NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHT0Y63E9HJWXXJEMGWTSMKE
Run Details
Model:
Gemini 2.5 Flash
Test:
Bad Writing Habits
Scenario:
Romance: separated couple reunites
Duration:
10.6s
Cost:
$0.004775
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
72.53%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
13.66%
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)
83.33%
Name drop frequency
(details)
76.47%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
68.29%
Paragraph length variance
(details)
100.00%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
89.95%
Em-dash & semicolon overuse
(details)
94.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
54.01%
Sentence opener variety
(details)
0.00%
Adverb-first sentence starts
(details)
7.34%
Pronoun-first sentence starts
(details)
0.00%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
65.00%
Useless dialogue additions
(details)
68.37%
Dialogue tag variety (said vs. fancy)
(details)
75.3204%
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="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="4415" name="Lucien Moreau" aliases="Lucien, Luc, the Frenchman" pronouns="he/him" species="Half-Demon" storyRole="Ally"> <eyeColor>heterochromatic — one amber, one black</eyeColor> <hair>slicked-back platinum blond</hair> <height>5'11"</height> <age>32</age> <cane>ivory-handled cane that conceals a thin blade</cane> <dress>tailored charcoal suits</dress> <description>An impeccably dressed fixer and information broker in London's supernatural underworld. He speaks four languages fluently.</description> <backstory>Born in Marseille to a human mother and a demon father from the realm of Avaros.</backstory> </character> <location id="858" name="Eva's Flat" aliases="Eva's place, the flat on Brick Lane" realm="Earth"> <cat>tabby cat named Ptolemy</cat> <security>three deadbolts on the front door</security> <description>A cramped one-bedroom flat above a curry house on Brick Lane, East London. Every surface is covered with books, scrolls, and research notes.</description> </location> </codex> Continue the story using the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the romance genre. Two people who parted on complicated terms are forced together again when one shows up unannounced at the other's flat. There's history between them — attraction, hurt, and things left unsaid. Write the scene from the moment the door opens. 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
Rory pulled the door inward. Lucien stood on the landing, framed against the dim hallway light.
The air in her small
flat, already humid from the overflowing kettle,
seemed to
thicken.
His tailored charcoal suit, as
immaculate as ever, looked out of place against her peeling paint. One amber eye gleamed, the other a void of black, fixed on her. “*
Bonsoir, chérie
*,”
Lucien purred, a ghost of
a smile playing on his lips.
He leaned on his ivory-handled
cane, a casual pose that did
not quite hide the tension in his shoulders
. “Fancy seeing you here.”
Rory’s grip tightened on the
doorknob. “What are you doing here, Lucien?”
Her voice sounded steadier than
she felt.
Her heart thumped a frantic
rhythm against her ribs. “A simple social call,”
he responded, pushing off the
cane, taking a step closer.
The scent of his familiar
cologne – sandalwood and something sharp, metallic – wafted into the flat, filling the small space. “Is that so hard to believe?”
She crossed her arms over
her chest. “Considering the last time we spoke, yes, it is.”
Her voice was low
. His gaze swept over her, lingering on her face. “Always so direct, *
ma petite
*.”
He tilted his head, platinum
blond hair catching the light. “I missed that.”
The words hung in the
air, a silent accusation. Rory bristled. “You’re wasting your time.”
She started to close the
door.
Lucien moved, quicker than she
anticipated. His hand, warm and firm, shot out, catching the edge of the door, stopping its swing. “Wait.”
His voice, suddenly stripped of
its usual playful
lilt
, held an edge of something she hadn't heard in a long time. She looked at his hand, then up at his face. The easy smile had vanished. A
flicker
of raw emotion,
something akin to regret, crossed his features
before he masked it. “I need your help, Rory.” The simple admission, coming from him, felt monumental. Rory stared, then let out a short, hollow laugh. “You? Need *
my
* help? The great Lucien Moreau, fixer of all things dark and mysterious, needs *
little old me
*?”
Her voice dripped with sarcasm
. The kettle on the hob shrieked, a piercing sound that momentarily broke the heavy
silence
.
