NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHTXVQG3EP3HXJ3D9NAB2FBT
Run Details
Model:
Gemini 2.5 Flash
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
10.6s
Cost:
$0.004630
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
92.41%
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)
83.33%
Name drop frequency
(details)
91.18%
Narrator intent-glossing
(details)
47.56%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
69.14%
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)
45.95%
Sentence opener variety
(details)
0.00%
Adverb-first sentence starts
(details)
73.47%
Pronoun-first sentence starts
(details)
19.41%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
41.67%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
78.6034%
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 against the grimy
brickwork of the Soho alley, each drop a tiny drum on the overflowing bins.
Detective Harlow Quinn, her salt-and-pepper
hair slicked dark against her sharp jaw, adjusted the worn leather
watch
on her left wrist. Eighteen years on the force, and the London rain still found new ways to soak her to the bone.
The military precision of her
bearing kept her moving, despite the
chill
seeping into her bones.
A shadow detached itself from
the deeper darkness at the far end of the alley.
Tomás Herrera, his short, curly
dark brown hair plastered to his head, moved with a surprising agility for a man carrying a heavy satchel.
His olive skin, usually a
warm contrast to his crisp shirts, now looked pale under the flickering streetlights.
A Saint Christopher medallion glinted
at his throat, a small
beacon
in the
gloom
. He didn't look back. Quinn knew he wouldn't. This wasn't a casual stroll. This was a flight. "Herrera!" Her voice, a sharp command, cut through the rain. He glanced over his shoulder, his warm brown eyes wide with a fear Quinn had seen too many times.
A flicker of recognition
, a silent plea, passed between them before he broke into a run, his breath pluming in the cold, wet air.
The scar along his left
forearm, a thin white line against his darker skin,
seemed to
twitch as he pumped his arms.
Quinn took off, her heavy
boots splashing through puddles.
The alley opened onto a
wider street, the
familiar
roar of Friday night traffic a temporary disguise.
Herrera wove through the handful
of pedestrians, a dark blur against the brightly lit shop windows.
Quinn kept her distance, the
gap between them never quite closing, never quite widening. She knew this
dance
.
She had led it a
thousand times.
He darted between a black
cab and a double-decker bus, its red paint
gleaming
under the streetlights. Quinn cut closer, risking the honks and shouts of frustrated drivers.
Her gaze never left his
retreating form.
Her mind raced, piecing together
the last few weeks, the whispers, the anomalies. Morris. The memory, sharp and unwelcome, spurred her on. Herrera turned down a narrow side street, a tangle of scaffolding and temporary barriers. Construction zone. Perfect. Quinn followed, her
footsteps
echoing
off the corrugated metal fencing. The sounds of the city faded, replaced by the relentless drumming of the rain. He didn't slow.
His breath hitched in ragged
gasps, but he kept moving, his pace relentless. Quinn noted the small details: the way he favoured his left side, a subtle stiffening, the precise, almost desperate grip on his satchel. Not just running from the law. Running from something else. Something he carried.
He rounded a corner, disappearing
behind a stack of sandbags. Quinn pushed harder, her lungs burning. The street opened into a small, ill-lit square, dominated by an old, abandoned Tube station.
Its rusted iron gates hung
ajar, a black
maw
in the urban landscape. Herrera didn't hesitate.
He plunged into the darkness
of the station entrance. Quinn reached the threshold, the
warmth
of the humid underground air a
stark
contrast to the biting cold of the street. Inside, the darkness deepened. The air smelled of damp earth and something else, something metallic and sharp, like ozone after a lightning strike. A lone, flickering bulb hung from a frayed wire far down the platform, casting long,
wavering
shadows. The tracks stretched into both directions, disappearing into tunnels that promised only deeper concealment. Herrera, a hunched figure against the faint light, stood by the edge of the platform, glancing between the tunnels.
He looked like a man
caught between two abysses. Quinn stepped into the station, her boots grating on loose gravel. "It's over, Herrera."
He spun, his features etched
with despair. His eyes, usually so kind, now held a frantic desperation. "You don't understand." His voice, raw and strained, carried a plea. "This isn't a place for you." "A place where you
suddenly
disappear into the ground?" Quinn scoffed, moving
slowly
along the platform, her hand resting on the holster at her hip. The military precision returned, every movement
measured
, deliberate. "Start explaining, or we do this the hard way."
He shook his head, a
single, definitive motion. "There's no explaining this. Not here. Not to you."
He glanced down the right
tunnel, then back at her, his lips pressed into a thin line. "You shouldn't be here. It's dangerous." "You went in first." She kept her voice even, a calm counterpoint to the growing
tension
. "So tell me, what makes it so dangerous, Tomás?" He swallowed, his gaze darting around the cavernous space. "Things... things you don't believe in. Things the Met doesn't account for." He shifted his
weight
, his eyes lingering on a small, almost imperceptible gap between the platform and the tunnel wall. Quinn saw it then, a faint, almost ghostly light emanating from the gap.
