NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHTXTYEMNNK9M8V6HR1R2K6H
Run Details
Model:
Gemini 2.5 Flash
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
10.2s
Cost:
$0.004520
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
63.64%
Adverbs in dialogue tags
(details)
76.25%
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)
91.58%
Name drop frequency
(details)
53.85%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
100.00%
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)
52.29%
Sentence opener variety
(details)
0.00%
Adverb-first sentence starts
(details)
0.00%
Pronoun-first sentence starts
(details)
0.00%
Subject-first sentence starts
(details)
57.47%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
44.74%
Dialogue tag variety (said vs. fancy)
(details)
74.4601%
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="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</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> </codex> Continue the story using the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the literary fiction genre. Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret. 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 distinctive green neon sign
of The Raven’s Nest
flickered
above, casting a sickly hue across the wet pavement. Rain, a steady British drizzle, slicked the Soho street.
Rory pushed through the heavy
oak door, the low hum of conversation and clinking glasses a
familiar
embrace.
She shucked off her rain-damp
jacket, hanging it on a peg near the entrance.
The usual crowd populated the
dimly lit bar. Old maps and faded black-and-white photographs covered the walls, each one a silent witness to countless whispered secrets and shared laughter.
Silas, his grey-streaked auburn hair
glinting
under the warm glow of the overhead lights, polished a glass behind the bar.
A silver signet ring caught
the light on his right hand as he worked.
He looked up, a faint
smile touching his lips. “Evening, Rory,”
a warm rumble from Silas
. “Thought you were done for the night.” “Just finished my last delivery,”
Rory said, pushing a stray
strand of black hair from her face. “Figured I’d grab a quick one before heading up.”
She moved to her usual
stool at the corner of the bar, the subtle ache in her left knee from a full day on her feet a
familiar
companion.
She ordered a sparkling water
with lime. The scent of aged wood, stale beer, and something faintly metallic, always present in the Nest, filled her nostrils.
She watched Silas, his slight
limp as he moved, a
testament
to old battles. He set her drink down, ice clinking. “Slow night,”
he observed, leaning against the
counter.
Rory nodded, tracing the condensation
on her glass. “Almost a relief after the day I’ve had. Ran into a rather… colourful character down on Drury Lane. Demanded I deliver his spring rolls in a top hat.”
Silas let out a low
chuckle. “Never a dull moment, is there?”
A sudden chill snaked its
way up Rory’s spine, a
sense of
being watched. She
slowly
turned her head.
A man sat several stools
down, his back to her, but something about the set of his shoulders, the dark curve of his hair, snagged at a forgotten memory.
He wore a heavy, dark
coat, its collar turned up. The bar’s dim lighting threw shadows across him, obscuring his features.
He turned slowly, a deliberate
motion, and met her gaze. Recognition, a jolt of ice water to the gut, slammed into Rory. Evan.
His eyes, once a vibrant
green she remembered, now seemed dulled, almost opaque. A scar, thin and white, slashed across his left
eyebrow
.
His face, once smooth, was
now
etched
with a weary maturity that went beyond his years. The boy she knew
was gone
, replaced by a ghost. A tremor ran through her.
Her breath caught in her
throat.
She gripped her glass, her
knuckles white.
He offered a tight, almost
grim, smile. “Rory?” His voice, a low rasp, sent another shiver through her. It was the same voice, yet harsher, like gravel on stone. “Evan,”
she managed, the name a
foreign taste on her tongue. The sound of it invoked a flood of
fragmented
images: laughter, promises, the cold grip of fear. He rose from his stool, his movements stiff, almost hesitant, as if the years had settled into his bones.
He walked towards her, each
step a further erosion of the distance between them, a closer inspection of her past. She felt a phantom pain on her left wrist, remembering the small crescent-shaped scar hidden beneath her sleeve. He stopped a polite distance away, his hands shoved into his pockets. “It’s been a while.” “Years,”
Rory replied, her voice flat
. She kept her gaze steady, unwilling to let him
see
the tumult
churning
inside her. “London suits you,” he said, his eyes
scanning
her face, lingering on her bright blue eyes, her straight black hair. A
flicker
, something she couldn't
quite decipher, crossed his face
. “I’m doing well,” she stated, a subtle defiance in her tone. He nodded
slowly
, a ghost of his former self. “I heard.”
