NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHTQQSNYGTDH4G1YJ8ADG3NB
Run Details
Model:
GPT-4o, May 13th (temp=0)
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
9.5s
Cost:
$0.026695
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
77.06%
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)
66.67%
Cliché density
(details)
83.33%
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)
78.32%
Name drop frequency
(details)
73.08%
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)
94.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
66.96%
Sentence opener variety
(details)
42.19%
Adverb-first sentence starts
(details)
7.34%
Pronoun-first sentence starts
(details)
10.63%
Subject-first sentence starts
(details)
63.29%
Subordinate conjunction sentence starts
(details)
99.57%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
78.7480%
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. The bar was dimly lit, the walls adorned with old maps and black-and-white
photographs that seemed to whisper stories of the past
. She took a deep breath, the scent of aged wood and whiskey filling her lungs, and stepped inside.
Silas Blackwood stood behind the
bar, his grey-streaked auburn hair catching the light as he polished a glass.
He looked up, his hazel
eyes meeting hers, and a small smile tugged at the corners of his mouth. "Rory,"
he greeted, his voice warm
and gravelly. "It's been a while." "Hey, Si,"
she replied, her own smile
mirroring his. "Thought I'd drop by for a drink." "Always welcome here,"
he said, setting the glass
down and reaching for a bottle of whiskey. "The usual?" "Yeah, thanks." As Silas poured her drink, Aurora
scanned
the room. It was a quiet night, a few regulars scattered at the tables, lost in their own worlds.
She took a seat at
the bar, her eyes lingering on the hidden bookshelf door that led to the secret room.
Memories of clandestine meetings and
whispered conversations flooded her mind.
Silas slid the glass across
the bar to her. "How's life treating you?" "Same old,"
she replied, taking a sip
.
The whiskey burned pleasantly down
her throat. "Delivering food, trying to keep my head above water." He nodded, his gaze thoughtful. "You always were a fighter."
Before she could respond, the
door swung open again, and a figure stepped inside.
Aurora's heart skipped a beat
as she recognized the tall, broad-shouldered man with sandy hair and piercing green eyes. It was Evan, her ex.
The man she had left
behind in Cardiff. Evan's eyes
scanned
the room, landing on her. For a moment, they both froze,
the weight of unspoken words
hanging heavy in the air.
Then, he walked over, his
steps
measured
and deliberate. "Rory,"
he said, his voice a
mix of surprise and something else she couldn't
quite place
. "It's been a long time." "Evan,"
she replied, her voice steady
despite the turmoil inside. "What brings you to London?" "Work,"
he said, taking a seat
next to her. "Got transferred here a few months ago. Didn't expect to run into you." "Small world,"
she said, taking another sip
of her drink. Silas watched the exchange with a keen eye, his presence a
comforting
anchor in the storm of emotions swirling around her. "So, how have you been?"
Evan asked, his tone casual but his eyes searching
. "Good,"
she replied, meeting his gaze
. "Busy. You?" "Same,"
he said, a hint of
a smile on his lips. "Life's been... interesting."
They fell into an uneasy
silence
, the years of separation and the pain of their past hanging between them like a ghost. Silas cleared his throat, breaking the
tension
. "Can I get you a drink, mate?" "Sure," Evan said, glancing at the menu. "I'll have a pint of lager." As Silas moved to pour the drink, Aurora turned to Evan. "So, what kind of work brought you here?" "Corporate law,"
he said, his tone almost
apologetic. "
Not exactly thrilling, but it pays the bills
." "Sounds... stable,"
she said, her voice tinged
with irony.
He chuckled, a sound that
was both
familiar
and foreign. "Yeah, I guess it is." Silas placed the pint in front of Evan, giving Aurora a reassuring nod before moving to attend to another customer. Evan took a sip of his beer, his eyes never leaving hers. "You look good, Rory. Different, but good." "Thanks,"
she said, her fingers tracing the rim of her glass
. "You too." He leaned back, studying her. "I heard about what happened with your dad. I'm sorry." She nodded, the memory of her father's passing still a raw wound. "Thanks. It was... hard." "I can imagine," he said
softly
. "He was a good man." "Yeah, he was,"
she agreed, her voice barely above a whisper
. They lapsed into
silence
again, the noise of the bar fading into the background. Aurora's mind
raced
, memories of their time together flashing before her eyes. The good times, the laughter, the love. And the bad times, the arguments, the pain. "Do you ever think about Cardiff?"
