NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-25-01KJ953W242RCT9HRMDY5W4R76
Run Details
Model:
Gemini 2.5 Flash (Reasoning)
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
14.6s
Cost:
$0.007385
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
0.00%
Adverbs in dialogue tags
(details)
100.00%
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)
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)
100.00%
Name drop frequency
(details)
100.00%
Narrator intent-glossing
(details)
22.38%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
95.50%
Paragraph length variance
(details)
100.00%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
49.69%
Em-dash & semicolon overuse
(details)
100.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
50.36%
Sentence opener variety
(details)
36.63%
Adverb-first sentence starts
(details)
83.74%
Pronoun-first sentence starts
(details)
14.95%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
77.92%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
0.00%
Dialogue tag variety (said vs. fancy)
(details)
71.0388%
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="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="4417" name="Tomás Herrera" aliases="Tommy, Tomás, Herrera" pronouns="he/him" species="Human" storyRole="Support"> <eyeColor>warm brown</eyeColor> <hair>short curly dark brown</hair> <height>5'10"</height> <age>29</age> <skinTone>olive skin</skinTone> <scar>scar running along his left forearm from a knife attack</scar> <medallion>Saint Christopher medallion around his neck</medallion> <birthplace>Seville, Spain</birthplace> <description>A former paramedic who provides off-the-books medical care for the clique.</description> <backstory>Born in Seville, Spain. He moved to London to work for the NHS but lost his license after administering unauthorized treatments to supernatural patients.</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> <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> </codex> Continue the story using the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the thriller genre. A detective is pursuing a suspect through rain-soaked city streets at night. The chase takes them from the street level down into an underground market. The detective must decide whether to follow the suspect into unfamiliar and potentially dangerous territory. 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
Rain lashed the grime-caked windows
of the passing black cab, distorting the Soho night into smears of neon.
Detective Harlow Quinn’s breath hitched
in her throat, a sharp, cold jab of air.
She spotted him, a flicker
of dark hair, a
fleeting
glimpse of olive skin, weaving through the human river on Old Compton Street. Tomás Herrera.
He moved with a dancer’s
grace, cutting angles through the throngs of theatre-goers and late-night revelers as if the crowd parted for him alone.
Quinn pushed off the taxi’s
door with a grunt, her military-precise bearing momentarily discarded for raw, unbridled pursuit.
Her boots slapped against slick
pavement, the rhythm a frantic heartbeat against the urban din.
Rain flattened her closely cropped
salt-and-pepper hair, plastered her trench coat to her frame.
The worn leather watch on
her left wrist, a ghost of her former partner, caught the glare of a Chinese lantern overhead. “Herrera!”
Her voice ripped through the
downpour, a futile bark against the city’s roar.
Tomás did not flinch, did
not break his stride.
He glanced back, a flash
of warm brown eyes, fear
etched
around them, before plunging into a narrow alleyway beside a blinking green neon sign that read "The Raven's Nest." The sign cast an eerie glow on the wet brick.
Quinn swerved, dodging a staggering
pedestrian, her shoulder knocking hard against a lamppost. Pain shot up her arm, a white-hot spike that she ignored.
Herrera knew these backstreets, these
veins of hidden London.
She swore he moved without
effort, a shadow ahead of her, while she fought every step, every breath. Her lungs burned, a raw, aching fire.
He rounded a corner, a
quick blur of motion in the dim light.
Quinn followed, her gaze already
scanning
for his next move.
The alley reeked of stale
beer and damp earth.
A stray cat darted from
beneath a overflowing skip, a sudden,
fleeting
distraction that almost cost her. “Stop now, Herrera!”
Her voice was hoarse, shredded
by exertion and the insistent rain. The chase had become a primal hunt, her focus narrowed to the retreating figure. Each stride, each muscle clench, served one purpose: close the gap. He didn't acknowledge her. He merely pushed harder. The city lights
began to
thin as they veered north, away from the vibrant heart of Soho. The buildings turned rougher, their facades grimy, unkempt. Puddles grew into small, murky lakes that splashed around Quinn’s ankles, soaking her trousers. Tomás vaulted over a low concrete barrier, a fluid, practiced motion. Quinn mirrored him, her muscles protesting.
