NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHTR2H0N8ZMCXSNECHZBZDD1
Run Details
Model:
DeepSeek-V2 Chat
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
1m 42s
Cost:
$0.001978
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
98.31%
Adverbs in dialogue tags
(details)
53.45%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
26.30%
AI-ism word frequency
(details)
33.33%
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)
0.00%
Name drop frequency
(details)
100.00%
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)
98.90%
Em-dash & semicolon overuse
(details)
93.20%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
46.92%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
100.00%
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)
31.25%
Useless dialogue additions
(details)
14.41%
Dialogue tag variety (said vs. fancy)
(details)
76.5359%
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 Raven’s Nest was its
usual self—dimly lit, the air thick with the scent of aged wood and whiskey.
The green neon sign flickered
lazily
above the door, casting an eerie glow on the cobblestone street outside. Rory leaned against the bar, her fingers
tracing
the rim of her glass.
The ice clinked softly, dissolving
into the amber liquid.
She wasn’t here for the
drinks, not
really
. Silas had called her in, something about a lead on Evan, but he’d
been tied
up in the back room for over an hour now.
She’d grown restless, her thoughts
wandering to the last time she’d seen Eva. Two years ago, maybe three.
Time had a way of
blurring the edges.
The door creaked open, and
a draft swept in, carrying with it the faint scent of rain.
Rory glanced up, her bright
blue eyes narrowing as she took in the figure silhouetted against the streetlight.
The woman paused, her gaze
sweeping the room before landing on Rory. For a moment, neither spoke.
Then, a slow, hesitant smile
broke across the woman’s face. “Rory?”
Eva’s voice was softer than
Rory remembered, less sure. She stepped into the bar, the light catching her face. Rory froze. Eva looked different—her once vibrant, fiery curls now tamed into sleek, dark waves.
Her eyes, though still the
same piercing green, carried a
weight
they hadn’t before. She wore a tailored coat, sharp and professional, a far cry from the bohemian dresses Rory associated with her. “Eva.”
Rory’s voice was steady, but
her chest tightened.
She set her glass down
on the bar, the sound louder than she intended.
Eva approached slowly, as if
unsure of her welcome.
She stopped a few feet
away, her hands shoved into the pockets of her coat. “I didn’t expect to see you here.” “Likewise.” Rory crossed her arms, leaning back against the bar. The
silence
stretched between them, heavy with
unspoken
words. “It’s been a while.” Eva’s voice was tentative, probing. Rory nodded, her gaze drifting to the maps on the wall. “Yeah, it has.” Eva shifted her
weight
, her eyes
scanning
Rory’s face. “You look… good.” “Do I?” Rory’s tone was flat, her expression
unreadable
. Eva hesitated, then sighed. “Look, Rory, I know things didn’t end well between us. I just… I wanted to say I’m sorry. For everything.” Rory’s jaw tightened.
She clenched, her fingers digging
into her arms. “You’re sorry?” “Yes.” Eva’s voice was firm now, her chin lifting. “I should’ve been there for you when you left Cardiff. I should’ve—” “You should’ve what, Eva?” Rory cut her off, her voice sharp. “Called? Written? Shown up when I needed you? You vanished. You left me to deal with Evan on my own.” Eva flinched, her green eyes flashing with something Rory couldn’t
quite place
. “I didn’t vanish. I was dealing with my own shit. You weren’t the only one going through hell, Rory.” “Bullshit.” Rory pushed off the bar, stepping closer. “You could’ve reached out. You didn’t. End of story.” Eva’s hands
clenched into fists
, the
tension
crackling between them. “You think it was easy for me? Watching you spiral? Seeing you with him? I wanted to help, but you pushed me away!” “Because I didn’t want your pity!” Rory’s voice rose, her bright blue eyes blazing. “I didn’t need you to fix me, Eva. I needed you to be there. But you couldn’t handle it, could you? You couldn’t handle the mess.”
