NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHT03ZXNF66D7KDZ6JQK0480
Run Details
Model:
Gemini 2.5 Flash
Test:
Bad Writing Habits
Scenario:
Romance: separated couple reunites
Duration:
8.5s
Cost:
$0.003938
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
71.51%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
28.77%
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)
100.00%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
90.04%
Overuse of "that" (subordinate clause padding)
(details)
97.49%
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)
92.29%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
61.69%
Sentence opener variety
(details)
46.95%
Adverb-first sentence starts
(details)
22.82%
Pronoun-first sentence starts
(details)
0.00%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
79.83%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
78.0465%
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
The top lock clicked, then
the middle, and finally the bolt scraped back with a
familiar
rasp. Rory pulled the door open, ready to tell Eva she'd forgotten her keys again.
Lucien Moreau stood on her
landing. He wore a charcoal suit,
perfectly
tailored as always, the kind of expensive cloth that whispered of silent money.
His platinum blond hair was
slicked back, catching the dim hallway light. In one hand, he held his ivory-handled cane, the tip resting on the worn runner.
His heterochromatic eyes – one
amber, one black – fixed on her, no surprise, no apology, just that calm, assessing gaze she knew too well.
Rory’s breath snagged in her
throat.
Her heart hammered against her
ribs, a frantic bird desperate for escape. Months.
It had been months since
she saw him, since she walked out of his life without a backward glance, without a single word.
She felt the old anger
simmer, a low, persistent heat beneath her ribs, threatening to ignite. “You’re early,”
she said, her voice a
little too sharp, a little too loud in the confined space.
A flimsy shield against the
sudden storm brewing inside her.
Lucien's lips twitched, a fleeting
ghost of a smile that never quite reached his eyes. "Punctuality, *
ma chérie
*, is a virtue." His French accent, that smooth, cultured sound, caressed the words, sending a shiver
down her spine
.
A shiver of fury, she
told herself. Nothing more. “I wasn’t expecting you,”
Rory said, tightening her grip
on the doorknob. Her
knuckles turned white
. “I wasn’t expecting anyone.” "Evidently,"
he swept his gaze over
her, taking in her worn jeans and faded band t-shirt, the hair she hadn't bothered to tame. A silent judgment, she thought, of her casual attire, a
stark
contrast to his impeccable presentation. “What do you want, Lucien?” She leaned against the doorframe, crossing her arms over her chest. A defensive posture, she knew, but she couldn't help it.
His presence alone was an
assault. He stepped into the flat, uninvited, pushing the door
gently
wider. The scent of his expensive cologne, a blend of woodsmoke and old leather, filled the small space, chasing away the faint aroma of curry from the restaurant below. Ptolemy, Eva’s tabby, wound around his ankles, purring loudly, rubbing against the fine fabric of his trousers. Even the cat, traitorous beast,
seemed to
welcome him. “I have information,” Lucien said, his eyes
scanning
the cluttered living room, the stacks of books and
scrolls that covered
every available surface. He took it all in, every detail, every change since his last visit. Rory closed the door with a soft click, sealing them inside. “Information about what?”
she asked, her voice tight
. The anger felt hotter now, coiling in her gut.
She hated that he could
still do this to her, still stir up all the old emotions with just a look, a word. Lucien moved further into the room, his cane tapping
softly
on the wooden floor. Ptolemy followed, a furry shadow at his heels.
He ran a gloved finger
along the spine of a leather-bound grimoire on a bookshelf. “Information you will find… illuminating.” “If you have something to tell me, just say it,”
Rory said, her patience fraying
.
She didn’t want to play
his games, not now, not ever again.
