NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHTR0510W93HJ2E7AYW6PBP0
Run Details
Model:
GPT-4o, May 13th (temp=0)
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
13.4s
Cost:
$0.028585
Provider:
Azure
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
79.82%
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)
26.32%
Emotion telling (show vs. tell)
(details)
67.67%
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)
56.79%
Sentence opener variety
(details)
45.05%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
41.08%
Subject-first sentence starts
(details)
67.57%
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)
79.4764%
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
Aurora Carter pushed open the
door to The Raven's Nest, the
familiar
green neon sign casting a soft glow on her face.
She stepped inside, the scent
of aged wood and whiskey wrapping around her like an old,
comforting
blanket.
The dim lighting and the
hum of quiet conversations made the bar
feel
like a
sanctuary
from the bustling streets of Soho.
She made her way to
the counter, her eyes
scanning
the room out of habit.
Silas Blackwood stood behind the
bar, his silver signet ring catching the light as he polished a glass.
He looked up and gave
her a nod, his hazel eyes warm with recognition. "Rory,"
he greeted, his voice a
low rumble. "It's been a while." "Hey, Si,"
she replied, sliding onto a
barstool. "Busy day. Thought I'd unwind here."
Silas placed the glass down
and leaned on the counter, his gaze steady. "You look like you could use a drink. The usual?" "Please." As Silas prepared her drink, Aurora glanced around the bar.
The walls were still adorned
with old maps and black-and-white photographs, each one telling a story of its own.
She felt a pang of
nostalgia, remembering the countless nights she had spent here, seeking refuge from her
chaotic
life.
Silas set the drink in
front of her, and she took a sip, savoring the
familiar
taste. "Thanks, Si." "Anytime, Rory."
The door to the bar
opened again, and Aurora turned to see who had entered.
Her breath caught in her
throat as she recognized the figure standing in the doorway.
It was Eva, her childhood
friend, the one who had convinced her to leave Cardiff and start anew in London. But Eva looked different now.
Her once vibrant red hair
was now a muted auburn, and there was a hardness in her eyes that hadn't been there before.
Eva's gaze swept the room
and landed on Aurora. For a moment, they simply stared at each other, the
weight
of years and
unspoken
words hanging between them. Then, with a hesitant smile, Eva made her way to the bar. "Rory,"
she said, her voice tinged
with surprise. "I didn't expect to see you here." "Eva,"
Aurora replied, her tone carefully
neutral. "It's been a long time."
Eva slid onto the barstool
next to Aurora, her movements graceful yet guarded. "Yeah, it has. How have you been?" Aurora took another sip of her drink, buying herself a moment to gather her thoughts. "I've been... managing. You?" "Same," Eva said, her eyes flicking to Silas, who
was watching
them with a keen interest. "Can I get a whiskey, neat?" Silas nodded and set about preparing the drink. Aurora studied Eva, noting the subtle changes in her friend's appearance. There were faint lines around her eyes, and her posture was more rigid than Aurora remembered.
It was clear that time
had not been kind to either of them. "So,"
Aurora began, her voice soft
. "What brings you to The Raven's Nest?" Eva shrugged, her fingers
tracing
the rim of her glass. "I was in the area and thought I'd stop by. Didn't expect to run into you, though." "Yeah, well, life has a funny way of throwing surprises at us." Silas placed Eva's drink in front of her and retreated to the other end of the bar, giving them some privacy. Eva took a sip of her whiskey, her eyes never leaving Aurora's face. "You've changed,"
Eva said, her tone almost accusatory
. Aurora raised an
eyebrow
. "So have you." Eva let out a bitter laugh. "I suppose we all do, eventually."
They fell into a heavy
silence
, the
weight
of their shared history pressing down on them. Aurora's mind
raced
with memories of their childhood, the laughter and secrets they had shared. But those days felt like a lifetime ago, and the distance between them now
seemed insurmountable
. "Do you ever think about Cardiff?"
Eva asked suddenly, her voice barely above a whisper
. Aurora's grip tightened around her glass. "Sometimes. But it's not the same without you." Eva looked away, her expression pained. "I had to leave, Rory. You know that." "I know,"
Aurora said, her voice cracking
. "But it doesn't make it any easier." Eva's eyes softened, and for a moment, Aurora saw a glimpse of the friend she had once known. "I'm sorry," Eva said, her voice
filled with regret
. "I never meant to hurt you." Aurora swallowed hard, the lump in her throat making it difficult to speak. "I know. I just... I miss the way things used to be." Eva reached out and placed a hand on Aurora's arm, the touch both
comforting
and heartbreaking. "Me too."
They sat in silence, the
noise of the bar fading into the background as they grappled with the
weight
of their past. Aurora felt a tear slip down her cheek, and she
quickly
wiped it away, not wanting to show weakness. "Do you ever wonder what might have been?"