Her voice cracked, and she
looked away, her chest heaving. Eva’s expression softened, her anger giving way to something else. “I didn’t know how to help,”
she admitted quietly
. “I didn’t know how to fix it.” “You didn’t have to fix it!” Rory snapped. “You just had to stay.” The words
hung in the air
between them, heavy and unrelenting. Eva’s shoulders slumped, her gaze dropping to the floor. “I’m sorry,” she whispered. “I didn’t realize… I didn’t know.” Rory exhaled
sharply
, her frustration ebbing as
quickly
as it had flared.
She ran a hand through
her black hair, revealing the small crescent-shaped scar on her wrist. “It’s not just about me,” she murmured. “You changed, Eva. You became… someone else.” Eva looked up, her green eyes searching Rory’s face. “I had to grow up, Rory. Life… it doesn’t stop just because we’re hurting. I couldn’t keep living in the past.” “Neither could I,”
Rory said, her voice softer now
. “But I didn’t lose myself in the process.” Eva’s lips pressed into a thin line, her gaze drifting to the bar. “Maybe I did,” she admitted. “But it wasn’t by choice.” The
tension
between them eased, the air growing lighter. Rory picked up her glass, swirling the liquid inside. “So, what brings you to Silas’ place? You’re not exactly the usual crowd.” Eva hesitated, then pulled out a stool and sat down. “Work,”
she said simply
. “I’m a journalist now. Freelance, mostly. Silas has… sources.” Rory raised an
eyebrow
. “Silas has sources for everything.” Eva chuckled
softly
, the sound
familiar
yet foreign. “He does. I needed information on a story I’m working on. He said he could help.” “And here I thought you’d come looking for me.” Rory’s tone was dry, but there was a hint of a smile in her eyes. Eva met her gaze, her own smile tentative. “Maybe I did.” The
silence
returned, but it was softer now, less fraught. Rory took a sip of her drink, the ice clinking against the glass. “So, what’s the story?” Eva hesitated, glancing around the bar. “It’s… complicated. Corruption, high-level stuff. I’m not sure how much I can say.” “Classic Eva,” Rory muttered, shaking her head. “Always keeping secrets.” Eva’s expression faltered, her smile fading. “Old habits die hard, I guess.” “Maybe.”
Rory sighed, her gaze drifting to the maps on the wall again
. “But we’re not kids anymore, Eva. Secrets… they have a way of eating you alive.” Eva didn’t respond, her hands clasped
tightly
in her lap. The
weight
of their shared history pressed down on them, the years stretching like a chasm between who they were and who they’d become.
Finally, Eva spoke, her voice
barely above a whisper
. “I missed you, Rory.” Rory’s breath caught, her grip tightening on her glass. “I missed you too,”
she admitted softly
. The door to the back room creaked open, and Silas emerged, his limp more pronounced than usual.
He paused, his hazel eyes
flicking between Rory and Eva. “Am I interrupting?” Eva stood
quickly
, smoothing her coat. “No, we were just catching up.” Silas nodded, his expression
unreadable
. “Good. Rory, I need to speak with you.” Rory glanced at Eva, a
flicker
of hesitation in her eyes. “Give me a minute.” Silas retreated to the back room, leaving the two women alone once more. Eva shifted uncomfortably, her gaze darting to the door. “I should go.” Rory’s heart sank, but she nodded. “Yeah. Work calls.” Eva hesitated, then reached into her pocket and pulled out a crumpled business card. “Here. If you ever want to… talk.” Rory took the card, her fingers brushing against Eva’s. The contact was brief, but it
sent a jolt through
her. “Thanks.” Eva lingered for a moment, her green eyes searching Rory’s face.
Then, with a nod, she
turned and walked out the door.
The green neon sign flickered
again as it swung shut, leaving Rory alone in the dim light of the bar.
She stared at the card
in her hand, the
weight
of years pressing down on her chest. The past was never
really
gone, she realized.
It lingered, waiting for the
right moment to resurface. Silas’ voice broke through her thoughts. “Rory.”
