Davies
2
Cardiff
3
Doc
1
Martens
1
Flourished
1
Welsh
1
Evan
1
Carter
1
Silas
4
persons
0
"Raven"
1
"Nest"
2
"Rory"
3
"Elara"
4
"Davies"
5
"Evan"
6
"Carter"
7
"Silas"
places
0
"London"
1
"Prague"
2
"Cardiff"
globalScore
0
windowScore
0
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
70
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.842
wordCount
1188
matches
0
"Not unkind, but…"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
123
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
48
mean
24.75
std
15.62
cv
0.631
sampleLengths
0
64
1
50
2
12
3
27
4
18
5
43
6
23
7
45
8
5
9
30
10
72
11
39
12
28
13
11
14
5
15
11
16
15
17
38
18
27
19
25
20
12
21
29
22
12
23
21
24
18
25
32
26
20
27
14
28
24
29
10
30
21
31
17
32
7
33
22
34
10
35
14
36
24
37
15
38
20
39
29
40
5
41
15
42
10
43
48
44
47
45
11
46
54
47
39
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
111
matches
0
"was gone"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
2
totalVerbs
172
matches
0
"was laughing"
1
"was talking"
26.71%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
5
semicolonCount
1
flaggedSentences
5
totalSentences
123
ratio
0.041
matches
0
"The bar wasn’t busy; a couple of older men nursing whiskeys in a corner booth, a solitary figure hunched over a newspaper."
1
"Her clothes – a tailored pantsuit of deep indigo – were expensive, impeccable."
2
"He was handsome, in a severe, polished way – the kind of man who smiled with his teeth, not his eyes."
3
"Rory felt a pang of something sharp and bitter— regret, perhaps?"
4
"As she walked away, Rory noticed a flash of gold on her finger – a large, intricate ring."
98.17%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1014
adjectiveStacks
0
stackExamples
(empty)
adverbCount
42
adverbRatio
0.04142011834319527
lyAdverbCount
21
lyAdverbRatio
0.020710059171597635
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
123
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
123
mean
9.66
std
6.58
cv
0.681
sampleLengths
0
21
1
8
2
10
3
25
4
13
5
37
6
10
7
2
8
17
9
10
10
6
11
12
12
16
13
22
14
5
15
19
16
4
17
10
18
12
19
23
20
3
21
2
22
6
23
14
24
1
25
9
26
2
27
1
28
20
29
13
30
14
31
22
32
18
33
21
34
9
35
19
36
4
37
7
38
5
39
11
40
1
41
7
42
7
43
4
44
9
45
10
46
15
47
6
48
15
49
6
66.40%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
5
diversityRatio
0.42276422764227645
totalSentences
123
uniqueOpeners
52
66.67%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
2
totalSentences
100
matches
0
"Then she saw her."
1
"Then a slow, almost hesitant"
ratio
0.02
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
25
totalSentences
100
matches
0
"She pushed open the heavy"
1
"His auburn hair, threaded with"
2
"he said, his hazel eyes"
3
"she replied, dropping her delivery"
4
"He chuckled, a dry, quiet"
5
"She leaned against the bar,"
6
"She took a long swallow"
7
"It was Elara."
8
"They hadn’t spoken in fifteen"
9
"Her clothes – a tailored"
10
"She was talking animatedly to"
11
"He was handsome, in a"
12
"It was like looking at"
13
"he asked, his voice low"
14
"She excused herself from the"
15
"She gripped the pint glass"
16
"Her nails were perfectly manicured,"
17
"She glanced at her companion,"
18
"She immediately regretted it."
19
"She thought of their shared"
ratio
0.25
50.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
82
totalSentences
100
matches
0
"The neon green of The"
1
"Rory shivered, pulling her worn"
2
"Another Golden Empress order, another"
3
"She pushed open the heavy"
4
"Silas was behind the bar,"
5
"His auburn hair, threaded with"
6
"he said, his hazel eyes"
7
"she replied, dropping her delivery"
8
"He chuckled, a dry, quiet"
9
"She leaned against the bar,"
10
"The bar wasn’t busy; a"
11
"The usual Thursday night crowd."
12
"She took a long swallow"
13
"A low, throaty laugh that"
14
"The woman turned, her face"
15
"It was Elara."
16
"They hadn’t spoken in fifteen"
17
"Rory hadn’t even known if"
18
"Her clothes – a tailored"
19
"The hesitant, almost apologetic posture"
ratio
0.82
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
100
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
38
technicalSentenceCount
1
matches
0
"No trace remained of the vintage dresses and Doc Martens that had defined her."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
22
uselessAdditionCount
11
matches
0
"he said, his hazel eyes crinkling at the corners"
1
"he asked, his voice low"
2
"Silas observed, his gaze following Elara’s"
3
"Elara asked, her voice deeper, more resonant than Rory remembered"
4
"Rory managed, the word sounding foreign on her tongue"
5
"Elara said, vaguely"
6
"Rory pressed, the question escaping before she could filter it"
7
"Elara said, her voice carefully neutral"
8
"Rory asked, desperate to find some common ground"
9
"Rory said, the words lacking any genuine warmth"
10
"he said, carefully"
25.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
20
fancyCount
5
fancyTags
0
"Silas observed (observe)"
1
"Rory managed (manage)"
2
"Rory agreed (agree)"
3
"Rory pressed (press)"
4
"Rory mumbled (mumble)"
dialogueSentences
36
tagDensity
0.556
leniency
1
rawRatio
0.25
effectiveRatio
0.25
74.3915%