NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHTQWRW1PG0Y9M5GS5E9J6B1
Run Details
Model:
Qwen 2.5 72B
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
46.0s
Cost:
$0.000748
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
91.78%
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)
0.00%
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)
38.32%
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)
94.71%
Paragraph length variance
(details)
97.80%
Passive voice overuse
(details)
43.14%
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)
39.72%
Sentence opener variety
(details)
0.00%
Adverb-first sentence starts
(details)
49.21%
Pronoun-first sentence starts
(details)
0.00%
Subject-first sentence starts
(details)
56.18%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
0.00%
Dialogue tag variety (said vs. fancy)
(details)
70.3622%
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="4416" name="Detective Harlow Quinn" aliases="Quinn, Detective Quinn, Harlow" pronouns="she/her" species="Human" storyRole="Antagonist"> <eyeColor>brown</eyeColor> <hair>closely cropped salt-and-pepper</hair> <height>5'9"</height> <age>41</age> <jawline>sharp jaw</jawline> <watch>worn leather watch on her left wrist</watch> <bearing>military precision</bearing> <description>A Metropolitan Police detective with 18 years of decorated service who suspects the clique is involved in criminal activity.</description> <backstory>She lost her partner, DS Morris, during a case three years ago under unexplained circumstances that had supernatural origins she doesn't yet understand.</backstory> </character> <character id="4417" name="Tomás Herrera" aliases="Tommy, Tomás, Herrera" pronouns="he/him" species="Human" storyRole="Support"> <eyeColor>warm brown</eyeColor> <hair>short curly dark brown</hair> <height>5'10"</height> <age>29</age> <skinTone>olive skin</skinTone> <scar>scar running along his left forearm from a knife attack</scar> <medallion>Saint Christopher medallion around his neck</medallion> <birthplace>Seville, Spain</birthplace> <description>A former paramedic who provides off-the-books medical care for the clique.</description> <backstory>Born in Seville, Spain. He moved to London to work for the NHS but lost his license after administering unauthorized treatments to supernatural patients.</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> <location id="856" name="The Veil Market" aliases="Veil Market, the Market, underground market" realm="Earth"> <currentLocation>abandoned Tube station beneath Camden</currentLocation> <entryRequirement>bone token</entryRequirement> <schedule>moves locations every full moon</schedule> <description>A hidden supernatural black market that sells enchanted goods, banned alchemical substances, and information.</description> </location> </codex> Continue the story using the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the thriller genre. A detective is pursuing a suspect through rain-soaked city streets at night. The chase takes them from the street level down into an underground market. The detective must decide whether to follow the suspect into unfamiliar and potentially dangerous territory. 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
Rain lashed the streets of
London, turning the asphalt into a river of darkness.
Detective Harlow Quinn's boots pounded
the wet pavement with military precision, her breath coming in controlled bursts.
The suspect, a young man
with a desperate gleam in his eyes, darted through the shadows, his movements erratic and panicky.
Quinn's sharp jaw tightened, her
determination
unwavering
.
She couldn't let him get
away. Not now. Not after what she'd uncovered.
The chase led them through
the winding alleys of Soho, the neon lights flickering and distorted by the downpour.
Quinn's closely cropped salt-and-pepper hair
clung to her forehead, but she barely noticed.
Her eyes were fixed on
the suspect, who
was gaining
ground.
She tightened her grip on
her service revolver, the worn leather of her
watch
strap biting into her wrist. She had to catch him, to find out what he knew. The man turned a corner, and Quinn surged after him, her heart
pounding
.
They were heading toward the
old Underground entrance, the one that led to the Veil Market. Quinn's mind
raced
.
The Veil Market was a
notorious black market for the supernatural, a place where anything could be bought or sold.
It was dangerous, unpredictable, and
she had no jurisdiction down there. But if she didn't follow him, she might lose her only lead.
The suspect plunged into the
abandoned station, and Quinn hesitated for a split second.
She could hear the distant
rumble of trains, the
echo
of
footsteps
, and the faint, eerie glow of light filtering through the darkness. She gritted her teeth.
She couldn't let her hesitation
cost her the case.