Evan asked suddenly, his voice breaking the spell
. "Sometimes," she admitted. "But it's in the past. I've moved on." "Have you?"
he asked, his eyes searching hers
. She met his gaze, her heart
pounding
. "Yes, I have." He nodded, a shadow of regret passing over his face. "I guess I haven't." The admission
hung in the air
, heavy and
unspoken
. Aurora felt
a pang of sympathy
for him, but also
a sense of relief
. She had made the right choice, leaving him and the life they had built together. "I'm sorry, Evan," she said
softly
. "But I can't go back." "I know,"
he said, his voice resigned
. "I just... I had to see you. To know that you're okay." "I'm okay," she assured him. "Better than okay, actually." He smiled, a genuine smile that reached his eyes. "I'm glad to hear that." They sat in
silence
for a while, the
weight
of their past
slowly
lifting. Aurora felt a
sense of
closure, a chapter of her life finally coming to an end. Silas returned, his presence a
comforting
reminder
of the life she had built in London. "Everything alright here?" "Yeah," Aurora said, smiling at him. "Everything's fine." Evan stood, finishing his beer. "I should go. It was good seeing you, Rory." "You too, Evan," she said, standing as well. "Take care of yourself." "You too," he said, giving her one last look before turning and walking out of the bar. Aurora watched him go, a
sense of
peace settling over her. She turned back to Silas, who
was watching
her with a knowing look. "Closure?" he asked, raising an
eyebrow
. "Yeah,"
she said, smiling
. "Closure." Silas nodded, a small smile playing on his lips. "Good. You deserve it." Aurora took a deep breath, feeling lighter than she had in years. She raised her glass to Silas, a silent toast to new beginnings. "To the future," she said, her voice
filled with hope
. "To the future," Silas
echoed
, clinking his glass against hers. As they drank, Aurora felt a
sense of
contentment wash over her. The past was behind her, and the future was full of possibilities. And for the first time in a long time, she felt ready to embrace it.
created_at
"2026-02-19T10:39:40.718Z"
2/19/2026, 10:39:40 AM
model
"openai/gpt-4o-2024-05-13"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
202
moderation_latency
(null)
generation_time
8834
tokens_prompt
1094
tokens_completion
1637
native_tokens_prompt
983
native_tokens_completion
1452
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
0.026695
router
(null)
provider_responses
0
endpoint_id
"3d6584e7-a2bb-48d6-903d-24e3d90e7e55"
id
"chatcmpl-DAvjYvLrECYofOU6LKI5FPAB2zJg9"
is_byok
false
latency
193
model_permaslug
"openai/gpt-4o-2024-05-13"
provider_name
"OpenAI"
status
200
api_type
"completions"
id
"gen-1771497580-t1pN87aBSEDw8Gb3OHGQ"
upstream_id
"chatcmpl-DAvjYvLrECYofOU6LKI5FPAB2zJg9"
total_cost
0.026695
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
30
adverbTagCount
3
adverbTags
0
"he said softly [softly]"
1
"Evan asked suddenly [suddenly]"
2
"she said softly [softly]"
dialogueSentences
65
tagDensity
0.462
leniency
0.923
rawRatio
0.1
effectiveRatio
0.092
77.06%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1090
totalAiIsmAdverbs
5
found
0
adverb
"softly"
count
2
1
adverb
"barely above a whisper"
count
1
2
adverb
"suddenly"
count
1
3
adverb
"slowly"
count
1
highlights
0
"softly"
1
"barely above a whisper"
2
"suddenly"
3
"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
1090
totalAiIsms
31
found
0
word
"familiar"
count
2
1
word
"whisper"
count
2
2
word
"scanned"
count
2
3
word
"clandestine"
count
1
4
word
"skipped a beat"
count
1
5
word
"weight"
count
2
6
word
"unspoken"
count
2
7
word
"measured"
count
1
8
word
"comforting"
count
2
9
word
"silence"
count
3
10
word
"tension"
count
1
11
word
"tinged"
count
1
12
word
"tracing"
count
1
13
word
"raced"
count
1
14
word
"pounding"
count
1
15
word
"pang"
count
1
16
word
"sense of"
count
4
17
word
"reminder"
count
1
18
word
"eyebrow"
count
1
19
word
"echoed"
count
1
highlights
0
"familiar"
1
"whisper"
2
"scanned"
3
"clandestine"
4
"skipped a beat"
5
"weight"
6
"unspoken"
7
"measured"
8
"comforting"
9
"silence"
10
"tension"
11
"tinged"
12
"tracing"
13
"raced"
14
"pounding"
15
"pang"
16
"sense of"
17
"reminder"
18
"eyebrow"
19
"echoed"
66.67%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
2
maxInWindow
2
found
0
label
"weight of words/silence"
count
1
1
label
"hung in the air"
count
1
highlights
0
"the weight of unspoken words"
1
"hung in the air"
83.33%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
4
narrationSentences
80
matches
0
"a pang of sympathy"
1
"a sense of relief"
2
"filled with hope"
3
"d with hope"
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
2
narrationSentences
80
filterMatches
(empty)
hedgeMatches
0
"seemed to"
1
"tend to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
115
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
24
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1086
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
28
unquotedAttributions
0
matches
(empty)
