NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-17-01KHMPB5V6RKEW9YH98JMF6P32
Run Details
Model:
Qwen 2.5 72B
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
30.4s
Cost:
$0.000699
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
69.41%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
8.22%
AI-ism word frequency
(details)
100.00%
Cliché density
(details)
99.75%
Emotion telling (show vs. tell)
(details)
99.57%
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)
99.95%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
100.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
54.95%
Sentence opener variety
(details)
50.51%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
20.61%
Subject-first sentence starts
(details)
100.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
83.4313%
Overall
Model input
System
You are an expert novelist with a gift for vivid, immersive prose. You write in tight third-person limited point of view with a strong narrative voice. Your prose is clean, precise, and engaging — you favor strong verbs, concrete details, and natural-sounding dialogue. You will be given a story bible (codex) containing canonical details about characters, locations, items, and lore. Use these details to ground your writing in the established world. Stay consistent with the codex. Write only the prose of the scene. Do not include titles, chapter headings, markdown formatting, or any commentary before or after the scene.
User/Human
<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> 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.
Model response
Messages
Meta
AI
The Raven's Nest was as
cozy and dim as Aurora remembered, the air thick with the scent of old wood and the faint hint of tobacco.
The neon green sign flickered
softly
above the door, casting a ghostly glow on the cobblestones.
She pushed open the heavy
oak door and stepped inside, the bell above ringing with a
familiar
chime.
The bar was quiet, a
stark
contrast to the bustling streets of Soho.
Only a few patrons lingered
at the long mahogany bar, their faces half-hidden in shadows.
Aurora's eyes adjusted to the
dim light, and she spotted Silas Blackwood, the bar owner, polishing a glass behind the counter.
His grey-streaked auburn hair and
neatly trimmed beard made him
look
more distinguished than the grizzled spy he once was. "Rory,"
Silas greeted, his hazel eyes
crinkling at the corners as he set the glass down. "You're back early."
Aurora nodded, her voice barely
above a
whisper
. "Had a quick delivery. Thought I'd grab a drink." Silas nodded, his expression softening. "The usual?" "Sure,"
she replied, sliding onto a
stool. "It's been a long day."
Silas poured her a glass
of dark amber whiskey, the liquid catching the light as it flowed.
Just as Aurora took a
sip, a
familiar
voice cut through the quiet of the bar. "Aurora Carter? Is that you?"
Aurora turned, her breath catching
in her throat. Standing in the doorway was a woman she hadn't seen in years—Eva.
Her hair was a cascade
of gold, cut shorter than Aurora remembered, and her eyes were the same intense green. But there was something different about her, a
newfound
confidence that radiated from every pore. "Eva,"
Aurora breathed, rising from her
stool. "It's been so long."
Eva crossed the room in
a few swift strides and pulled Aurora into a tight hug.
The embrace was warm, a
reminder
of the bond they once shared.
Aurora felt a lump form
in her throat, the
weight
of time and
unspoken
words pressing down on her. "God, it's good to see you,"
Eva said, pulling back and
squeezing Aurora's shoulders. "How have you been?"
Aurora forced a smile, her
bright blue eyes meeting Eva's. "I've been okay. Just working at the restaurant, you know. How about you? Where have you been?"
Eva's expression faltered for a
moment, her eyes flickering with a hint of guilt. "I've been... around. Travelling, mostly. I've seen a lot of the world." Silas watched the exchange from behind the bar, his gaze sharp but unobtrusive.
He knew the history between
the two women, the
unspoken
tension
that had always existed even in their better days. "Can I get you something to drink, Eva?"
Silas asked, his voice smooth and even
. Eva nodded, sitting down next to Aurora. "A Scotch on the rocks, please." Silas nodded and turned to
tend to
the drink. Aurora and Eva sat in
silence
for a moment, the
weight
of the past heavy between them. Aurora's fingers
traced
the condensation on her glass, the cool surface a soothing distraction. "So, what have you been up to?"
Aurora asked, trying to keep her tone light
. "You disappeared for a while. We all thought you'd dropped off the face of the earth." Eva's gaze darkened, and she took a deep breath. "I had to get away, Rory. From everything. From the city, from the people, from the... memories." Aurora nodded, understanding the pain that underlay Eva's words. She remembered the dark days, the nights when Eva's smile
was forced
and her laughter hollow. The memories of their shared apartment, the late-night conversations, and the whispered fears that lingered in the shadows. "I get it," Aurora said
softly
. "Sometimes you just need to go. To find yourself, I guess." Eva's eyes were a mix of gratitude and regret. "You have no idea. I've seen things, done things... I've changed, Rory. Maybe more than you." Silas placed the Scotch on the rocks in front of Eva, breaking the somber mood with a small nod. Eva took a sip, the liquor burning a path down her throat. "You've changed too,"
Eva said, her voice softer now
. "You
look
... stronger. More grounded." Aurora smiled, the corners of her mouth tugging up
reluctantly
. "I've had to be. Life has a way of shaping you, doesn't it?" Eva nodded, her fingers tightening around the glass. "It does." The two women sat in
silence
for a while, each lost in their own thoughts. Aurora's mind drifted back to the days when they were inseparable, when the future was full of possibilities and the world seemed within reach.
