NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHTXKJESEAC22CB0BGGFC63X
Run Details
Model:
Gemini 2.5 Flash
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
8.5s
Cost:
$0.003763
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
85.73%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
4.85%
AI-ism word frequency
(details)
66.67%
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)
16.67%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
63.29%
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)
55.80%
Sentence opener variety
(details)
0.00%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
0.70%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
89.95%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
79.2548%
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, the kind of biting, cold November rain that soaked through clothes and
chilled
to the bone.
Detective Harlow Quinn’s closely cropped
salt-and-pepper hair plastered to her scalp, water streamed down her sharp jaw, blurring the streetlights into distorted halos.
Her breath plumed out in
ragged gasps, each one a struggle against the burn in her lungs.
The worn leather watch on
her left wrist pressed into her skin as she pumped her arms, pursuing the figure ahead.
Tomás Herrera, a blur of
dark clothing, wove through overflowing bins and discarded takeaway boxes.
He moved with a speed
Quinn would not have expected from a civilian. She’d underestimated him.
A grave error she wouldn’t
repeat.
The alley opened onto a
wider street, the neon glow of “The Raven’s Nest” a lurid splash of green against the grey.
Herrera didn’t hesitate, hooking a
sharp left, disappearing around the corner.
Quinn pushed harder, her military
precision bearing her forward despite the fatigue.
Her boots skidded on slick
pavement. She rounded the corner. Herrera had vanished. She
scanned
the street.
The rain hammered down, creating
a shimmering veil, distorting her view.
A flash of movement, a
dark coat disappearing into a narrow gap between a boarded-up shop and a grimy pub.
An access point she hadn't
charted.
She darted towards it, the
air thick with the smell of stale beer and damp earth.
The gap was barely wide
enough for her shoulders, a tunnel of grime and shadow.
She squeezed through, her clothes
snagging on unseen protrusions. The space opened onto a deserted stretch of cobbled backstreet, lit by a single flickering streetlamp that cast long,
dancing
shadows. Herrera was a hundred yards ahead, a dark silhouette against the dull glow of streetlights in the distance.
He looked back, his face
a pale oval, a moment of hesitation before he accelerated. “Police! Stop!” Quinn’s voice was hoarse, swallowed by the drumming rain. Herrera ignored her, his short curly dark brown hair plastered wetly to his head.
He sprinted, his olive skin
gleaming
as the streetlamp caught him. The Saint Christopher medallion around his neck swung wildly, catching the light like a tiny, erratic pendulum. He wasn’t a street rat,
not really, but he moved like one, agile
and quick. The street ended abruptly at a high brick wall. No escape. Quinn felt a surge of triumph, the chase nearing its conclusion. But Herrera didn’t falter. He slid to a halt, hands braced against the wall. A loose brick, hidden in the perpetual
gloom
, popped inwards, revealing a narrow opening. An old service entrance, long forgotten.
He disappeared inside, a ghost
fading into the stone. Quinn reached the wall seconds later, panting, her hands pressed against the cold, wet brick. She found the loose brick, pushed, and felt a rush of stale, damp air. The opening was a dark
maw
, a staircase spiralling downwards into absolute blackness. No light. No sound except the distant rumble of the Tube and the unending downpour above.
She drew her sidearm, the
cold steel a
familiar
weight
in her hand. The glow of her phone’s torch cut through the
gloom
, revealing rough concrete steps, slick with moisture. A faint metallic tang, like old blood and rust,
hung in the air
. This wasn’t an ordinary cellar. The air grew heavy, thick with an almost
palpable
silence
, broken only by the drip of water. Quinn descended
cautiously
, her training kicking in, each step deliberate. The staircase seemed endless, twisting and turning, disorienting her. The concrete gave way to rough-hewn earth, the air growing colder, carrying a faint
whisper
of… something unidentifiable. A faint, distant hum, like a forgotten city breathing.