She landed hard, jarring her
knees before finding her footing. Ahead, a decrepit iron gate, half-off its hinges, marked the entrance to a forgotten service road.
He ducked under a sagging
archway, the darkness swallowing him whole. Quinn pushed through the gate, its rusty shriek tearing at the night. The service road snaked downwards, the air growing heavier, colder. The sounds of traffic faded, replaced by the persistent drip of unseen water. The concrete walls on either side were slick with moss, dark stains blooming like ancient bruises.
She tasted copper in her
mouth. Then she saw it. Not an exit. A gaping
maw
. The entrance to an abandoned Tube station.
Its gaping maw consumed the
faint light, a black hole beneath the city’s skin. The rusted, peeling enamel sign proudly declared ‘CAMDEN TOWN’ in faded, almost illegible letters, a ghost of purpose. Tomás, now little more than a silhouette, slipped through a gap in a chain-link fence, disappearing into its
depths
. Quinn skidded to a halt at the edge of the descent. A
chill
, unlike the rain’s biting cold, seeped into her bones. The air grew still, heavy with the scent of damp earth and something else—something metallic, like old blood and ozone. The darkness within
pulsed
, a living entity. She knew this feeling. The same unsettling dread that had clung to her after Morris’s death, after the world had
fractured
and revealed its true, grotesque edges. This wasn’t just an abandoned station.
It hummed with a different
energy, a discordant note beneath the metropolitan
symphony
. The codex, the cryptic reports she’d filed, the dismissed theories—they all converged here. This place, it
echoed
the impossible. Her mind
raced
. Standard procedure dictated she call for backup, secure the perimeter, wait. But Herrera was inside. And something about this entrance, the deep, unsettling quiet that emanated from it, told her waiting would mean losing him forever.
It also told her that
backup might not even know what they
were looking
for down here. Her sharp jaw tightened. A faint clatter
echoed
from below, perhaps Herrera, perhaps something else entirely. The decision hung in the cold, damp air, heavy and insistent. Every nerve ending screamed caution, every shred of her training warned against it. But the memory of Morris, the unfinished business that gnawed at her, pushed harder. She took a breath, the metallic air scraping her throat. "Bastard,"
she whispered, her voice a low growl
. She lowered herself through the fence, snagging her coat, a harsh tear of fabric ripping through the
silence
. The descent steepened, the concrete steps worn smooth,
treacherous
with slime. Darkness pressed in. She pulled a small, powerful torch from her coat pocket, its beam cutting a
stark
, almost blinding path through the
gloom
. It illuminated a passage hewn
not so much from brick, but from something organic, a twisting tunnel of compacted earth
and rock. Faint,
rhythmic
sounds drifted upwards, a
cacophony
of distant murmurs, clinking metal, and
something like the low thrum of power
. The tunnel opened into a vast cavern. The air hit her, thick with a hundred different smells: incense, damp fur, something sweet and cloying like decay, sharp like burnt sugar. Light,
not from electricity but from countless flickering lamps
and bioluminescent fungi, painted the cavern walls in shifting hues of green and violet. Stalls, carved from rock or crudely assembled wood, lined winding pathways that vanished into the
gloom
. Figures moved through the labyrinthine aisles, not all distinctly human. Their forms shifted, cloaked shapes, grotesque silhouettes, glowing eyes. This was no abandoned Tube station. This was the Veil Market. Her gaze swept an aisle, searching for Herrera. He could be anywhere among this throng, swallowed by the sheer alienness of the place. A stall nearby offered an array of shrunken heads. Another displayed vials of shimmering liquid. A deep, guttural laugh erupted from a shadowy corner,
echoing
off the cavern walls, then faded into the
ceaseless
thrum of the crowd. The bone token entry, the shifting location—this was it. She had followed him into the heart of everything she knew existed but could not explain. The market
vibrated
with a raw, dangerous energy. She tightened her grip on the torch. He was here somewhere.