She remembered the late-night phone
calls, the shared secrets, and the unbreakable bond they once shared. "What brought you back to London?" Aurora asked, breaking the
silence
. Eva's eyes
flickered
with a hint of sadness. "A job. A new start, I hope. I need to do something different, something that doesn't leave me feeling... hollow." Aurora nodded, her heart aching with empathy. "I know the feeling. Sometimes, it feels like we're just going through the motions, you know? Like we're not
really
living." Eva's gaze met Aurora's, and for a moment, the years fell away.
They were just two friends
again, sharing a moment of honesty and vulnerability. "Rory, I'm sorry,"
Eva said, her voice breaking
. "For everything. For leaving without a word, for the things I did, for the person I became." Aurora reached out and placed a hand on Eva's arm, her touch gentle but firm. "You don't have to apologize, Eva. We both made choices. We both have our regrets." Eva's eyes glistened with unshed tears, and she nodded. "But it's important to acknowledge them, isn't it?" Aurora smiled, her bright blue eyes warm with understanding. "It is. It's the only way to move forward." Silas watched the exchange from behind the bar, his expression
unreadable
.
He knew the power of
forgiveness and the healing that comes from facing the past.
He refilled Aurora's glass, his
eyes meeting hers briefly before he turned away. The two women sat in the dim light of The Raven's Nest, their conversation a mix of laughter and tears, of shared memories and
unspoken
truths. As the night grew late, they found a renewed connection, a bridge across the chasm of time that had grown between them.
Before leaving, Eva hugged Aurora
tightly
once more, her voice filled with sincerity. "Thank you, Rory. For everything." Aurora smiled, her heart lighter than it had been in years. "Anytime, Eva. We're in this together, always." As Eva left the bar, Aurora watched her go, a
sense of
peace settling over her.
She finished her whiskey, the
warmth
spreading through her as she reflected on the evening. Some wounds healed
slowly
, but they did heal. And in the quiet moments, in the company of old friends, the light of hope shone bright.
created_at
"2026-02-17T02:20:22.205853+00:00"
2/17/2026, 2:20:22 AM
model
"qwen/qwen-2.5-72b-instruct"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
145
moderation_latency
(null)
generation_time
30156
tokens_prompt
889
tokens_completion
1718
native_tokens_prompt
834
native_tokens_completion
1535
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
0.00069873
router
(null)
provider_responses
0
id
"cmpl-aed81a2fcf524d5cb337c2ee53fb5444"
status
200
is_byok
false
latency
72
endpoint_id
"8b6b26e9-621a-4b31-b55a-c9aaa7482ede"
provider_name
"DeepInfra"
model_permaslug
"qwen/qwen-2.5-72b-instruct"
api_type
"completions"
id
"gen-1771294791-aVw21UMfwepQzMQV3kt7"
upstream_id
"cmpl-aed81a2fcf524d5cb337c2ee53fb5444"
total_cost
0.00069873
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
10
adverbTagCount
1
adverbTags
0
"Aurora said softly [softly]"
dialogueSentences
35
tagDensity
0.286
leniency
0.571
rawRatio
0.1
effectiveRatio
0.057
69.41%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1144
totalAiIsmAdverbs
7
found
0
adverb
"softly"
count
2
1
adverb
"barely above a whisper"
count
1
2
adverb
"reluctantly"
count
1
3
adverb
"really"
count
1
4
adverb
"tightly"
count
1
5
adverb
"slowly"
count
1
highlights
0
"softly"
1
"barely above a whisper"
2
"reluctantly"
3
"really"
4
"tightly"
5
"slowly"
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)
8.22%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1144
totalAiIsms
21
found
0
word
"flickered"
count
2
1
word
"familiar"
count
2
2
word
"stark"
count
1
3
word
"whisper"
count
1
4
word
"newfound"
count
1
5
word
"reminder"
count
1
6
word
"weight"
count
2
7
word
"unspoken"
count
3
8
word
"tension"
count
1
9
word
"silence"
count
3
10
word
"traced"
count
1
11
word
"unreadable"
count
1
12
word
"sense of"
count
1
13
word
"warmth"
count
1
highlights
0
"flickered"
1
"familiar"
2
"stark"
3
"whisper"
4
"newfound"
5
"reminder"
6
"weight"
7
"unspoken"
8
"tension"
9
"silence"
10
"traced"
11
"unreadable"
12
"sense of"
13
"warmth"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
0
maxInWindow
0
found
(empty)
highlights
(empty)
99.75%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
2
narrationSentences
66
matches
0
"felt a lump"
1
"g with empathy"
99.57%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