She reached an archway, shrouded
in shadow. Herrera’s
footsteps
, faint but distinct,
echoed
from beyond. She moved through the arch, past the crumbling remains of what looked like an old turnstile, forgotten for decades. The space opened into a vast chamber, far larger than she expected. An abandoned Tube station, long disused. But it wasn’t empty. A
kaleidoscope
of glowing lanterns illuminated a
chaotic
scene. Stalls crafted from salvaged wood and rusted metal lined a wide platform. Shadows danced across the vaulted ceiling, lost in the cavernous space. Strange, aromatic smoke drifted from braziers, mingling with the scent of spices and something else, something wild and untamed. Faces, human and not-quite-human, moved through the throng. Figures wrapped in heavy cloaks, some with eyes that gleamed with unnatural light, haggled over goods on display. Trinkets that
pulsed
with a faint, internal glow. Vials filled with swirling, iridescent liquids. A low murmur of voices, a confluence of languages she didn’t recognize, filled the air, a constant hum that
vibrated
through the
very
ground. This was the Veil Market.
She’d heard whispers, the kind
of urban legends dismissed by rational minds. Stories from street informants, the ones about impossible goods and shadowy figures. A place that moved locations every full moon, accessible only with a bone token. Herrera, standing by a stall laden with wicked-looking blades and strange leather-bound books, spotted her. His warm brown
eyes widened
, alarm replacing the exhaustion.
He had thought he was
safe. A skeletal hand, its fingers impossibly long, reached out from a nearby stall, adorned with shimmering, unidentifiable fabrics. It gestured towards Quinn, its owner a hunched figure cloaked in shadows, a skull-like mask obscuring its face. A low, guttural growl rumbled through the market. Heads turned. Dozens of eyes, some human, some not, fixed on her. A police uniform. An outsider. Tomas spun on his heel, merging with the crowd, his olive skin disappearing
amidst
the swirling bodies. Quinn had a moment, a split second to decide. Her priority, Tomás Herrera, was a man she needed to question about his involvement in a string of disappearances. He possessed information, information that could lead her to answers. Answers to DS Morris and the truth behind his death. But following him further meant diving headfirst into this bizarre, dangerous world. A world she didn't understand, a
world that seemed to be actively hostile
. One against many. She was deep within unfamiliar territory, deep in the earth, far from backup, far from anything resembling law and order. A world without rules. Except theirs.
created_at
"2026-02-19T12:22:13.222Z"
2/19/2026, 12:22:13 PM
model
"google/gemini-2.5-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
359
moderation_latency
(null)
generation_time
8497
tokens_prompt
1140
tokens_completion
1645
native_tokens_prompt
1042
native_tokens_completion
1380
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
0.0037626
router
(null)
provider_responses
0
endpoint_id
"16c01e26-9b91-4d22-b487-ed35634b017d"
is_byok
false
latency
359
model_permaslug
"google/gemini-2.5-flash"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771503733-9cqxjB9eyx7npbO1l6U1"
upstream_id
(null)
total_cost
0.0037626
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
2
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
2
tagDensity
1
leniency
1
rawRatio
0
effectiveRatio
0
85.73%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1051
totalAiIsmAdverbs
3
found
0
adverb
"really"
count
1
1
adverb
"cautiously"
count
1
2
adverb
"very"
count
1
highlights
0
"really"
1
"cautiously"
2
"very"
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)
4.85%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1051
totalAiIsms
20
found
0
word
"chilled"
count
1
1
word
"grave"
count
1
2
word
"scanned"
count
1
3
word
"dancing"
count
1
4
word
"gleaming"
count
1
5
word
"gloom"
count
2
6
word
"maw"
count
1
7
word
"familiar"
count
1
8
word
"weight"
count
1
9
word
"palpable"
count
1
10
word
"silence"
count
1
11
word
"whisper"
count
1
12
word
"footsteps"
count
1
13
word
"echoed"
count
1
14
word
"kaleidoscope"
count
1
15
word
"chaotic"
count
1
16
word
"pulsed"
count
1
17
word
"vibrated"
count
1
18
word
"amidst"
count
1
highlights
0
"chilled"
1
"grave"
2
"scanned"
3
"dancing"
4
"gleaming"
5
"gloom"
6
"maw"
7
"familiar"
8
"weight"
9
"palpable"
10
"silence"
11
"whisper"
12
"footsteps"
13
"echoed"
14
"kaleidoscope"
15
"chaotic"
16
"pulsed"
17
"vibrated"
18
"amidst"
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 widened"