created_at
"2026-02-25T01:02:49.419Z"
2/25/2026, 1:02:49 AM
model
"google/gemini-2.5-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1434
moderation_latency
(null)
generation_time
14579
tokens_prompt
1140
tokens_completion
2596
native_tokens_prompt
1042
native_tokens_completion
2829
native_tokens_completion_images
0
native_tokens_reasoning
1343
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
0.0073851
router
(null)
provider_responses
0
endpoint_id
"16c01e26-9b91-4d22-b487-ed35634b017d"
is_byok
false
latency
1434
model_permaslug
"google/gemini-2.5-flash"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771981369-qEOZaLBfy8r3S9pq6kkM"
upstream_id
(null)
total_cost
0.0073851
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
4
adverbTagCount
1
adverbTags
0
"He glanced back [back]"
dialogueSentences
4
tagDensity
1
leniency
1
rawRatio
0.25
effectiveRatio
0.25
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1129
totalAiIsmAdverbs
0
found
(empty)
highlights
(empty)
100.00%
AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions
(empty)
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
1129
totalAiIsms
26
found
0
word
"flicker"
count
1
1
word
"fleeting"
count
2
2
word
"etched"
count
1
3
word
"scanning"
count
1
4
word
"maw"
count
2
5
word
"depths"
count
1
6
word
"chill"
count
1
7
word
"pulsed"
count
1
8
word
"fractured"
count
1
9
word
"symphony"
count
1
10
word
"echoed"
count
2
11
word
"raced"
count
1
12
word
"standard"
count
1
13
word
"silence"
count
1
14
word
"treacherous"
count
1
15
word
"stark"
count
1
16
word
"gloom"
count
2
17
word
"rhythmic"
count
1
18
word
"cacophony"
count
1
19
word
"echoing"
count
1
20
word
"ceaseless"
count
1
21
word
"vibrated"
count
1
highlights
0
"flicker"
1
"fleeting"
2
"etched"
3
"scanning"
4
"maw"
5
"depths"
6
"chill"
7
"pulsed"
8
"fractured"
9
"symphony"
10
"echoed"
11
"raced"
12
"standard"
13
"silence"
14
"treacherous"
15
"stark"
16
"gloom"
17
"rhythmic"
18
"cacophony"
19
"echoing"
20
"ceaseless"
21
"vibrated"
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
92
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
1
narrationSentences
92
filterMatches
0
"watch"
hedgeMatches
0
"began to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
92
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
40
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1126
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
5
unquotedAttributions
0
matches
(empty)
100.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
31
wordCount
1107
uniqueNames
14
maxNameDensity
0.72
worstName
"Quinn"
maxWindowNameDensity
2
worstWindowName
"Quinn"
discoveredNames
Soho
2
Harlow
1
Quinn
8
Old
1
Compton
1
Street
1
Herrera
5
Chinese
1
Tomás
4
London
1
Tube
2
Morris
2
Veil
1
Market
1
persons
0
"Harlow"
1
"Quinn"
2
"Herrera"
3
"Tomás"
4
"Morris"
5
"Market"
places
0
"Soho"
1
"Old"
2
"Compton"
3
"Street"
4
"London"
globalScore
1
windowScore
1
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
79
glossingSentenceCount
1
matches
0
"something like the low thrum of power"
22.38%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
2
per1kWords
1.776
wordCount
1126
matches
0
"not so much from brick, but from something organic, a twisting tunnel of compacted earth"
1
"not from electricity but from countless flickering lamps"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
92
matches
(empty)
95.50%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
19
mean
59.26
std
28.7
cv
0.484
sampleLengths
0
81
1
69
2
14
3
49
4
58
5
49
6
39
7
47
8
54
9
57
10
68
11
114
12
60
13
60
14
8
15
95
16
88
17
11
18
105
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
92
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
1
totalVerbs
168
matches
0
"were looking"
49.69%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
3
semicolonCount
0
flaggedSentences
3
totalSentences
92
ratio
0.033
matches
0
"The air grew still, heavy with the scent of damp earth and something else—something metallic, like old blood and ozone."