She turned, walked to the
stove, and switched it off, the sudden quiet making the
tension
even more
palpable
. “It’s not a request I make
lightly
,”
he said, his voice softer
now as he pushed the door fully open and stepped inside, closing it
gently
behind him.
He took in the cramped
space, every surface laden with books and papers, a tabby cat named Ptolemy watching him from atop a stack of journals. “So I gathered,” Rory replied, pouring water into a mug. The steam rose, warming her face.
She kept her back to
him, busying her hands. “What could possibly be so dire that you’d come to me?” “A rather delicate matter. One that requires a certain… touch. A certain *
perspective
*.”
He took another step, closer
now, filling her peripheral vision. “Your
perspective
.”
She wheeled around, mug in
hand. “My
perspective
on what, Lucien? Because if this is about some demon lord’s missing teacup, I’m
really
not in the mood.” A genuine smile, slow and charming, spread across his face. “Always a wit, even when you’re vexed.” He paused. “No missing teacups, I assure you. Something far more… personal.” Rory's brow
furrowed
. Personal? Nothing about Lucien was personal. He was layers of
carefully
constructed
charm
and indifference. “What are you talking about?” He walked closer still, until
only
an arm's length separated them. “A mutual acquaintance of ours. One who seems to have… vanished.” His voice dropped, a serious undertone that Rory rarely heard. “Eva.” The mug slipped from Rory’s trembling fingers. It hit the floor with a dull thud, the ceramic cracking, water spreading across the worn linoleum. Her breath hitched. “What?” A sharp pain shot through her chest. “She’s gone, Rory. Vanished. No trace. Her flat is empty. Her cat, Ptolemy, left alone.” He gestured to the tabby, who still sat watching, now with an intense focus. “I’ve tried contacting her, tracking her, everything. It’s like she simply ceased to exist.” Rory felt a cold dread creep into her
stomach
. Eva. Her best friend. Her lifeline. The thought of her just... disappeared. “That’s… that’s impossible. Eva wouldn’t just leave. Not without telling me.” “I agree.” Lucien’s gaze softened, a rare, unguarded look that pierced through her
carefully
constructed
defenses. “Which is why I believe she’s in trouble. And I believe you are the
only
one who can help me find her.” He reached out, his hand hovering for a second before he
gently
touched her arm, his fingers warm. “Please, Rory.” His touch, after so long,
sent a jolt through
her. Memories surfaced – late-night talks, shared secrets, stolen kisses in dimly lit alleys. The easy camaraderie they had once shared, that dangerous pull between them. She jerked her arm away, the cold dread turning to a
simmering
anger. “Why now?”
she asked, her voice tight with suppressed emotion
. “Why come to me now, after… everything?” The words were out before she could stop them. He flinched. The mask of
charm
, briefly dropped, settled back into place, though a shadow lingered in his eyes. “This isn’t about us, Rory. This is about Eva. And she is in danger.” “Don’t you dare, Lucien,” she hissed, pointing a finger at him. “Don’t you dare try to use Eva as a shield for whatever it is you’re trying to say, or not say, or *
do
*.” “I’m not,”
he insisted, his voice firm, losing its softness
. “I searched for her for a week, exhausted all
my
usual resources. Then I thought of you. You know her better than anyone. You have an intuition, a way of seeing things others miss.” Rory scoffed. “You’re just saying that because you need something.” “I am,” he conceded, surprising her. “I am saying that because I need something. I need your help. Because I’m worried about her. And I know you are too.” He took another step, closing the distance she had created. His eyes, the amber and the black, bore into hers. “Rory, you and I… we have our past. Our complications. But Eva… she deserves for us to put that aside. For her.” The mention of “us” sent a fresh wave of conflicting emotions through her. She wanted to yell at him, to rail against his sudden appearance, his charming lies, the way he had walked out of her life without a backward glance. But the image of Eva, laughing, vibrant, vanished, pushed all that aside. She looked at the broken mug on the floor, the spreading puddle. A small tremor went through her. “What… what exactly
do
you want me to
do
?” Her voice was barely a
whisper
. The anger, for now, had given way to a
profound
sense of
worry.