1
"hung in the air"
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
"seemed 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
26
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1043
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
2
unquotedAttributions
0
matches
(empty)
100.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
30
wordCount
1038
uniqueNames
12
maxNameDensity
0.87
worstName
"Quinn"
maxWindowNameDensity
2
worstWindowName
"Herrera"
discoveredNames
Soho
1
November
1
Harlow
1
Quinn
9
Herrera
9
Saint
1
Christopher
1
Tube
2
Veil
1
Market
1
Tomás
2
Morris
1
persons
0
"Harlow"
1
"Quinn"
2
"Herrera"
3
"Saint"
4
"Christopher"
5
"Veil"
6
"Tomás"
7
"Morris"
places
0
"Soho"
1
"Market"
globalScore
1
windowScore
1
16.67%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
75
glossingSentenceCount
4
matches
0
"seemed endless twisting and turning, disorienting her"
1
"looked like an old turnstile, forgotten f"
2
"not-quite human, moved through the throng"
3
"world that seemed to be actively hostile"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.959
wordCount
1043
matches
0
"not really, but he moved like one, agile"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
92
matches
(empty)
63.29%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
15
mean
69.53
std
25.83
cv
0.372
sampleLengths
0
87
1
70
2
66
3
94
4
11
5
57
6
65
7
58
8
65
9
46
10
56
11
115
12
73
13
61
14
119
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
0
totalVerbs
160
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
92
ratio
0
matches
(empty)
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1046
adjectiveStacks
1
stackExamples
0
"strange leather-bound books,"
adverbCount
23
adverbRatio
0.02198852772466539
lyAdverbCount
12
lyAdverbRatio
0.011472275334608031
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
11.34
std
5.82
cv
0.514
sampleLengths
0
26
1
23
2
17
3
21
4
15
5
13
6
3
7
6
8
22
9
11
10
12
11
6
12
4
13
3
14
4
15
11
16
20
17
6
18
16
19
15
20
9
21
21
22
18
23
15
24
11
25
14
26
11
27
17
28
15
29
9
30
2
31
11
32
4
33
10
34
14
35
6
36
9
37
15
38
14
39
13
40
2
41
14
42
13
43
17
44
13
45
5
46
17
47
10
48
9
49
16
55.80%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
2
diversityRatio
0.34782608695652173
totalSentences
92
uniqueOpeners
32
0.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
0
totalSentences
86
matches
(empty)
ratio
0
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
24
totalSentences
86
matches
0
"Her breath plumed out in"
1
"He moved with a speed"
2
"She’d underestimated him."
3
"Her boots skidded on slick"
4
"She rounded the corner."
5
"She scanned the street."
6
"She darted towards it, the"
7
"She squeezed through, her clothes"
8
"He looked back, his face"
9
"He sprinted, his olive skin"
10
"He wasn’t a street rat,"
11
"He slid to a halt,"
12
"He disappeared inside, a ghost"
13
"She found the loose brick,"
14
"She drew her sidearm, the"
15
"She reached an archway, shrouded"
16
"She moved through the arch,"
17
"She’d heard whispers, the kind"
18
"His warm brown eyes widened,"
19
"He had thought he was"
ratio
0.279
0.70%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
79
totalSentences
86
matches
0
"Rain lashed against the grimy"
1
"Detective Harlow Quinn’s closely cropped"
2
"Her breath plumed out in"
3
"The worn leather watch on"
4
"Tomás Herrera, a blur of"
5
"He moved with a speed"
6
"She’d underestimated him."
7
"A grave error she wouldn’t"
8
"The alley opened onto a"
9
"Herrera didn’t hesitate, hooking a"
10
"Quinn pushed harder, her military"
11
"Her boots skidded on slick"
12
"She rounded the corner."
13
"Herrera had vanished."
14
"She scanned the street."
15
"The rain hammered down, creating"
16
"A flash of movement, a"
17
"An access point she hadn't"
18
"She darted towards it, the"
19
"The gap was barely wide"
ratio
0.919
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
86
matches
(empty)
ratio
0
89.95%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
54
technicalSentenceCount
4
matches
0
"Figures wrapped in heavy cloaks, some with eyes that gleamed with unnatural light, haggled over goods on display."
1
"A low murmur of voices, a confluence of languages she didn’t recognize, filled the air, a constant hum that vibrated through the very ground."
2
"A place that moved locations every full moon, accessible only with a bone token."
3
"Tomas spun on his heel, merging with the crowd, his olive skin disappearing amidst the swirling bodies."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
2
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
0
79.2548%