1
"The codex, the cryptic reports she’d filed, the dismissed theories—they all converged here."
2
"The bone token entry, the shifting location—this was it."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
556
adjectiveStacks
0
stackExamples
(empty)
adverbCount
15
adverbRatio
0.02697841726618705
lyAdverbCount
4
lyAdverbRatio
0.007194244604316547
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
92
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
92
mean
12.24
std
6.47
cv
0.529
sampleLengths
0
18
1
14
2
23
3
2
4
24
5
18
6
15
7
14
8
22
9
14
10
9
11
40
12
13
13
11
14
9
15
18
16
7
17
13
18
10
19
9
20
17
21
14
22
14
23
11
24
4
25
4
26
17
27
8
28
14
29
11
30
6
31
10
32
16
33
11
34
12
35
10
36
13
37
16
38
6
39
4
40
3
41
3
42
7
43
14
44
18
45
19
46
11
47
11
48
20
49
7
50.36%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
7
diversityRatio
0.34782608695652173
totalSentences
92
uniqueOpeners
32
36.63%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
91
matches
0
"Then she saw it."
ratio
0.011
83.74%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
31
totalSentences
91
matches
0
"She spotted him, a flicker"
1
"He moved with a dancer’s"
2
"Her boots slapped against slick"
3
"Her voice ripped through the"
4
"He glanced back, a flash"
5
"She swore he moved without"
6
"Her lungs burned, a raw,"
7
"He rounded a corner, a"
8
"Her voice was hoarse, shredded"
9
"He didn't acknowledge her."
10
"He merely pushed harder."
11
"She landed hard, jarring her"
12
"He ducked under a sagging"
13
"She tasted copper in her"
14
"Its gaping maw consumed the"
15
"She knew this feeling."
16
"It hummed with a different"
17
"Her mind raced."
18
"It also told her that"
19
"Her sharp jaw tightened."
ratio
0.341
14.95%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
81
totalSentences
91
matches
0
"Rain lashed the grime-caked windows"
1
"Detective Harlow Quinn’s breath hitched"
2
"She spotted him, a flicker"
3
"He moved with a dancer’s"
4
"Quinn pushed off the taxi’s"
5
"Her boots slapped against slick"
6
"Rain flattened her closely cropped"
7
"The worn leather watch on"
8
"Her voice ripped through the"
9
"Tomás did not flinch, did"
10
"He glanced back, a flash"
11
"Quinn swerved, dodging a staggering"
12
"Pain shot up her arm,"
13
"Herrera knew these backstreets, these"
14
"She swore he moved without"
15
"Her lungs burned, a raw,"
16
"He rounded a corner, a"
17
"Quinn followed, her gaze already"
18
"The alley reeked of stale"
19
"A stray cat darted from"
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
77.92%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
55
technicalSentenceCount
5
matches
0
"He moved with a dancer’s grace, cutting angles through the throngs of theatre-goers and late-night revelers as if the crowd parted for him alone."
1
"Quinn swerved, dodging a staggering pedestrian, her shoulder knocking hard against a lamppost."
2
"Puddles grew into small, murky lakes that splashed around Quinn’s ankles, soaking her trousers."
3
"The same unsettling dread that had clung to her after Morris’s death, after the world had fractured and revealed its true, grotesque edges."
4
"She pulled a small, powerful torch from her coat pocket, its beam cutting a stark, almost blinding path through the gloom."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
4
uselessAdditionCount
2
matches
0
"Her voice ripped, a futile bark against the city’s roar"
1
"she whispered, her voice a low growl"
0.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
1
fancyCount
1
fancyTags
0
"she whispered (whisper)"
dialogueSentences
4
tagDensity
0.25
leniency
0.5
rawRatio
1
effectiveRatio
0.5
71.0388%