NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHTRGQG706A0SJRS10PZNN42
Run Details
Model:
Qwen 2.5 72B
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
35.8s
Cost:
$0.000731
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
95.81%
AI-ism adverb frequency
(details)
80.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
0.00%
AI-ism word frequency
(details)
100.00%
Cliché density
(details)
96.75%
Emotion telling (show vs. tell)
(details)
94.43%
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)
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)
54.51%
Sentence opener variety
(details)
0.00%
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)
0.00%
Useless dialogue additions
(details)
92.86%
Dialogue tag variety (said vs. fancy)
(details)
77.1454%
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 hummed with
the murmur of conversation and the clink of glasses.
The dim light cast long
shadows on the walls, where old maps and black-and-white photographs gave the bar a
sense of
history and depth.
The air was thick with
the scent of aged wood and a hint of smoke, despite the smoking ban.
Aurora Carter, known to her
friends as Rory, pushed open the door, the distinctive green neon sign above it flickering to life as she stepped inside.
Her eyes adjusted to the
semi-darkness, and she
scanned
the room for
familiar
faces.
The bar was bustling, as
it always was, but there was one figure at the far end who caught her attention.
It was Silas Blackwood, the
owner of the bar, leaning against the counter, his hazel eyes surveying the room with a quiet authority. He nodded in her direction, a small smile playing at the corners of his mouth.
Rory made her way through
the crowd, her black hair falling in straight, shoulder-length waves around her face, and took a seat next to him. "Evening, Rory,"
Silas said, his voice a
mix of gravel and
warmth
. "The usual?" She nodded. "Thanks, Si."
Silas poured her a glass
of whiskey, the amber liquid swirling in the glass as he set it down in front of her.
She took a sip, letting
the
familiar
burn slide down her throat. As she set the glass back down, her gaze landed on a figure sitting alone at a corner table.
It was a woman with
a shock of red hair, her eyes hidden behind dark glasses. Rory's heart
skipped a beat
.
She had seen that hair
before, years ago. "Eva,"
she whispered, almost to herself
.
Silas followed her gaze and
raised an
eyebrow
. "Seems like destiny's giving you a surprise tonight." Rory hesitated for a moment, then pushed herself off the stool and made her way across the room.
The woman at the table
looked up as she approached, and the dark glasses slipped off, revealing a pair of deep, green eyes.
Eva's face was different—older, more
pronounced lines around her mouth and eyes, but the same fiery spirit still lingered. "Rory," Eva said, her voice a mix of surprise and something else Rory couldn't
quite place
. "It's been a long time." Rory pulled up a chair and sat down, the
weight
of the years settling between them. "It has," she agreed. "How have you been?" Eva's lips curved into a small, wry smile. "I've been ... a lot. What about you? Losing yourself in the city, as usual?" Rory laughed, a short, sharp sound that felt almost foreign. "Something like that. Work, deliveries, the usual grind. What about you? Last I heard, you were off to Paris." "Ah, Paris,"
Eva said, her eyes taking on a faraway look
. "It was a beautiful city. But it wasn't meant to be a permanent home. Life has a way of pulling you in different directions." Silas appeared at the table, a glass of red wine in his hand.
He set it down in
front of Eva and gave her a nod. "Good to see you, Eva. You're looking well." Eva smiled at him, a genuine, warm smile that lit up her face. "Thanks, Silas. You haven't changed a bit." Silas chuckled. "Neither have you, darling. Now, if you'll excuse me, I have a bar to run."
He disappeared back into the
crowd, leaving the two women alone again. Rory took a deep breath and looked at Eva, trying to find the words to bridge the gap of time and
silence
between them. "So, what brought you back to London?"
Rory asked, her voice steady but tinged with curiosity
. Eva swirled the wine in her glass, her expression thoughtful. "A job. A new start, I hope. I've been traveling a lot, but I needed to settle down. London felt like ... a good place to start over." Rory nodded, understanding the pull of the
familiar
. "I get that. This city has a way of drawing you back, no matter how far you go."