A flicker of relief
crossed Lucien’s face. “Her flat on Brick Lane. I’ve secured it. Untouched, as she left it. There might be something there. A clue, a message… anything.” He paused. “I know it’s a long shot. But it’s all we have.” Rory closed her eyes, picturing Eva’s
chaotic
,
comfortable
flat, smelling of old books and patchouli. It was where she had found refuge after fleeing Cardiff, after Evan. Eva had been her rock, her steady presence. “Fine,” she said, opening her eyes. Her gaze met his, sharp and unyielding. “But this is about Eva, and *
only
* about Eva. Nothing else.” Lucien gave a slow, deliberate nod. “Understood, *
chérie
*.” The endearment, despite her
resolve
, still
sent a shiver down
her spine. “When can you be ready?”
created_at
"2026-02-19T04:01:12.312Z"
2/19/2026, 4:01:12 AM
model
"google/gemini-2.5-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
288
moderation_latency
(null)
generation_time
10576
tokens_prompt
1034
tokens_completion
2005
native_tokens_prompt
976
native_tokens_completion
1793
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
0.0047753
router
(null)
provider_responses
0
endpoint_id
"16c01e26-9b91-4d22-b487-ed35634b017d"
is_byok
false
latency
288
model_permaslug
"google/gemini-2.5-flash"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771473672-b5ss70JTEUlCXZkxc5dU"
upstream_id
(null)
total_cost
0.0047753
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
25
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
49
tagDensity
0.51
leniency
1
rawRatio
0
effectiveRatio
0
72.53%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1274
totalAiIsmAdverbs
7
found
0
adverb
"suddenly"
count
1
1
adverb
"lightly"
count
1
2
adverb
"gently"
count
2
3
adverb
"really"
count
1
4
adverb
"carefully"
count
2
highlights
0
"suddenly"
1
"lightly"
2
"gently"
3
"really"
4
"carefully"
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)
13.66%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1274
totalAiIsms
22
found
0
word
"tension"
count
2
1
word
"familiar"
count
1
2
word
"lilt"
count
1
3
word
"flicker"
count
2
4
word
"silence"
count
1
5
word
"palpable"
count
1
6
word
"furrowed"
count
1
7
word
"constructed"
count
2
8
word
"charm"
count
2
9
word
"stomach"
count
1
10
word
"simmering"
count
1
11
word
"whisper"
count
1
12
word
"profound"
count
1
13
word
"sense of"
count
1
14
word
"chaotic"
count
1
15
word
"comfortable"
count
1
16
word
"resolve"
count
1
17
word
"down her spine"
count
1
highlights
0
"tension"
1
"familiar"
2
"lilt"
3
"flicker"
4
"silence"
5
"palpable"
6
"furrowed"
7
"constructed"
8
"charm"
9
"stomach"
10
"simmering"
11
"whisper"
12
"profound"
13
"sense of"
14
"chaotic"
15
"comfortable"
16
"resolve"
17
"down her spine"
66.67%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
3
maxInWindow
2
found
0
label
"hung in the air"
count
1
1
label
"sent a shiver through"
count
2
highlights
0
"hung in the air"
1
"sent a jolt through"
2
"sent a shiver down"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
1
narrationSentences
88
matches
0
"A flicker of relief"
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
2
narrationSentences
88
filterMatches
(empty)
hedgeMatches
0
"seemed to"
1
"started to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
108
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
8
markdownWords
12
totalWords
1275
ratio
0.009
matches
0
"Bonsoir, chérie"
1
"ma petite"
2
"my"
3
"little old me"
4
"perspective"
5
"do"
6
"only"
7
"chérie"
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
14
unquotedAttributions
0
matches
(empty)
83.33%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
25
wordCount
845
uniqueNames
6
maxNameDensity
1.3
worstName
"Rory"
maxWindowNameDensity
2.5
worstWindowName
"Rory"
discoveredNames
Lucien
7
Rory
11
Ptolemy
1
Eva
4
Cardiff
1
Evan
1
persons
0
"Lucien"
1
"Rory"
2
"Ptolemy"
3
"Eva"
4
"Evan"
places
0
"Cardiff"
globalScore
0.849
windowScore
0.833
76.47%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
68
glossingSentenceCount
2
matches
0
"not quite hide the tension in his shoulders"
1
"something akin to regret, crossed his features"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1275
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
108
matches
(empty)
68.29%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
35
mean
36.43
std
14.17
cv
0.389
sampleLengths
0
60
1
36
2
28
3
41
4
20
5
27
6
21
7
44
8
31
9
13
10
67
11
54
12
36
13
25
14
27
15
29
16
23
17
33
18
35
19
43
20
32
21
58
22
48
23
26
24
33
25
34
26
44
27
10
28
71
29
53
30
46
31
43
32
35
33
24
34
25
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
88
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
142
matches
(empty)
89.95%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
3
semicolonCount
0
flaggedSentences
2
totalSentences
108
ratio
0.019
matches
0
"The scent of his familiar cologne – sandalwood and something sharp, metallic – wafted into the flat, filling the small space."