Eva asked, her voice barely audible
. "All the time," Aurora admitted. "But we can't change the past." "No, we can't," Eva agreed. "But maybe we can find a way to move forward." Aurora looked into Eva's eyes, searching for any sign of the friend she had once known. "Do you think we can?" Eva's smile
was sad
but hopeful. "I think we can try." Aurora nodded, feeling
a glimmer of hope
for the first time in years. "Yeah, we can try." They clinked their glasses together, the sound a small but significant gesture of reconciliation. As they drank, Aurora felt the
weight
of the years
begin to
lift, replaced by the possibility of a new beginning. Silas watched them from the other end of the bar, a knowing smile on his lips.
He had seen many reunions
in his time, but this one felt different. There was a
sense of
healing in the air, a promise of better days to come. Aurora and Eva continued to talk, their conversation flowing more easily as the night wore on.
They shared stories of their
lives, the struggles and triumphs that had shaped them into the people they were now. And as they spoke, the distance between them
slowly
began to
close.
By the time the bar
began to
empty, Aurora felt a
sense of
peace she hadn't known in years.
She looked at Eva, her
heart full of gratitude for this unexpected reunion. "Thank you,"
she said, her voice filled
with emotion. "For everything." Eva smiled, her eyes shining with unshed tears. "No, thank you, Rory. For not giving up on me."
They embraced, the hug a
promise of a renewed friendship. As they pulled away, Aurora felt
a sense of hope
for the future, knowing that no matter what lay ahead, they would face it together. Silas approached them, his limp more pronounced after a long night on his feet. "Closing time, ladies." Aurora nodded, feeling a
sense of
contentment she hadn't felt in years. "We'll be going, Si. Thanks for everything." "Anytime, Rory,"
Silas replied, his eyes twinkling with warmth
. "Take care of each other." "We will," Eva said, her voice
filled with determination
. As they left The Raven's Nest, Aurora felt a
sense of
closure and a new beginning all at once. The
weight
of the past had
been lifted
, and she was ready to face whatever the future held, knowing that she had her friend by her side once more.
created_at
"2026-02-19T10:44:13.989Z"
2/19/2026, 10:44:13 AM
model
"openai/gpt-4o-2024-05-13"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
528
moderation_latency
(null)
generation_time
13351
tokens_prompt
1094
tokens_completion
1814
native_tokens_prompt
983
native_tokens_completion
1578
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
0.028585
router
(null)
provider_responses
0
endpoint_id
"ef6b0afa-fd92-4db6-96e0-b8f0e5e4734b"
id
"chatcmpl-DAvnyqKOBN6LDgdLumc16JQ4YQmID"
is_byok
false
latency
215
model_permaslug
"openai/gpt-4o-2024-05-13"
provider_name
"Azure"
status
200
api_type
"completions"
id
"gen-1771497853-fXqZJyRExYawLnATOfKK"
upstream_id
"chatcmpl-DAvnyqKOBN6LDgdLumc16JQ4YQmID"
total_cost
0.028585
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Azure"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
16
adverbTagCount
1
adverbTags
0
"Eva asked suddenly [suddenly]"
dialogueSentences
48
tagDensity
0.333
leniency
0.667
rawRatio
0.063
effectiveRatio
0.042
79.82%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1239
totalAiIsmAdverbs
5
found
0
adverb
"carefully"
count
1
1
adverb
"suddenly"
count
1
2
adverb
"barely above a whisper"
count
1
3
adverb
"quickly"
count
1
4
adverb
"slowly"
count
1
highlights
0
"carefully"
1
"suddenly"
2
"barely above a whisper"
3
"quickly"
4
"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)
0.00%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1239
totalAiIsms
27
found
0
word
"familiar"
count
2
1
word
"comforting"
count
2
2
word
"sanctuary"
count
1
3
word
"scanning"
count
1
4
word
"pang"
count
1
5
word
"chaotic"
count
1
6
word
"weight"
count
5
7
word
"unspoken"
count
1
8
word
"tinged"
count
1
9
word
"tracing"
count
1
10
word
"eyebrow"
count
1
11
word
"silence"
count
2
12
word
"raced"
count
1
13
word
"whisper"
count
1
14
word
"sense of"
count
5
15
word
"warmth"
count
1
highlights
0
"familiar"
1
"comforting"
2
"sanctuary"
3
"scanning"
4
"pang"
5
"chaotic"
6
"weight"
7
"unspoken"
8
"tinged"
9
"tracing"
10
"eyebrow"
11
"silence"
12
"raced"
13
"whisper"
14
"sense of"
15
"warmth"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"flicker of emotion"
count
1
highlights
0
"a glimmer of hope"
26.32%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
9
narrationSentences
76
matches
0
"a pang of nostalgia"
1
"d with surprise"
2
"filled with regret"
3
"d with regret"
4
"was sad"
5
"a sense of hope"
6
"g with warmth"
7
"filled with determination"
8
"d with determination"
67.67%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
3