He paused, as if searching for the right words
. “I… I’ve changed, Rory.” “I can
see
that,”
she said, her gaze unwavering
. The harsh lines
etched
around his eyes, the hollows in his cheeks, spoke volumes she didn’t want to hear. A sigh escaped him. “You always could
see
through me, couldn’t you?” He offered another one of his tight, sad smiles. “Always knew what I was thinking.” “Some things are hard to forget,” Rory said, a bitter edge to her voice. He flinched, a subtle tightening of his jaw. “I deserved that,”
he conceded, his gaze drifting to the scarred surface of the bar
. “And more.” The
silence
stretched between them, heavy and weighted with
unspoken
history. The clinking of glasses, the low murmur of conversation,
seemed to
fade into the background. It was just them, suspended in a moment that felt both endless and
fleeting
. “What are you doing here, Evan?” she finally asked, her voice laced with a mixture of curiosity and
apprehension
. He met her gaze, his eyes shadowed. “Passing through. Needed a drink.” He gestured around the bar. “Didn’t expect to find you in a place like this.” “I live above it,” Rory said, a small, almost imperceptible shrug of her shoulders. His eyebrows rose
slightly
. “You always had a knack for finding adventure.” A faint, almost imperceptible
warmth
entered his eyes. “Remember that time we snuck into the old abandoned theatre by the docks?” A prickle of irritation rose within Rory. He
was trying
to invoke nostalgia, to erase the years, to soften the edges of their shared past. “I remember a lot of things, Evan.” His smile faltered. “I know,”
he whispered, the earlier confidence draining from his posture
. He shifted his
weight
, his gaze falling to his hands. “I’ve done a lot of thinking, Rory. About… about everything.” “Has it made a difference?”
she asked, her voice quiet, almost a challenge
. He hesitated, then
slowly
raised his head. “I hope so. I’m trying. To be… better.” “Good for you,”
she said, the words clipped, devoid of emotion
. She wouldn’t offer him comfort, not after all this time. The memories, the fear, the pain, still
resonated
. He ran a hand through his dark hair, the gesture somehow alien on his changed face. “I know it’s not enough. Nothing I can say or do will ever make up for… for what I did.” Rory remained silent, watching him, her face a mask. She saw the regret in his eyes, felt the
weight
of it in the air between them, but it offered no balm to her old wounds. “Did you ever… hate me?” His voice was barely a
whisper
. Rory finally looked away, focusing on the condensation on her glass. “It’s complicated, Evan. It always was.” He nodded, a slow, solemn movement. “I understand.” He took a step back, widening the gap between them. “I won’t bother you. It was… good to
see
you.” His voice cracked
slightly
on the last few words.
Before she could respond, he
turned and walked back to his stool, his heavy coat a dark silhouette against the muted lights of the bar. He sat down, his back once again to her, becoming just another shadow in the corner of The Raven’s Nest. The space he left between them, once filled with
tension
, now felt empty, a void that had swallowed a piece of her past. Rory stared at the ripple of her reflection in the glass, the bright blue of her eyes a
stark
contrast to the dimness around her.
created_at
"2026-02-19T12:26:14.874Z"
2/19/2026, 12:26:14 PM
model
"google/gemini-2.5-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
543
moderation_latency
(null)
generation_time
10172
tokens_prompt
1094
tokens_completion
1921
native_tokens_prompt
1032
native_tokens_completion
1684
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
0.0045196
router
(null)
provider_responses
0
endpoint_id
"16c01e26-9b91-4d22-b487-ed35634b017d"
is_byok
false
latency
543
model_permaslug
"google/gemini-2.5-flash"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771503974-ir1eVBDUdvv6larq8q2Q"
upstream_id
(null)
total_cost
0.0045196
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
63.64%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
22
adverbTagCount
3
adverbTags
0
"she finally asked [finally]"
1
"He gestured around [around]"
2
"His voice cracked slightly [slightly]"
dialogueSentences
38
tagDensity
0.579
leniency
1
rawRatio
0.136
effectiveRatio
0.136
76.25%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1263
totalAiIsmAdverbs
6
found
0
adverb
"slowly"
count
4
1
adverb
"slightly"
count
2
highlights
0
"slowly"
1
"slightly"
100.00%
AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0
"Blackwood"
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
1263
totalAiIsms
27
found
0
word
"flickered"
count
1
1
word
"familiar"
count
2
2
word
"glinting"
count
1
3
word
"testament"
count
1
4
word
"tracing"
count
1
5
word
"chill"
count
1
6
word
"sense of"
count
1
7
word
"eyebrow"
count
1
8
word
"etched"
count
2
9
word
"fragmented"
count
1
10
word
"churning"
count
1
11
word
"scanning"
count
1
12
word
"flicker"
count
1
13
word
"unwavering"
count
1
14
word
"silence"
count
1
15
word
"unspoken"
count
1
16
word
"fleeting"
count
1
17
word
"apprehension"
count
1
18
word
"warmth"
count
1
19
word
"weight"
count
2
20
word
"resonated"
count
1
21
word
"whisper"
count
1
22
word
"tension"
count
1
23
word
"stark"
count
1
highlights
0
"flickered"
1
"familiar"
2
"glinting"