He turned, his gaze locking
with hers. “It concerns the disappearances. The ones you’ve been investigating.” Rory’s heart gave a sudden
lurch
. The disappearances. The reason she’d been spending restless nights poring over ancient texts with Eva, the reason she hadn’t slept properly in weeks. “How do you know about that?” The question came out sharper than she intended. Lucien simply raised an
eyebrow
. “My dear Rory, do you
truly
believe anything happens in this city without my knowledge?” A hint of amusement played in his tone, a subtle mockery that grated on her nerves. “Get to the point, Lucien,”
she demanded, her voice an
octave lower, laced with a warning. He walked past her towards the small, worn sofa, Ptolemy still trailing him. He settled onto it, his movements fluid and unhurried. The sofa creaked under his
weight
. Ptolemy immediately hopped onto his lap, kneading against his chest, purring a rumble that
vibrated
through the quiet room. Lucien stroked the cat’s head, his movements gentle, almost tender. It was a
stark
contrast to the aloof, dangerous man she knew. “The information is delicate,” he said, his gaze fixed on her. “And it comes with a price.” Rory scoffed. “Of course, it does.” The anger flared brighter, hotter, an inferno in her chest. Everything with Lucien had a price. Everything was a transaction. “You look well,” he said, changing the subject with infuriating ease. His eyes, those mismatched windows to a hidden world, softened just a fraction. “A touch tired, perhaps. But well.” She ignored the compliment, the sudden
warmth
she felt against her will, the way her skin tingled where his gaze touched her. “I don’t need your pleasantries, Lucien. I need to know what you came here for.” He sighed, a soft, weary sound. “Always so direct, *
ma chérie
*.” He lifted Ptolemy off his lap, placing the cat
gently
on the floor. Ptolemy let out an indignant meow, then rubbed against Lucien’s legs. “Very well.” He leaned forward, resting his clasped hands on his cane, his amber eye
gleaming
in the dim light. “There’s a new player in town. Someone with a particular… taste.” “What kind of taste?”
Rory asked, her voice still tight with tension
. “One that involves human souls,”
Lucien said, his voice dropping to a low, serious tone
. “And rare, potent magical artifacts.” Rory frowned. “Souls?” She’d dealt with a lot in the supernatural underworld, but soul-snatching was a level of depravity even she hadn’t encountered often. “Who is it?” Lucien leaned back, his gaze lingering on her for a moment longer than necessary. “That, Rory, is where the price comes in.” “What do you want?”
she asked, her voice barely a whisper
. She knew, deep down, that whatever he asked, she would pay. The disappearances, the missing people, gnawed at her. She couldn’t let anything stand in the way of finding them. His
eyes narrowed
, a
flicker
of something she couldn't
quite decipher passing through them
. “I want you to come back to me.”
created_at
"2026-02-19T03:46:54.017Z"
2/19/2026, 3:46:54 AM
model
"google/gemini-2.5-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
614
moderation_latency
(null)
generation_time
8427
tokens_prompt
1034
tokens_completion
1659
native_tokens_prompt
976
native_tokens_completion
1458
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
0.0039378
router
(null)
provider_responses
0
endpoint_id
"16c01e26-9b91-4d22-b487-ed35634b017d"
is_byok
false
latency
614
model_permaslug
"google/gemini-2.5-flash"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771472814-rXerhL73pjdbmaD2S3m4"
upstream_id
(null)
total_cost
0.0039378
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
20
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
31
tagDensity
0.645
leniency
1
rawRatio
0
effectiveRatio
0
71.51%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1053
totalAiIsmAdverbs
6
found
0
adverb
"perfectly"
count
1
1
adverb
"gently"
count
2
2
adverb
"softly"
count
1
3
adverb
"truly"
count
1
4
adverb
"very"
count
1
highlights
0
"perfectly"
1
"gently"
2
"softly"
3
"truly"
4
"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)
28.77%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1053
totalAiIsms
15
found
0
word
"familiar"
count
1
1
word
"fleeting"
count
1
2
word
"down her spine"
count
1
3
word
"stark"
count
2
4
word
"scanning"
count
1
5
word
"lurch"
count
1
6
word
"eyebrow"
count
1
7
word
"weight"
count
1
8
word
"vibrated"
count
1
9
word
"warmth"
count
1
10
word
"gleaming"
count
1
11
word
"tension"
count
1
12
word
"whisper"
count
1
13
word
"flicker"
count
1
highlights
0
"familiar"
1
"fleeting"
2
"down her spine"
3
"stark"
4
"scanning"
5
"lurch"
6
"eyebrow"
7
"weight"
8
"vibrated"
9
"warmth"
10
"gleaming"
11
"tension"
12
"whisper"
13
"flicker"
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
"knuckles turned white"
count
1
highlights
0
"eyes narrowed"
1
"knuckles turned white"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
76
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
1
narrationSentences
76
filterMatches
(empty)
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
87
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
31
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
2
markdownWords
4
totalWords
1052
ratio
0.004
matches
0
"ma chérie"
1
"ma chérie"
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
12
unquotedAttributions
1
matches
0
"A shiver of fury, she told herself."