Not the cold, artificial glow of a forgotten utility light, but something warmer, stranger
. A thrumming sensation
vibrated
through the soles of her boots. The air, already thick with the scent of damp earth, now carried a faint, sweet smell, like bruised petals. "What is that?"
she asked, her voice dropping, a raw edge to her tone
. Morris's unexplained partner's death, the strange details surrounding it, surfaced unbidden. Her gut tightened. Herrera didn't answer. He took a hesitant step towards the glowing fissure, then looked back at her, his expression a mixture of fear and
resolve
. "You have to stay back. Please." He disappeared into the opening. The light
pulsed
, then faded, leaving behind only the
oppressive
gloom
of the abandoned station and the distant sound of the rain. Quinn stood alone on the platform. The cold, damp air pressed in on her. The thrumming sensation intensified, a low hum beneath the ground. Her partner died three years ago, under circumstances the police had declared accidental, but Quinn knew better. She felt the
echoes
of that case now, in the strange light, in Herrera’s desperate flight. She reached the mouth of the fissure. It was a narrow, jagged tear in the concrete, barely wide enough for a man to slip through sideways. Beyond it, a faint, iridescent light
pulsed
, painting the rough-hewn stone walls with shifting colours. From within, she heard a muffled murmur, a low hum of voices, a strange mix of languages she didn’t recognize. The sweet, bruised-petal scent strengthened, cut with the sharp tang of something metallic. This wasn't a hidden door to a squatter's den. This was something else entirely. The air beyond the fissure felt alive, vibrant, almost
electric
. She
felt a prickle
of alarm, a deep, primal unease. She could call for backup. Wait for the cavalry, let the uniformed officers deal with whatever lay beyond. But the thought, once a natural instinct, now
felt like a surrender
. Morris. His face flashed in her mind, a ghost of a smile. She had promised him,
not aloud, but in the silent chambers of her heart
, that she would find answers. She stared into the pulsating light. Every instinct screamed at her to retreat, to follow protocol, to stay within the
familiar
boundaries of her world. But every memory, every unresolved question, every phantom
echo
of a partner lost, urged her forward. The Metropolitan Police didn't have a manual for this. No rulebook covered iridescent fissures in abandoned Tube stations. The murmur of voices grew louder, a strange, disjointed
symphony
. An
otherworldly
music, faint but resonant, drifted from within, a melody unlike anything she had ever heard. The scent of bruised petals became almost intoxicating, weaving with the sharp, metallic tang. She made her choice. With a deep breath, Quinn squeezed through the narrow opening, leaving the mundane world of endless rain and concrete behind her. The fissure closed behind her with a soft sigh.
created_at
"2026-02-19T12:26:40.52Z"
2/19/2026, 12:26:40 PM
model
"google/gemini-2.5-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
453
moderation_latency
(null)
generation_time
10612
tokens_prompt
1140
tokens_completion
2022
native_tokens_prompt
1042
native_tokens_completion
1727
native_tokens_completion_images
0
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
0.0046301
router
(null)
provider_responses
0
endpoint_id
"16c01e26-9b91-4d22-b487-ed35634b017d"
is_byok
false
latency
453
model_permaslug
"google/gemini-2.5-flash"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771504000-mzn1uDzmvY9m9uAe3mE0"
upstream_id
(null)
total_cost
0.0046301
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
6
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
13
tagDensity
0.462
leniency
0.923
rawRatio
0
effectiveRatio
0
92.41%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1318
totalAiIsmAdverbs
2
found
0
adverb
"suddenly"
count
1
1
adverb
"slowly"
count
1
highlights
0
"suddenly"
1
"slowly"
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
1318
totalAiIsms
31
found
0
word
"chill"
count
1
1
word
"beacon"
count
1
2
word
"gloom"
count
2
3
word
"flicker"
count
1
4
word
"familiar"
count
2
5
word
"dance"
count
1
6
word
"gleaming"
count
1
7
word
"raced"
count
1
8
word
"perfect"
count
1
9
word
"footsteps"
count
1
10
word
"echoing"
count
1
11
word
"maw"
count
1
12
word
"warmth"
count
1
13
word
"stark"
count
1
14
word
"wavering"
count
1
15
word
"etched"
count
1
16
word
"measured"
count
1
17
word
"tension"
count
1
18
word
"weight"
count
1
19
word
"vibrated"
count
1
20
word
"resolve"
count
1
21
word
"pulsed"
count
2
22
word
"oppressive"
count
1
23
word
"echoes"
count
1
24
word
"electric"
count
1
25
word
"echo"
count
1
26
word
"symphony"
count
1
27
word
"otherworldly"
count
1
highlights
0
"chill"
1
"beacon"
2
"gloom"
3
"flicker"
4
"familiar"
5
"dance"
6
"gleaming"
7
"raced"
8
"perfect"
9
"footsteps"
10
"echoing"
11
"maw"
12
"warmth"
13
"stark"
14
"wavering"
15
