NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHTQQSNZEZGNZ1B16PE3X4FV
Run Details
Model:
GPT-4o, Aug. 6th (temp=0)
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
28.0s
Cost:
$0.018388
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
83.63%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
9.98%
AI-ism word frequency
(details)
66.67%
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)
100.00%
Name drop frequency
(details)
89.76%
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)
60.66%
Sentence opener variety
(details)
0.00%
Adverb-first sentence starts
(details)
0.00%
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)
19.57%
Dialogue tag variety (said vs. fancy)
(details)
74.3423%
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 low murmur of conversation, the clinking of glasses, and the occasional burst of laughter.
The green neon sign outside
cast a soft glow through the windows, painting the patrons in shades of emerald.
Aurora Carter, known to most
as Rory, slipped through the door, her eyes
scanning
the room with a
practiced ease
.
She wore a leather jacket
over her delivery uniform, the logo of Golden Empress peeking out from beneath.
Her bright blue eyes, sharp
and observant, took in the
familiar
surroundings. She moved towards the bar, her steps confident, yet there was a subtle
tension
in her shoulders.
The weight of the day
clung to her like a second skin. Silas Blackwood, the bar's owner, stood behind the counter, his hazel eyes meeting hers with a knowing
glint
.
He nodded, acknowledging her presence
without words, as he polished a glass with a white cloth. "Evening, Rory,"
he greeted, his voice a
low rumble that matched the bar's ambiance. "Evening, Silas,"
she replied, sliding onto a
stool. "Busy night?" "Steady enough,"
he said, setting the glass
down. "The usual?"
She nodded, and he poured
her a drink, the liquid catching the light as it filled the glass.
Rory took a sip, savoring
the
warmth
that spread through her chest.
She glanced around, her gaze
lingering on the old maps and photographs that adorned the walls. Each one told a story, much like the patrons who frequented the bar. As she turned back to the bar, a figure caught her eye.
A man, seated at the
far end, his back to her.
Something about the way he
held himself, the set of his shoulders, tugged at her memory.
She frowned, trying to place
him, when he turned
slightly
, revealing a profile she hadn't seen in years. Her breath caught. It was Evan.
He looked different, older, the
lines of his face more pronounced.
His hair, once a deep
chestnut, was now streaked with grey. He wore a tailored suit, the fabric expensive and well-fitted, a
stark
contrast to the casual attire she remembered. He
seemed absorbed in thought, his fingers tracing the rim of his glass
. Rory hesitated, the past rushing back with a force that left her momentarily breathless. Memories of laughter, of whispered promises, and the darker times that followed.
She had left that life
behind, or so she thought. Yet here he was, a ghost from her past, sitting in the same bar she frequented. Silas, ever perceptive, followed her gaze. "Old friend?"
he asked, his tone neutral
. "Something like that,"
she replied, her voice steady
despite the turmoil within. Silas nodded, understanding without needing further explanation.
He moved away, giving her
space to decide her next move. Rory took a deep breath, steeling herself. She slid off the stool, her
footsteps
quiet on the wooden floor as she approached Evan. He didn't notice her at first, his attention elsewhere. She stopped a few feet away, her presence finally drawing his gaze. "Evan," she said, her voice carrying a mix of surprise and something else—something unresolved. He looked up, his eyes widening in recognition. "Rory,"
he breathed, the name a whisper on his lips
. "It's been a long time." "Years," she agreed, crossing her arms. "I didn't expect to see you here." "Nor I you,"
he replied, a faint smile tugging at his lips
. "Life's full of surprises, isn't it?" She nodded, unsure of what to say next. The
silence
stretched between them, heavy with
the weight of unspoken words
. "Can I buy you a drink?" he offered, gesturing to the empty seat beside him. She hesitated, then nodded, taking the seat. "Why not?" He signaled to the bartender, ordering another round. As they waited, Rory studied him, noting the changes time had wrought. He seemed more composed, the restless energy she remembered now tempered by experience. "So," he began, breaking the
silence
, "what brings you to London?" "Work," she replied, keeping her answer vague. "And you?" "Business,"
he said, his tone equally noncommittal
. "I travel a lot these days." The drinks arrived, and they each took a sip, the alcohol a welcome distraction from the
tension
between them. "You look well,"
he remarked, his gaze lingering on her face
. "Thanks,"
she said, her voice guarded
. "You too." He chuckled, a sound that held a hint of self-deprecation. "Time hasn't been entirely kind, but I manage." She nodded, unsure of how to respond. The years apart had created a chasm between them, one that couldn't be bridged with small talk. "Do you ever think about Cardiff?"