narrationSentences
76
filterMatches
0
"feel"
hedgeMatches
0
"begin to"
1
"began to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
108
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
1237
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
11
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
72
wordCount
999
uniqueNames
10
maxNameDensity
2.8
worstName
"Aurora"
maxWindowNameDensity
5.5
worstWindowName
"Aurora"
discoveredNames
Carter
1
Raven
2
Nest
2
Soho
1
Blackwood
1
Silas
10
Aurora
28
Eva
25
Cardiff
1
London
1
persons
0
"Carter"
1
"Raven"
2
"Blackwood"
3
"Silas"
4
"Aurora"
5
"Eva"
places
0
"Soho"
1
"Cardiff"
2
"London"
globalScore
0.099
windowScore
0
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
70
glossingSentenceCount
1
matches
0
"seemed insurmountable"
1
"felt like a lifetime ago, and the dista"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1237
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
108
matches
0
"clear that time"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
51
mean
24.25
std
16.18
cv
0.667
sampleLengths
0
62
1
47
2
12
3
14
4
23
5
1
6
49
7
19
8
2
9
78
10
40
11
15
12
12
13
20
14
19
15
22
16
48
17
13
18
27
19
12
20
34
21
8
22
7
23
12
24
47
25
15
26
14
27
14
28
14
29
33
30
25
31
18
32
41
33
14
34
11
35
15
36
21
37
11
38
17
39
35
40
45
41
48
42
32
43
11
44
18
45
35
46
17
47
19
48
14
49
9
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
76
matches
0
"been lifted"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
1
totalVerbs
167
matches
0
"was watching"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
108
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1001
adjectiveStacks
0
stackExamples
(empty)
adverbCount
27
adverbRatio
0.026973026973026972
lyAdverbCount
8
lyAdverbRatio
0.007992007992007992
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
108
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
108
mean
11.45
std
5.96
cv
0.521
sampleLengths
0
22
1
18
2
22
3
15
4
18
5
14
6
8
7
4
8
8
9
6
10
13
11
10
12
1
13
10
14
19
15
20
16
17
17
2
18
2
19
15
20
15
21
20
22
5
23
23
24
9
25
19
26
12
27
8
28
7
29
7
30
5
31
13
32
7
33
15
34
4
35
16
36
6
37
8
38
11
39
16
40
13
41
6
42
7
43
10
44
17
45
12
46
21
47
13
48
8
49
4
56.79%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
2
diversityRatio
0.35185185185185186
totalSentences
108
uniqueOpeners
38
45.05%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
74
matches
0
"Then, with a hesitant smile,"
ratio
0.014
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
19
totalSentences
74
matches
0
"She stepped inside, the scent"
1
"She made her way to"
2
"He looked up and gave"
3
"he greeted, his voice a"
4
"she replied, sliding onto a"
5
"She felt a pang of"
6
"Her breath caught in her"
7
"It was Eva, her childhood"
8
"Her once vibrant red hair"
9
"she said, her voice tinged"
10
"It was clear that time"
11
"They fell into a heavy"
12
"They sat in silence, the"
13
"They clinked their glasses together,"
14
"He had seen many reunions"
15
"They shared stories of their"
16
"She looked at Eva, her"
17
"she said, her voice filled"
18
"They embraced, the hug a"
ratio
0.257
41.08%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
62
totalSentences
74
matches
0
"Aurora Carter pushed open the"
1
"She stepped inside, the scent"
2
"The dim lighting and the"
3
"She made her way to"
4
"Silas Blackwood stood behind the"
5
"He looked up and gave"
6
"he greeted, his voice a"
7
"she replied, sliding onto a"
8
"Silas placed the glass down"
9
"The walls were still adorned"
10
"She felt a pang of"
11
"Silas set the drink in"
12
"The door to the bar"
13
"Her breath caught in her"
14
"It was Eva, her childhood"
15
"Her once vibrant red hair"
16
"Eva's gaze swept the room"
17
"she said, her voice tinged"
18
"Aurora replied, her tone carefully"
19
"Eva slid onto the barstool"
ratio
0.838
67.57%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
74
matches
0
"By the time the bar"
ratio
0.014
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
51
technicalSentenceCount
1
matches
0
"They shared stories of their lives, the struggles and triumphs that had shaped them into the people they were now."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
16
uselessAdditionCount
8
matches
0
"he greeted, his voice a low rumble"
1
"Aurora replied, her tone carefully neutral"
2
"Aurora began, her voice soft"
3
"Eva said, her tone almost accusatory"
4
"Eva asked suddenly, her voice barely above a whisper"
5
"Aurora said, her voice cracking"
6
"Eva asked, her voice barely audible"
7
"Silas replied, his eyes twinkling with warmth"
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
14
fancyCount
2
fancyTags
0
"Aurora admitted (admit)"
1
"Eva agreed (agree)"
dialogueSentences
48
tagDensity
0.292
leniency
0.583
rawRatio
0.143
effectiveRatio
0.083
79.4764%