1
"Memories surfaced – late-night talks, shared secrets, stolen kisses in dimly lit alleys."
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
844
adjectiveStacks
1
stackExamples
0
"chaotic, comfortable flat, smelling"
adverbCount
30
adverbRatio
0.035545023696682464
lyAdverbCount
12
lyAdverbRatio
0.014218009478672985
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
108
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
108
mean
11.81
std
7.67
cv
0.65
sampleLengths
0
5
1
11
2
15
3
16
4
13
5
13
6
19
7
4
8
6
9
13
10
9
11
14
12
21
13
6
14
7
15
13
16
9
17
15
18
3
19
9
20
2
21
10
22
6
23
16
24
22
25
10
26
5
27
16
28
13
29
9
30
24
31
15
32
19
33
28
34
26
35
10
36
6
37
9
38
11
39
23
40
2
41
6
42
21
43
10
44
9
45
10
46
3
47
1
48
5
49
9
54.01%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
5
diversityRatio
0.35185185185185186
totalSentences
108
uniqueOpeners
38
0.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
0
totalSentences
79
matches
(empty)
ratio
0
7.34%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
42
totalSentences
79
matches
0
"His tailored charcoal suit, as"
1
"He leaned on his ivory-handled"
2
"Her voice sounded steadier than"
3
"Her heart thumped a frantic"
4
"he responded, pushing off the"
5
"She crossed her arms over"
6
"Her voice was low"
7
"His gaze swept over her,"
8
"He tilted his head, platinum"
9
"She started to close the"
10
"His hand, warm and firm,"
11
"His voice, suddenly stripped of"
12
"She looked at his hand,"
13
"Her voice dripped with sarcasm"
14
"She turned, walked to the"
15
"he said, his voice softer"
16
"He took in the cramped"
17
"She kept her back to"
18
"He took another step, closer"
19
"She wheeled around, mug in"
ratio
0.532
0.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
77
totalSentences
79
matches
0
"Rory pulled the door inward."
1
"Lucien stood on the landing,"
2
"The air in her small"
3
"His tailored charcoal suit, as"
4
"Lucien purred, a ghost of"
5
"He leaned on his ivory-handled"
6
"Rory’s grip tightened on the"
7
"Her voice sounded steadier than"
8
"Her heart thumped a frantic"
9
"he responded, pushing off the"
10
"The scent of his familiar"
11
"She crossed her arms over"
12
"Her voice was low"
13
"His gaze swept over her,"
14
"He tilted his head, platinum"
15
"The words hung in the"
16
"She started to close the"
17
"Lucien moved, quicker than she"
18
"His hand, warm and firm,"
19
"His voice, suddenly stripped of"
ratio
0.975
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
79
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
27
technicalSentenceCount
1
matches
0
"He leaned on his ivory-handled cane, a casual pose that did not quite hide the tension in his shoulders."
65.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
25
uselessAdditionCount
3
matches
0
"Lucien purred, a ghost of a smile playing on his lips"
1
"she asked, her voice tight with suppressed emotion"
2
"he insisted, his voice firm, losing its softness"
68.37%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
8
fancyCount
4
fancyTags
0
"he responded (respond)"
1
"she hissed (hiss)"
2
"he insisted (insist)"
3
"he conceded (concede)"
dialogueSentences
49
tagDensity
0.163
leniency
0.327
rawRatio
0.5
effectiveRatio
0.163
75.3204%