3
"testament"
4
"tracing"
5
"chill"
6
"sense of"
7
"eyebrow"
8
"etched"
9
"fragmented"
10
"churning"
11
"scanning"
12
"flicker"
13
"unwavering"
14
"silence"
15
"unspoken"
16
"fleeting"
17
"apprehension"
18
"warmth"
19
"weight"
20
"resonated"
21
"whisper"
22
"tension"
23
"stark"
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
88
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
1
narrationSentences
88
filterMatches
0
"see"
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
102
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
38
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1258
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
14
unquotedAttributions
0
matches
(empty)
91.58%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
23
wordCount
1027
uniqueNames
6
maxNameDensity
1.17
worstName
"Rory"
maxWindowNameDensity
2
worstWindowName
"Silas"
discoveredNames
Raven
2
Nest
3
British
1
Soho
1
Silas
4
Rory
12
persons
0
"Raven"
1
"Nest"
2
"Silas"
3
"Rory"
places
0
"Soho"
globalScore
0.916
windowScore
1
53.85%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
78
glossingSentenceCount
3
matches
0
"seemed dulled almost opaque"
1
"quite decipher, crossed his face"
2
"as if searching for the right words"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1258
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
102
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
39
mean
32.26
std
20.37
cv
0.631
sampleLengths
0
89
1
43
2
14
3
55
4
47
5
8
6
36
7
12
8
69
9
72
10
25
11
22
12
28
13
57
14
16
15
21
16
30
17
11
18
24
19
28
20
27
21
14
22
25
23
40
24
19
25
27
26
14
27
33
28
32
29
34
30
13
31
15
32
29
33
36
34
35
35
11
36
17
37
37
38
93
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
88
matches
0
"was gone"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
1
totalVerbs
156
matches
0
"was trying"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
102
ratio
0
matches
(empty)
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1032
adjectiveStacks
1
stackExamples
0
"small crescent-shaped scar"
adverbCount
37
adverbRatio
0.035852713178294575
lyAdverbCount
12
lyAdverbRatio
0.011627906976744186
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
102
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
102
mean
12.33
std
6.42
cv
0.52
sampleLengths
0
19
1
9
2
18
3
14
4
8
5
21
6
20
7
14
8
9
9
7
10
7
11
17
12
38
13
7
14
19
15
14
16
7
17
8
18
8
19
28
20
6
21
6
22
14
23
5
24
29
25
10
26
11
27
10
28
12
29
1
30
13
31
10
32
16
33
10
34
5
35
6
36
7
37
7
38
11
39
11
40
11
41
17
42
19
43
20
44
18
45
12
46
4
47
6
48
15
49
20
52.29%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
5
diversityRatio
0.3431372549019608
totalSentences
102
uniqueOpeners
35
0.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
0
totalSentences
87
matches
(empty)
ratio
0
0.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
51
totalSentences
87
matches
0
"She shucked off her rain-damp"
1
"He looked up, a faint"
2
"She moved to her usual"
3
"She ordered a sparkling water"
4
"She watched Silas, his slight"
5
"He set her drink down,"
6
"he observed, leaning against the"
7
"She slowly turned her head."
8
"He wore a heavy, dark"
9
"He turned slowly, a deliberate"
10
"His eyes, once a vibrant"
11
"His face, once smooth, was"
12
"Her breath caught in her"
13
"She gripped her glass, her"
14
"He offered a tight, almost"
15
"His voice, a low rasp,"
16
"It was the same voice,"
17
"she managed, the name a"
18
"He rose from his stool,"
19
"He walked towards her, each"
ratio
0.586
0.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
84
totalSentences
87
matches
0
"The distinctive green neon sign"
1
"Rory pushed through the heavy"
2
"She shucked off her rain-damp"
3
"The usual crowd populated the"
4
"Silas, his grey-streaked auburn hair"
5
"A silver signet ring caught"
6
"He looked up, a faint"
7
"a warm rumble from Silas"
8
"Rory said, pushing a stray"
9
"She moved to her usual"
10
"She ordered a sparkling water"
11
"The scent of aged wood,"
12
"She watched Silas, his slight"
13
"He set her drink down,"
14
"he observed, leaning against the"
15
"Rory nodded, tracing the condensation"
16
"Silas let out a low"
17
"A sudden chill snaked its"
18
"She slowly turned her head."
19
"A man sat several stools"
ratio
0.966
57.47%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
87
matches
0
"Before she could respond, he"
ratio
0.011
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
40
technicalSentenceCount
1
matches
0
"He rose from his stool, his movements stiff, almost hesitant, as if the years had settled into his bones."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
22
uselessAdditionCount
7
matches
0
"Rory replied, her voice flat"
1
"He paused, as if searching for the right words"
2
"she said, her gaze unwavering"
3
"he conceded, his gaze drifting to the scarred surface of the bar"
4
"he whispered, the earlier confidence draining from his posture"
5
"she asked, her voice quiet, almost a challenge"
6
"she said, the words clipped, devoid of emotion"
44.74%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
13
fancyCount
4
fancyTags
0
"he observed (observe)"
1
"she stated (state)"
2
"he conceded (concede)"
3
"he whispered (whisper)"
dialogueSentences
38
tagDensity
0.342
leniency
0.684
rawRatio
0.308
effectiveRatio
0.211
74.4601%