83.33%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
30
wordCount
880
uniqueNames
6
maxNameDensity
1.14
worstName
"Lucien"
maxWindowNameDensity
2.5
worstWindowName
"Lucien"
discoveredNames
Eva
3
Moreau
1
French
1
Lucien
10
Ptolemy
6
Rory
9
persons
0
"Eva"
1
"Moreau"
2
"Lucien"
3
"Ptolemy"
4
"Rory"
places
(empty)
globalScore
0.932
windowScore
0.833
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
66
glossingSentenceCount
1
matches
0
"quite decipher passing through them"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1052
matches
(empty)
90.04%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
2
totalSentences
87
matches
0
"scrolls that covered"
1
"hated that he"
97.49%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
30
mean
35.07
std
17.23
cv
0.491
sampleLengths
0
31
1
6
2
71
3
58
4
28
5
46
6
20
7
39
8
32
9
65
10
36
11
51
12
42
13
27
14
16
15
43
16
36
17
16
18
69
19
17
20
26
21
30
22
37
23
66
24
12
25
20
26
27
27
22
28
41
29
22
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
76
matches
0
"was slicked"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
142
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
2
semicolonCount
0
flaggedSentences
1
totalSentences
87
ratio
0.011
matches
0
"His heterochromatic eyes – one amber, one black – fixed on her, no surprise, no apology, just that calm, assessing gaze she knew too well."
92.29%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
881
adjectiveStacks
0
stackExamples
(empty)
adverbCount
43
adverbRatio
0.04880817253121453
lyAdverbCount
10
lyAdverbRatio
0.011350737797956867
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
87
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
87
mean
12.09
std
6.37
cv
0.527
sampleLengths
0
17
1
14
2
6
3
19
4
12
5
15
6
25
7
6
8
12
9
1
10
23
11
16
12
18
13
10
14
15
15
22
16
7
17
2
18
12
19
4
20
4
21
23
22
16
23
16
24
10
25
6
26
11
27
28
28
17
29
9
30
23
31
13
32
11
33
8
34
9
35
23
36
14
37
8
38
15
39
5
40
15
41
12
42
7
43
9
44
6
45
2
46
21
47
14
48
5
49
31
61.69%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
3
diversityRatio
0.39080459770114945
totalSentences
87
uniqueOpeners
34
46.95%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
71
matches
0
"Even the cat, traitorous beast,"
ratio
0.014
22.82%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
35
totalSentences
71
matches
0
"He wore a charcoal suit,"
1
"His platinum blond hair was"
2
"His heterochromatic eyes – one"
3
"Her heart hammered against her"
4
"It had been months since"
5
"She felt the old anger"
6
"she said, her voice a"
7
"His French accent, that smooth,"
8
"Her knuckles turned white."
9
"he swept his gaze over"
10
"She leaned against the doorframe,"
11
"His presence alone was an"
12
"He stepped into the flat,"
13
"He took it all in,"
14
"she asked, her voice tight"
15
"She hated that he could"
16
"He ran a gloved finger"
17
"She didn’t want to play"
18
"He turned, his gaze locking"
19
"she demanded, her voice an"
ratio
0.493
0.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
69
totalSentences
71
matches
0
"The top lock clicked, then"
1
"Rory pulled the door open,"
2
"Lucien Moreau stood on her"
3
"He wore a charcoal suit,"
4
"His platinum blond hair was"
5
"His heterochromatic eyes – one"
6
"Rory’s breath snagged in her"
7
"Her heart hammered against her"
8
"It had been months since"
9
"She felt the old anger"
10
"she said, her voice a"
11
"A flimsy shield against the"
12
"Lucien's lips twitched, a fleeting"
13
"His French accent, that smooth,"
14
"A shiver of fury, she"
15
"Rory said, tightening her grip"
16
"Her knuckles turned white."
17
"he swept his gaze over"
18
"A silent judgment, she thought,"
19
"She leaned against the doorframe,"
ratio
0.972
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
71
matches
(empty)
ratio
0
79.83%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
34
technicalSentenceCount
3
matches
0
"He wore a charcoal suit, perfectly tailored as always, the kind of expensive cloth that whispered of silent money."
1
"Ptolemy, Eva’s tabby, wound around his ankles, purring loudly, rubbing against the fine fabric of his trousers."
2
"Ptolemy immediately hopped onto his lap, kneading against his chest, purring a rumble that vibrated through the quiet room."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
20
uselessAdditionCount
6
matches
0
"she asked, her voice tight"
1
"Rory said, her patience fraying"
2
"she demanded, her voice an octave lower, laced with a warning"
3
"Rory asked, her voice still tight with tension"
4
"Lucien said, his voice dropping to a low, serious tone"
5
"she asked, her voice barely a whisper"
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
11
fancyCount
1
fancyTags
0
"she demanded (demand)"
dialogueSentences
31
tagDensity
0.355
leniency
0.71
rawRatio
0.091
effectiveRatio
0.065
78.0465%