They fell into a comfortable
silence
, each lost in their own thoughts. The bar was a place of refuge, a haven from the chaos of the outside world. Rory sipped her whiskey, the
warmth
spreading through her, and Eva sipped her wine, the gentle clink of the glass against the table the only sound between them. "Remember when we used to sneak into this place?" Eva said, breaking the
silence
. "Silas would always catch us, but he never kicked us out. He just shook his head and told us to behave." Rory laughed, the memory bringing a smile to her face. "Those were the days. We were so young and reckless." Eva nodded, a wistful smile playing at her lips. "We were. And now here we are, years later, sitting in the same bar, but so much has changed." Rory's smile faded, and she met Eva's gaze. "It has. People change, don't they?" Eva's green eyes searched Rory's face, and for a moment, the
tension
between them was almost
palpable
. "You've changed, Rory. You're ... different." Rory shifted in her seat, the
weight
of Eva's words settling on her shoulders. "I know. I had to. Things happened. People happened. I couldn't stay the same." Eva's expression softened. "I can't blame you for that. We all have our reasons. But I'm glad you're here. I've missed ... this." Rory
felt a lump
form in her throat, the
unspoken
words hanging between them. "I've missed you too, Eva. More than you know."
They sat in silence for
a moment, the
weight
of their
unspoken
regrets and the years that had passed thick in the air. The bar around them
seemed to
fade away, leaving only the two of them and the ghosts of their past. "I'm sorry, Rory,"
Eva said, her voice barely above a whisper
. "For everything. For being gone when you needed me. For all the things I didn't say." Rory's breath caught in her throat, and she reached out, her hand finding Eva's. "I know. And I'm sorry too. For pushing you away. For not reaching out. We were kids,
Evans
. We made mistakes." Eva's hand tightened around Rory's, and for a moment, the world around them ceased to exist. The past and the present blurred together, and they were just two old friends, finding their way back to each other. "It's not too late, you know," Eva said, her voice filled with a
newfound
determination. "To make things right. To start over." Rory felt
a wave of hope
wash over her, and she smiled, a genuine, heartfelt smile. "No, it's not. Let's do it,
Evans
. Let's start over." Eva's eyes sparkled, and she raised her glass in a toast. "To new beginnings." Rory clinked her glass against Eva's, and they both took a sip, the
warmth
of the alcohol and the
warmth
of their reunited friendship spreading through them. The bar continued to hum around them, but for Rory and Eva, the world had narrowed down to this moment, this table, and the promise of a new beginning.
created_at
"2026-02-19T10:53:17.196Z"
2/19/2026, 10:53:17 AM
model
"qwen/qwen-2.5-72b-instruct"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
362
moderation_latency
(null)
generation_time
35727
tokens_prompt
1115
tokens_completion
1698
native_tokens_prompt
1012
native_tokens_completion
1562
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
0.00073062
router
(null)
provider_responses
0
endpoint_id
"8b6b26e9-621a-4b31-b55a-c9aaa7482ede"
id
"cmpl-c747c432cdfb43bdbd9682d570ff4b26"
is_byok
false
latency
52
model_permaslug
"qwen/qwen-2.5-72b-instruct"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771498397-iPflTKu01SC30vHoTFPd"
upstream_id
"cmpl-c747c432cdfb43bdbd9682d570ff4b26"
total_cost
0.00073062
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
9
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
35
tagDensity
0.257
leniency
0.514
rawRatio
0
effectiveRatio
0
95.81%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1194
totalAiIsmAdverbs
1
found
0
adverb
"barely above a whisper"
count
1
highlights
0
"barely above a whisper"
80.00%
AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0
"Blackwood"
found
0
"Evans"
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
1194
totalAiIsms
26
found
0
word
"sense of"
count
1
1
word
"scanned"
count
1
2
word
"familiar"
count
3
3
word
"warmth"
count
4
4
word
"skipped a beat"
count
1
5
word
"eyebrow"
count
1
6
word
"weight"
count
3
7
word
"silence"
count
4
8
word
"tinged"
count
1
9
word
"comfortable"
count
1
10
word
"tension"
count
1
11
word
"palpable"
count
1
12
word
"unspoken"
count
2
13
word
"whisper"
count
1
14
word
"newfound"
count
1
highlights
0
"sense of"
1
"scanned"
2
"familiar"
3
"warmth"
4
"skipped a beat"
5
"eyebrow"
6
"weight"
7
"silence"
8
"tinged"