She turned, the card slipping
into her pocket. “Coming.”
created_at
"2026-02-19T10:45:31.821Z"
2/19/2026, 10:45:31 AM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
276
moderation_latency
(null)
generation_time
101768
tokens_prompt
1094
tokens_completion
2079
native_tokens_prompt
991
native_tokens_completion
1866
native_tokens_completion_images
(null)
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
0.00197786
router
(null)
provider_responses
0
endpoint_id
"5294d55f-9012-496b-8f22-8cc919432dcd"
id
"chatcmpl-R17Kx9oJF9iBl9bXIlo2pYaa"
is_byok
false
latency
58
model_permaslug
"deepseek/deepseek-chat-v3"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771497931-nSRxaU8Klze9TVLj5RDv"
upstream_id
"chatcmpl-R17Kx9oJF9iBl9bXIlo2pYaa"
total_cost
0.00197786
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
98.31%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
16
adverbTagCount
3
adverbTags
0
"she admitted quietly [quietly]"
1
"she said simply [simply]"
2
"she admitted softly [softly]"
dialogueSentences
59
tagDensity
0.271
leniency
0.542
rawRatio
0.188
effectiveRatio
0.102
53.45%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1289
totalAiIsmAdverbs
12
found
0
adverb
"lazily"
count
1
1
adverb
"softly"
count
3
2
adverb
"really"
count
2
3
adverb
"slowly"
count
1
4
adverb
"sharply"
count
1
5
adverb
"quickly"
count
2
6
adverb
"tightly"
count
1
7
adverb
"barely above a whisper"
count
1
highlights
0
"lazily"
1
"softly"
2
"really"
3
"slowly"
4
"sharply"
5
"quickly"
6
"tightly"
7
"barely above a whisper"
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)
26.30%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1289
totalAiIsms
19
found
0
word
"flickered"
count
2
1
word
"tracing"
count
1
2
word
"weight"
count
4
3
word
"silence"
count
2
4
word
"unspoken"
count
1
5
word
"scanning"
count
1
6
word
"unreadable"
count
2
7
word
"tension"
count
2
8
word
"eyebrow"
count
1
9
word
"familiar"
count
1
10
word
"whisper"
count
1
11
word
"flicker"
count
1
highlights
0
"flickered"
1
"tracing"
2
"weight"
3
"silence"
4
"unspoken"
5
"scanning"
6
"unreadable"
7
"tension"
8
"eyebrow"
9
"familiar"
10
"whisper"
11
"flicker"
33.33%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
3
maxInWindow
3
found
0
label
"clenched jaw/fists"
count
1
1
label
"hung in the air"
count
1
2
label
"sent a shiver through"
count
1
highlights
0
"clenched into fists"
1
"hung in the air"
2
"sent a jolt through"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
90
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
90
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
130
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
36
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1285
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
21
unquotedAttributions
1
matches
0
"Finally, Eva spoke, her voice barely above a whisper."
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
68
wordCount
885
uniqueNames
6
maxNameDensity
3.73
worstName
"Rory"
maxWindowNameDensity
6
worstWindowName
"Rory"
discoveredNames
Raven
1
Nest
1
Evan
1
Eva
28
Rory
33
Silas
4
persons
0
"Raven"
1
"Evan"
2
"Eva"
3
"Rory"
4
"Silas"
places
(empty)
globalScore
0
windowScore
0
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
74
glossingSentenceCount
1
matches
0
"quite place"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1285
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
130
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
50
mean
25.7
std
20.08
cv
0.781
sampleLengths
0
118
1
62
2
1
3
67
4
23
5
31
6
19
7
9
8
14
9
12
10
9
11
24
12
13
13
21
14
31
15
31
16
17
17
33
18
50
19
26
20
13
21
30
22
42
23
30
24
17
25
23
26
31
27
23
28
9
29
24
30
24
31
11
32
27
33
19
34
10
35
12
36
28
37
47
38
16
39
30
40
12
41
13
42
15
43
25
44
9
45
21
46
21
47
76
48
7
49
9
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
90
matches
0
"been tied"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
171
matches
(empty)
98.90%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
2
semicolonCount
0
flaggedSentences
2
totalSentences
130
ratio
0.015
matches
0
"The Raven’s Nest was its usual self—dimly lit, the air thick with the scent of aged wood and whiskey."