78.32%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
39
wordCount
837
uniqueNames
9
maxNameDensity
1.43
worstName
"Silas"
maxWindowNameDensity
2.5
worstWindowName
"Silas"
discoveredNames
Carter
1
Raven
1
Nest
1
Blackwood
1
Silas
12
Aurora
12
Evan
9
Cardiff
1
London
1
persons
0
"Carter"
1
"Blackwood"
2
"Silas"
3
"Aurora"
4
"Evan"
places
0
"Raven"
1
"Cardiff"
2
"London"
globalScore
0.783
windowScore
0.833
73.08%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
65
glossingSentenceCount
2
matches
0
"photographs that seemed to whisper stories of the past"
1
"quite place"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.921
wordCount
1086
matches
0
"Not exactly thrilling, but it pays the bills"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
115
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
59
mean
18.41
std
11.9
cv
0.647
sampleLengths
0
62
1
37
2
12
3
16
4
18
5
2
6
57
7
13
8
23
9
10
10
46
11
33
12
21
13
15
14
22
15
10
16
21
17
14
18
8
19
14
20
22
21
14
22
13
23
19
24
16
25
9
26
15
27
20
28
19
29
13
30
15
31
16
32
11
33
11
34
41
35
14
36
11
37
8
38
10
39
14
40
38
41
11
42
19
43
9
44
14
45
30
46
18
47
8
48
14
49
12
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
80
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
1
totalVerbs
153
matches
0
"was watching"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
115
ratio
0
matches
(empty)
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
841
adjectiveStacks
1
stackExamples
0
"tall, broad-shouldered man"
adverbCount
19
adverbRatio
0.022592152199762187
lyAdverbCount
9
lyAdverbRatio
0.01070154577883472
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
115
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
115
mean
9.44
std
5.04
cv
0.533
sampleLengths
0
22
1
22
2
18
3
18
4
19
5
8
6
4
7
9
8
7
9
16
10
2
11
2
12
9
13
17
14
21
15
10
16
9
17
4
18
7
19
7
20
9
21
5
22
5
23
14
24
19
25
5
26
8
27
8
28
16
29
9
30
16
31
5
32
10
33
5
34
9
35
13
36
10
37
21
38
14
39
6
40
2
41
11
42
3
43
22
44
7
45
7
46
7
47
6
48
11
49
8
66.96%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
3
diversityRatio
0.41739130434782606
totalSentences
115
uniqueOpeners
48
42.19%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
79
matches
0
"Then, he walked over, his"
ratio
0.013
7.34%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
42
totalSentences
79
matches
0
"She took a deep breath,"
1
"He looked up, his hazel"
2
"he greeted, his voice warm"
3
"she replied, her own smile"
4
"he said, setting the glass"
5
"It was a quiet night,"
6
"She took a seat at"
7
"she replied, taking a sip"
8
"He nodded, his gaze thoughtful."
9
"It was Evan, her ex."
10
"he said, his voice a"
11
"she replied, her voice steady"
12
"he said, taking a seat"
13
"she said, taking another sip"
14
"she replied, meeting his gaze"
15
"he said, a hint of"
16
"They fell into an uneasy"
17
"he said, his tone almost"
18
"she said, her voice tinged"
19
"He chuckled, a sound that"
ratio
0.532
10.63%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
71
totalSentences
79
matches
0
"Aurora Carter pushed open the"
1
"The bar was dimly lit,"
2
"She took a deep breath,"
3
"Silas Blackwood stood behind the"
4
"He looked up, his hazel"
5
"he greeted, his voice warm"
6
"she replied, her own smile"
7
"he said, setting the glass"
8
"It was a quiet night,"
9
"She took a seat at"
10
"Memories of clandestine meetings and"
11
"Silas slid the glass across"
12
"she replied, taking a sip"
13
"The whiskey burned pleasantly down"
14
"He nodded, his gaze thoughtful."
15
"Aurora's heart skipped a beat"
16
"It was Evan, her ex."
17
"The man she had left"
18
"Evan's eyes scanned the room,"
19
"he said, his voice a"
ratio
0.899
63.29%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
79
matches
0
"Before she could respond, the"
ratio
0.013
99.57%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
33
technicalSentenceCount
2
matches
0
"The bar was dimly lit, the walls adorned with old maps and black-and-white photographs that seemed to whisper stories of the past."
1
"She took a seat at the bar, her eyes lingering on the hidden bookshelf door that led to the secret room."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
30
uselessAdditionCount
12
matches
0
"he greeted, his voice warm and gravelly"
1
"she replied, her own smile mirroring his"
2
"she replied, her voice steady despite the turmoil inside"
3
"Evan asked, his tone casual but his eyes searching"
4
"he said, a hint of a smile on his lips"
5
"he said, his tone almost apologetic"
6
"she said, her fingers tracing the rim of her glass"
7
"she agreed, her voice barely above a whisper"
8
"Evan asked suddenly, his voice breaking the spell"
9
"he asked, his eyes searching hers"
10
"he said, his voice resigned"
11
"she said, smiling"
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
28
fancyCount
3
fancyTags
0
"she agreed (agree)"
1
"she admitted (admit)"
2
"she assured (assure)"
dialogueSentences
65
tagDensity
0.431
leniency
0.862
rawRatio
0.107
effectiveRatio
0.092
78.7480%