9
"comfortable"
10
"tension"
11
"palpable"
12
"unspoken"
13
"whisper"
14
"newfound"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"air was thick with"
count
1
highlights
0
"The air was thick with"
96.75%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
2
narrationSentences
59
matches
0
"felt a lump"
1
"a wave of hope"
94.43%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
1
narrationSentences
59
filterMatches
0
"look"
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
85
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
1193
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
10
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
53
wordCount
843
uniqueNames
7
maxNameDensity
2.61
worstName
"Eva"
maxWindowNameDensity
5
worstWindowName
"Eva"
discoveredNames
Raven
1
Nest
1
Carter
1
Rory
21
Silas
6
Blackwood
1
Eva
22
persons
0
"Raven"
1
"Nest"
2
"Carter"
3
"Rory"
4
"Silas"
5
"Blackwood"
6
"Eva"
places
(empty)
globalScore
0.195
windowScore
0
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
52
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
1193
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
85
matches
0
"seen that hair"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
38
mean
31.39
std
20.11
cv
0.641
sampleLengths
0
83
1
98
2
14
3
4
4
83
5
6
6
16
7
60
8
21
9
24
10
23
11
29
12
35
13
34
14
20
15
17
16
36
17
16
18
38
19
26
20
56
21
35
22
20
23
28
24
14
25
23
26
28
27
23
28
23
29
43
30
27
31
35
32
37
33
22
34
26
35
14
36
27
37
29
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
59
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
124
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
1
semicolonCount
0
flaggedSentences
1
totalSentences
85
ratio
0.012
matches
0
"Eva's face was different—older, more pronounced lines around her mouth and eyes, but the same fiery spirit still lingered."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
848
adjectiveStacks
0
stackExamples
(empty)
adverbCount
19
adverbRatio
0.02240566037735849
lyAdverbCount
3
lyAdverbRatio
0.003537735849056604
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
85
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
85
mean
14.04
std
6.9
cv
0.491
sampleLengths
0
14
1
24
2
19
3
26
4
14
5
21
6
23
7
15
8
25
9
12
10
2
11
2
12
2
13
23
14
12
15
19
16
16
17
5
18
8
19
6
20
8
21
8
22
18
23
23
24
19
25
16
26
5
27
16
28
4
29
4
30
8
31
15
32
10
33
19
34
11
35
24
36
13
37
13
38
8
39
13
40
7
41
2
42
15
43
12
44
24
45
16
46
10
47
28
48
8
49
18
54.51%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
2
diversityRatio
0.3411764705882353
totalSentences
85
uniqueOpeners
29
0.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
0
totalSentences
56
matches
(empty)
ratio
0
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
11
totalSentences
56
matches
0
"Her eyes adjusted to the"
1
"It was Silas Blackwood, the"
2
"He nodded in her direction,"
3
"She took a sip, letting"
4
"It was a woman with"
5
"She had seen that hair"
6
"she whispered, almost to herself"
7
"He set it down in"
8
"He disappeared back into the"
9
"They fell into a comfortable"
10
"They sat in silence for"
ratio
0.196
0.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
55
totalSentences
56
matches
0
"The Raven's Nest hummed with"
1
"The dim light cast long"
2
"The air was thick with"
3
"Aurora Carter, known to her"
4
"Her eyes adjusted to the"
5
"The bar was bustling, as"
6
"It was Silas Blackwood, the"
7
"He nodded in her direction,"
8
"Rory made her way through"
9
"Silas said, his voice a"
10
"Silas poured her a glass"
11
"She took a sip, letting"
12
"It was a woman with"
13
"Rory's heart skipped a beat."
14
"She had seen that hair"
15
"she whispered, almost to herself"
16
"Silas followed her gaze and"
17
"Rory hesitated for a moment,"
18
"The woman at the table"
19
"Eva's face was different—older, more"
ratio
0.982
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
56
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
40
technicalSentenceCount
0
matches
(empty)
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
9
uselessAdditionCount
5
matches
0
"Silas said, his voice a mix of gravel and warmth"
1
"she whispered, almost to herself"
2
"Eva said, her eyes taking on a faraway look"
3
"Rory asked, her voice steady but tinged with curiosity"
4
"Eva said, her voice barely above a whisper"
92.86%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
9
fancyCount
2
fancyTags
0
"she whispered (whisper)"
1
"she agreed (agree)"
dialogueSentences
35
tagDensity
0.257
leniency
0.514
rawRatio
0.222
effectiveRatio
0.114
77.1454%