"etched"
16
"measured"
17
"tension"
18
"weight"
19
"vibrated"
20
"resolve"
21
"pulsed"
22
"oppressive"
23
"echoes"
24
"electric"
25
"echo"
26
"symphony"
27
"otherworldly"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"flicker of emotion"
count
1
highlights
0
"A flicker of recognition"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
2
narrationSentences
105
matches
0
"d with despair"
1
"felt a prickle"
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
1
narrationSentences
105
filterMatches
0
"watch"
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
111
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
1312
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
5
unquotedAttributions
0
matches
(empty)
83.33%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
36
wordCount
1232
uniqueNames
12
maxNameDensity
1.3
worstName
"Quinn"
maxWindowNameDensity
2.5
worstWindowName
"Quinn"
discoveredNames
Soho
1
Harlow
1
Quinn
16
London
1
Herrera
7
Saint
1
Christopher
1
Friday
1
Tube
2
Morris
3
Metropolitan
1
Police
1
persons
0
"Harlow"
1
"Quinn"
2
"Herrera"
3
"Saint"
4
"Christopher"
5
"Morris"
6
"Police"
places
0
"Soho"
1
"London"
globalScore
0.851
windowScore
0.833
91.18%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
85
glossingSentenceCount
2
matches
0
"looked like a man caught between two abys"
1
"felt like a surrender"
47.56%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
2
per1kWords
1.524
wordCount
1312
matches
0
"Not the cold, artificial glow of a forgotten utility light, but something warmer, stranger"
1
"not aloud, but in the silent chambers of her heart"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
111
matches
(empty)
69.14%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
28
mean
46.86
std
18.37
cv
0.392
sampleLengths
0
75
1
88
2
10
3
65
4
67
5
57
6
41
7
52
8
44
9
56
10
59
11
14
12
34
13
42
14
40
15
25
16
41
17
56
18
28
19
31
20
27
21
57
22
74
23
34
24
61
25
59
26
41
27
34
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
105
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
174
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
111
ratio
0
matches
(empty)
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1238
adjectiveStacks
1
stackExamples
0
"small, ill-lit square,"
adverbCount
35
adverbRatio
0.02827140549273021
lyAdverbCount
11
lyAdverbRatio
0.008885298869143781
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
111
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
111
mean
11.82
std
6.48
cv
0.548
sampleLengths
0
19
1
21
2
19
3
16
4
15
5
24
6
18
7
14
8
4
9
4
10
5
11
4
12
10
13
19
14
24
15
22
16
9
17
17
18
16
19
14
20
4
21
7
22
17
23
11
24
7
25
13
26
1
27
8
28
14
29
2
30
1
31
10
32
14
33
3
34
13
35
23
36
6
37
4
38
3
39
10
40
6
41
15
42
13
43
3
44
9
45
21
46
4
47
19
48
17
49
14
45.95%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
9
diversityRatio
0.32432432432432434
totalSentences
111
uniqueOpeners
36
0.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
0
totalSentences
101
matches
(empty)
ratio
0
73.47%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
37
totalSentences
101
matches
0
"His olive skin, usually a"
1
"He didn't look back."
2
"Her voice, a sharp command,"
3
"He glanced over his shoulder,"
4
"She knew this dance."
5
"She had led it a"
6
"He darted between a black"
7
"Her gaze never left his"
8
"Her mind raced, piecing together"
9
"He didn't slow."
10
"His breath hitched in ragged"
11
"He rounded a corner, disappearing"
12
"Its rusted iron gates hung"
13
"He plunged into the darkness"
14
"He looked like a man"
15
"He spun, his features etched"
16
"His eyes, usually so kind,"
17
"His voice, raw and strained,"
18
"He shook his head, a"
19
"He glanced down the right"
ratio
0.366
19.41%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
89
totalSentences
101
matches
0
"Rain lashed against the grimy"
1
"Detective Harlow Quinn, her salt-and-pepper"
2
"The military precision of her"
3
"A shadow detached itself from"
4
"Tomás Herrera, his short, curly"
5
"His olive skin, usually a"
6
"A Saint Christopher medallion glinted"
7
"He didn't look back."
8
"Quinn knew he wouldn't."
9
"This wasn't a casual stroll."
10
"This was a flight."
11
"Her voice, a sharp command,"
12
"He glanced over his shoulder,"
13
"A flicker of recognition, a"
14
"The scar along his left"
15
"Quinn took off, her heavy"
16
"The alley opened onto a"
17
"Herrera wove through the handful"
18
"Quinn kept her distance, the"
19
"She knew this dance."
ratio
0.881
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
101
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
58
technicalSentenceCount
0
matches
(empty)
41.67%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
6
uselessAdditionCount
1
matches
0
"she asked, her voice dropping, a raw edge to her tone"
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
1
fancyCount
0
fancyTags
(empty)
dialogueSentences
13
tagDensity
0.077
leniency
0.154
rawRatio
0
effectiveRatio
0
78.6034%