She followed him down the
steep, narrow stairs, the metal railings slick with rain. The air grew colder, heavier, as if the
weight
of the city above pressed down on her. The suspect slipped through a narrow doorway, and Quinn pushed it open, her flashlight cutting through the
gloom
. The Veil Market sprawled before her, a labyrinth of makeshift stalls and shadowy figures.
The air was thick with
the scent of incense and the low murmur of hushed conversations. Vendors displayed an array of strange and forbidden items: enchanted amulets, alchemical potions, and ancient relics. Quinn's eyes
scanned
the crowd, her hand steady on her flashlight.
She spotted the suspect weaving
through the aisles, his back hunched
as if trying to melt into the shadows
. "Stay sharp,"
she muttered to herself, her
voice barely a
whisper
.
She moved with caution, her
senses heightened. The ground beneath her feet was uneven, a mix of cobblestones and dirt.
She could feel the eyes
of the market watching her, judging her.
She was an outsider, and
they knew it. The suspect ducked into a narrow alley, and Quinn followed, her flashlight beam
dancing
along the walls. The alley
was lined
with graffiti and makeshift shrines, the air heavy with the smell of damp earth. Quinn's heart
raced
as she caught up to him, her flashlight beam catching him in the corner. "Stop!"
she barked, her voice slicing
through the
silence
. "I know you're hiding something. Talk to me!" The suspect spun around, his eyes wide with fear.
He held something in his
hand, a small, glowing object. Quinn's
eyes narrowed
. It was a bone token, the key to entering the Veil Market. She took a step forward, her hand on her revolver. "Who are you working for?"
she demanded, her voice steely
. "What do you know about the recent disappearances?" The suspect's hands
trembled
, the bone token clutched
tightly
. "I—I don't know anything," he stammered. "Please, you have to believe me." Quinn's sharp jaw tightened. "You're lying,"
she said, her voice cold
. "I can see it in your eyes. Now, tell me the truth, or I will make you regret it." The suspect's face contorted with fear, and he backed away, his eyes darting around for an escape. Quinn's patience
was wearing
thin. She took another step forward, her hand moving to her holster. But before she could draw her weapon, a figure emerged from the shadows, blocking her path. "Detective Quinn," a voice called out,
familiar
yet unwelcome. Quinn's
eyes narrowed
as she recognized the speaker. Tomás Herrera, the former paramedic turned off-the-books healer. He stood there, his olive skin illuminated by the dim light, the Saint Christopher medallion
glinting
around his neck. "What are you doing here, Herrera?"
Quinn demanded, her voice sharp
. "This is police business." Tomás took a step forward, his warm brown eyes steady. "I know what you're chasing, Detective,"
he said, his voice calm
. "But this is more than just a missing person case. You're dealing with something else entirely." Quinn's eyes
flicked
to the suspect, then back to Tomás. "What do you mean?" she asked, her voice
tinged
with suspicion. Tomás's eyes met hers, and for a moment, she saw a glimpse of the
weight
he carried. "The Veil Market isn't just a place for black market deals," he said. "It's a gateway to something deeper, something ancient. And the people here aren't just petty criminals. They're protecting something." Quinn's brow
furrowed
. "Protecting what?"
she asked, her voice low and intense
. Tomás hesitated, his gaze flicking to the suspect. "That bone token he's holding,"
he said, his voice barely above a whisper
. "It's more than just a key. It's a pass to the other side. To a place where the rules are different, where the lines between good and evil blur." Quinn's
eyes widened
. She had heard rumors of such places, but she had never encountered one herself. Her grip on her revolver tightened. "That's impossible,"
she said, her voice firm
. "There's no other side. Just this world." Tomás's eyes held hers, and for a moment, she saw a glimmer of something she couldn't understand. "Believe what you will, Detective," he said. "But if you want to catch your suspect, you need to understand what you're dealing with. The Veil Market is just the beginning." Quinn's mind
raced
. She
could feel
the
weight
of the decision in front of her. Follow the suspect into the unknown, or let him slip away and possibly lose her only lead. She glanced at the suspect, still trembling in the corner, and then back to Tomás. "Fine,"
she said, her voice steely
. "But I'm doing this my way." Tomás nodded, a faint smile playing on his lips. "I wouldn't expect anything less," he said. Quinn turned to the suspect, her face hard. "You're coming with me,"
she said, her voice leaving no room for argument
. "One wrong move, and you'll regret it." The suspect nodded, his hands still trembling. Quinn grabbed him by the arm, pulling him to his feet. She glanced at Tomás, a silent understanding passing between them. She knew she
was stepping
into the unknown, but she couldn't turn back now. Not when the truth was within her grasp. "Lead the way,"
she said, her voice firm
. "We have work to do." Tomás nodded and led the way through the crowded market, his
footsteps
steady and purposeful. Quinn followed, her mind
racing
, the city above a distant memory. She was in new territory now, a place where the rules were different. But she was a detective, and she would find the answers she sought. No matter what it took.