1
"Eva looked different—her once vibrant, fiery curls now tamed into sleek, dark waves."
93.20%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
880
adjectiveStacks
1
stackExamples
0
"small crescent-shaped scar"
adverbCount
36
adverbRatio
0.04090909090909091
lyAdverbCount
17
lyAdverbRatio
0.019318181818181818
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
130
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
130
mean
9.88
std
5.7
cv
0.576
sampleLengths
0
19
1
18
2
13
3
9
4
8
5
25
6
13
7
5
8
8
9
17
10
18
11
12
12
5
13
10
14
1
15
9
16
10
17
2
18
13
19
14
20
19
21
9
22
14
23
9
24
15
25
7
26
10
27
9
28
9
29
11
30
3
31
9
32
3
33
9
34
4
35
20
36
3
37
8
38
2
39
9
40
12
41
11
42
20
43
12
44
19
45
8
46
9
47
10
48
23
49
14
46.92%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
4
diversityRatio
0.3
totalSentences
130
uniqueOpeners
39
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
3
totalSentences
85
matches
0
"Then, a slow, hesitant smile"
1
"Finally, Eva spoke, her voice"
2
"Then, with a nod, she"
ratio
0.035
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
17
totalSentences
85
matches
0
"She wasn’t here for the"
1
"She’d grown restless, her thoughts"
2
"She stepped into the bar,"
3
"Her eyes, though still the"
4
"She wore a tailored coat,"
5
"She set her glass down"
6
"She stopped a few feet"
7
"She clenched, her fingers digging"
8
"Her voice cracked, and she"
9
"she admitted quietly"
10
"She ran a hand through"
11
"she said simply"
12
"she admitted softly"
13
"He paused, his hazel eyes"
14
"She stared at the card"
15
"It lingered, waiting for the"
16
"She turned, the card slipping"
ratio
0.2
0.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
80
totalSentences
85
matches
0
"The Raven’s Nest was its"
1
"The green neon sign flickered"
2
"Rory leaned against the bar,"
3
"The ice clinked softly, dissolving"
4
"She wasn’t here for the"
5
"Silas had called her in,"
6
"She’d grown restless, her thoughts"
7
"Time had a way of"
8
"The door creaked open, and"
9
"Rory glanced up, her bright"
10
"The woman paused, her gaze"
11
"Eva’s voice was softer than"
12
"She stepped into the bar,"
13
"Eva looked different—her once vibrant,"
14
"Her eyes, though still the"
15
"She wore a tailored coat,"
16
"Rory’s voice was steady, but"
17
"She set her glass down"
18
"Eva approached slowly, as if"
19
"She stopped a few feet"
ratio
0.941
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
85
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
38
technicalSentenceCount
1
matches
0
"The woman paused, her gaze sweeping the room before landing on Rory."
31.25%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
16
uselessAdditionCount
3
matches
0
"Rory cut, her voice sharp"
1
"Rory said, her voice softer now"
2
"Rory sighed, her gaze drifting to the maps on the wall again"
14.41%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
10
fancyCount
8
fancyTags
0
"she admitted quietly (admit)"
1
"Rory snapped (snap)"
2
"she whispered (whisper)"
3
"she murmured (murmur)"
4
"she admitted (admit)"
5
"Rory muttered (mutter)"
6
"Rory sighed (sigh)"
7
"she admitted softly (admit)"
dialogueSentences
59
tagDensity
0.169
leniency
0.339
rawRatio
0.8
effectiveRatio
0.271
76.5359%