1
narrationSentences
66
filterMatches
0
"look"
hedgeMatches
0
"tend to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
91
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
1143
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
9
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
66
wordCount
855
uniqueNames
8
maxNameDensity
3.27
worstName
"Aurora"
maxWindowNameDensity
5
worstWindowName
"Aurora"
discoveredNames
Raven
2
Nest
2
Aurora
28
Soho
1
Silas
9
Blackwood
1
Eva
22
Scotch
1
persons
0
"Raven"
1
"Aurora"
2
"Silas"
3
"Blackwood"
4
"Eva"
places
0
"Soho"
globalScore
0
windowScore
0
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
62
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1143
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
91
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
41
mean
27.88
std
15.53
cv
0.557
sampleLengths
0
60
1
69
2
19
3
17
4
7
5
12
6
33
7
5
8
55
9
11
10
47
11
18
12
27
13
26
14
33
15
15
16
13
17
40
18
31
19
26
20
43
21
17
22
25
23
31
24
14
25
23
26
10
27
55
28
11
29
28
30
28
31
25
32
25
33
30
34
17
35
18
36
39
37
48
38
18
39
18
40
56
99.95%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
66
matches
0
"was forced"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
135
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
1
semicolonCount
0
flaggedSentences
1
totalSentences
91
ratio
0.011
matches
0
"Standing in the doorway was a woman she hadn't seen in years—Eva."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
860
adjectiveStacks
0
stackExamples
(empty)
adverbCount
25
adverbRatio
0.029069767441860465
lyAdverbCount
10
lyAdverbRatio
0.011627906976744186
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
91
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
91
mean
12.56
std
5.39
cv
0.429
sampleLengths
0
26
1
16
2
18
3
13
4
15
5
21
6
20
7
16
8
3
9
8
10
9
11
5
12
2
13
7
14
5
15
17
16
16
17
5
18
8
19
12
20
20
21
15
22
7
23
4
24
16
25
12
26
19
27
14
28
4
29
10
30
17
31
14
32
12
33
13
34
20
35
15
36
7
37
6
38
9
39
17
40
14
41
15
42
16
43
9
44
17
45
9
46
16
47
18
48
6
49
11
54.95%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
5
diversityRatio
0.3626373626373626
totalSentences
91
uniqueOpeners
33
50.51%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
66
matches
0
"Only a few patrons lingered"
ratio
0.015
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
11
totalSentences
66
matches
0
"She pushed open the heavy"
1
"His grey-streaked auburn hair and"
2
"she replied, sliding onto a"
3
"Her hair was a cascade"
4
"He knew the history between"
5
"She remembered the dark days,"
6
"She remembered the late-night phone"
7
"They were just two friends"
8
"He knew the power of"
9
"He refilled Aurora's glass, his"
10
"She finished her whiskey, the"
ratio
0.167
20.61%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
58
totalSentences
66
matches
0
"The Raven's Nest was as"
1
"The neon green sign flickered"
2
"She pushed open the heavy"
3
"The bar was quiet, a"
4
"Aurora's eyes adjusted to the"
5
"His grey-streaked auburn hair and"
6
"Silas greeted, his hazel eyes"
7
"Aurora nodded, her voice barely"
8
"Silas nodded, his expression softening."
9
"she replied, sliding onto a"
10
"Silas poured her a glass"
11
"Aurora turned, her breath catching"
12
"Her hair was a cascade"
13
"Aurora breathed, rising from her"
14
"Eva crossed the room in"
15
"The embrace was warm, a"
16
"Aurora felt a lump form"
17
"Eva said, pulling back and"
18
"Aurora forced a smile, her"
19
"Eva's expression faltered for a"
ratio
0.879
100.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
2
totalSentences
66
matches
0
"Just as Aurora took a"
1
"Before leaving, Eva hugged Aurora"
ratio
0.03
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
42
technicalSentenceCount
2
matches
0
"But there was something different about her, a newfound confidence that radiated from every pore."
1
"The memories of their shared apartment, the late-night conversations, and the whispered fears that lingered in the shadows."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
10
uselessAdditionCount
4
matches
0
"Silas asked, his voice smooth and even"
1
"Aurora asked, trying to keep her tone light"
2
"Eva said, her voice softer now"
3
"Eva said, her voice breaking"
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
9
fancyCount
1
fancyTags
0
"Aurora breathed (breathe)"
dialogueSentences
35
tagDensity
0.257
leniency
0.514
rawRatio
0.111
effectiveRatio
0.057
83.4313%