created_at
"2026-02-19T10:42:23.24Z"
2/19/2026, 10:42:23 AM
model
"qwen/qwen-2.5-72b-instruct"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
412
moderation_latency
(null)
generation_time
45932
tokens_prompt
1162
tokens_completion
1835
native_tokens_prompt
1007
native_tokens_completion
1609
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
0.00074835
router
(null)
provider_responses
0
endpoint_id
"8b6b26e9-621a-4b31-b55a-c9aaa7482ede"
id
"cmpl-07ea0b1f50df4a128ae2ade5a306eeb5"
is_byok
false
latency
46
model_permaslug
"qwen/qwen-2.5-72b-instruct"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771497743-rcYdiZKvetisLk89SEx4"
upstream_id
"cmpl-07ea0b1f50df4a128ae2ade5a306eeb5"
total_cost
0.00074835
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
18
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
31
tagDensity
0.581
leniency
1
rawRatio
0
effectiveRatio
0
91.78%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1217
totalAiIsmAdverbs
2
found
0
adverb
"tightly"
count
1
1
adverb
"barely above a whisper"
count
1
highlights
0
"tightly"
1
"barely above a whisper"
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)
0.00%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1217
totalAiIsms
26
found
0
word
"unwavering"
count
1
1
word
"pounding"
count
1
2
word
"raced"
count
3
3
word
"echo"
count
1
4
word
"footsteps"
count
2
5
word
"weight"
count
3
6
word
"gloom"
count
1
7
word
"scanned"
count
1
8
word
"whisper"
count
2
9
word
"could feel"
count
2
10
word
"dancing"
count
1
11
word
"silence"
count
1
12
word
"trembled"
count
1
13
word
"familiar"
count
1
14
word
"glinting"
count
1
15
word
"flicked"
count
1
16
word
"tinged"
count
1
17
word
"furrowed"
count
1
18
word
"racing"
count
1
highlights
0
"unwavering"
1
"pounding"
2
"raced"
3
"echo"
4
"footsteps"
5
"weight"
6
"gloom"
7
"scanned"
8
"whisper"
9
"could feel"
10
"dancing"
11
"silence"
12
"trembled"
13
"familiar"
14
"glinting"
15
"flicked"
16
"tinged"
17
"furrowed"
18
"racing"
0.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
4
maxInWindow
4
found
0
label
"eyes widened/narrowed"
count
3
1
label
"air was thick with"
count
1
highlights
0
"eyes narrowed"
1
"eyes widened"
2
"The air was thick with"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
2
narrationSentences
94
matches
0
"e with fear"
1
"d with fear"
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
0
narrationSentences
94
filterMatches
0
"watch"
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
107
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
29
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1212
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
18
unquotedAttributions
0
matches
(empty)
38.32%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
47
wordCount
985
uniqueNames
11
maxNameDensity
2.23
worstName
"Quinn"
maxWindowNameDensity
3.5
worstWindowName
"Quinn"
discoveredNames
London
1
Harlow
1
Quinn
22
Soho
1
Underground
1
Veil
4
Market
4
Herrera
1
Saint
1
Christopher
1
Tomás
10
persons
0
"Harlow"
1
"Quinn"
2
"Market"
3
"Herrera"
4
"Saint"
5
"Christopher"
6
"Tomás"
places
0
"London"
1
"Soho"
2
"Veil"
globalScore
0.383
windowScore
0.5
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
72
glossingSentenceCount
1
matches
0
"as if trying to melt into the shadows"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1212
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
107
matches
(empty)
94.71%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
30
mean
40.4
std
19.45
cv
0.481
sampleLengths
0
72
1
73
2
75
3
50
4
49
5
76
6
51
7
52
8
17
9
44
10
18
11
21
12
30
13
49
14
44
15
15
16
37
17
21
18
49
19
12
20
50
21
37
22
47
23
47
24
12
25
16
26
28
27
50
28
13
29
57
97.80%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
2
totalSentences
94
matches
0
"were fixed"
1
"was lined"
43.14%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
4
totalVerbs
170
matches
0
"was gaining"
1
"were heading"
2
"was wearing"
3
"was stepping"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
107
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
989
adjectiveStacks
0
stackExamples
(empty)
adverbCount
21
adverbRatio
0.021233569261880688
lyAdverbCount
10
lyAdverbRatio
0.010111223458038422
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
107
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
107
mean
11.33
std
5.21
cv
0.46
sampleLengths
0
14
1
17
2
21
3
7
4
6
5
2
6
5
7
19
8
13
9
11
10
19
11
11
12
13
13
16
14
3
15
20
16
11
17
12
18
14
19
23
20
4
21
9
22
14
23
17
24
18
25
14
26
16
27
16
28
11
29
19
30
11
31
7
32
13
33
12
34
8
35
17
36
18
37
17
38
9
39
8
40
9
41
10
42
3
43
12
44
10
45
10
46
8
47
9
48
6
49
6
39.72%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
11
diversityRatio
0.2897196261682243
totalSentences
107
uniqueOpeners
31
0.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
0
totalSentences
89
matches
(empty)
ratio
0
49.21%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
38
totalSentences
89
matches
0
"She couldn't let him get"
1
"Her eyes were fixed on"
2
"She tightened her grip on"
3
"She had to catch him,"
4
"They were heading toward the"
5
"It was dangerous, unpredictable, and"
6
"She could hear the distant"
7
"She gritted her teeth."
8
"She couldn't let her hesitation"
9
"She followed him down the"
10
"She spotted the suspect weaving"
11
"she muttered to herself, her"
12
"She moved with caution, her"
13
"She could feel the eyes"
14
"She was an outsider, and"
15
"she barked, her voice slicing"
16
"He held something in his"
17
"It was a bone token,"
18
"She took a step forward,"
19
"she demanded, her voice steely"
ratio
0.427
0.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
82
totalSentences
89
matches
0
"Rain lashed the streets of"
1
"Detective Harlow Quinn's boots pounded"
2
"The suspect, a young man"
3
"Quinn's sharp jaw tightened, her"
4
"She couldn't let him get"
5
"The chase led them through"
6
"Quinn's closely cropped salt-and-pepper hair"
7
"Her eyes were fixed on"
8
"She tightened her grip on"
9
"She had to catch him,"
10
"The man turned a corner,"
11
"They were heading toward the"
12
"Quinn's mind raced."
13
"The Veil Market was a"
14
"It was dangerous, unpredictable, and"
15
"The suspect plunged into the"
16
"She could hear the distant"
17
"She gritted her teeth."
18
"She couldn't let her hesitation"
19
"She followed him down the"
ratio
0.921
56.18%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
89
matches
0
"No matter what it took."
ratio
0.011
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
51
technicalSentenceCount
0
matches
(empty)
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
18
uselessAdditionCount
12
matches
0
"she muttered, her voice barely a whisper"
1
"she barked, her voice slicing through the silence"
2
"she demanded, her voice steely"
3
"she said, her voice cold"
4
"Quinn demanded, her voice sharp"
5
"he said, his voice calm"
6
"she asked, her voice low and intense"
7
"he said, his voice barely above a whisper"
8
"she said, her voice firm"
9
"she said, her voice steely"
10
"she said, her voice leaving no room for argument"
11
"she said, her voice firm"
0.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
18
fancyCount
6
fancyTags
0
"she muttered (mutter)"
1
"she barked (bark)"
2
"she demanded (demand)"
3
"he stammered (stammer)"
4
"a voice called out (call out)"
5
"Quinn demanded (demand)"
dialogueSentences
31
tagDensity
0.581
leniency
1
rawRatio
0.333
effectiveRatio
0.333
70.3622%