he asked suddenly, his eyes searching hers
. "Sometimes," she admitted, the memories bittersweet. "It feels like a lifetime ago." "It does,"
he agreed, his expression thoughtful
. "We were different people back then." "Weren't we all?"
she replied, a hint of irony in her voice
. He smiled, a genuine one this time, and for a moment, she glimpsed the man she once knew. "I suppose we were." They fell silent again, the noise of the bar a backdrop to their thoughts. Rory
traced
the rim of her glass, her mind a whirl of emotions. She had moved on, built a new life, yet the past lingered, a shadow that refused to fade. "Rory," Evan said, his voice softer now, "I'm sorry." The words
hung in the air
, unexpected and raw. She met his gaze, seeing the sincerity in his eyes. "For everything,"
he continued, his expression earnest
. "I was young and foolish, and I hurt you. I regret that." She took a deep breath, the apology stirring something within her. "I appreciate that,"
she said, her voice steady
. "But we can't change the past." "No, we can't,"
he agreed, a hint of sadness in his voice
. "But maybe we can learn from it." "Maybe," she allowed, the
tension
between them easing
slightly
. They talked then, the conversation flowing more easily. They spoke of old friends, of places they had visited, of the paths their lives had taken. The years apart had changed them both, yet there was a comfort in the familiarity, in the shared history that bound them. As the night wore on, the bar
began to
empty, the patrons drifting out into the cool London air. Rory glanced at the clock, surprised at how
quickly
time had passed. "I should go," she said, rising from her seat. Evan stood as well, a hint of reluctance in his movements. "It was good to see you, Rory." "You too,"
she replied, a small smile playing on her lips
. They walked to the door together, the night air crisp and refreshing. She paused, turning to face him. "Take care, Evan,"
she said, her voice sincere
. "You too," he replied, his eyes holding hers for a moment longer. With a final nod, she turned and walked away, her
footsteps
echoing
in the quiet street. The past was a part of her, but it no longer defined her. She had her own path to follow, and she intended to do just that. As she disappeared into the night, Evan watched her go, a
sense of
closure settling over him. The years had changed them both, but in that moment, he felt a
sense of
peace. The past was behind them, and the future lay ahead, full of possibilities.
created_at
"2026-02-19T10:39:40.696Z"
2/19/2026, 10:39:40 AM
model
"openai/gpt-4o-2024-08-06"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
829
moderation_latency
(null)
generation_time
27020
tokens_prompt
1094
tokens_completion
1835
native_tokens_prompt
983
native_tokens_completion
1593
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
0.0183875
router
(null)
provider_responses
0
endpoint_id
"9d15935a-34e6-4a5e-a5bc-c7dda213e876"
id
"chatcmpl-DAvjY82iI6fh6aIXCyJAJsi6RFZ5o"
is_byok
false
latency
792
model_permaslug
"openai/gpt-4o-2024-08-06"
provider_name
"OpenAI"
status
200
api_type
"completions"
id
"gen-1771497580-R8KXt8pUplbEyDoQJtdv"
upstream_id
"chatcmpl-DAvjY82iI6fh6aIXCyJAJsi6RFZ5o"
total_cost
0.0183875
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
28
adverbTagCount
1
adverbTags
0
"he asked suddenly [suddenly]"
dialogueSentences
45
tagDensity
0.622
leniency
1
rawRatio
0.036
effectiveRatio
0.036
83.63%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1222
totalAiIsmAdverbs
4
found
0
adverb
"slightly"
count
2
1
adverb
"suddenly"
count
1
2
adverb
"quickly"
count
1
highlights
0
"slightly"
1
"suddenly"
2
"quickly"
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)
9.98%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1222
totalAiIsms
22
found
0
word
"scanning"
count
1
1
word
"practiced ease"
count
1
2
word
"familiar"
count
1
3
word
"tension"
count
3
4
word
"weight"
count
2
5
word
"glint"
count
1
6
word
"warmth"
count
1
7
word
"stark"
count
1
8
word
"tracing"
count
1
9
word
"footsteps"
count
2
10
word
"whisper"
count
1
11
word
"silence"
count
2
12
word
"unspoken"
count
1
13
word
"traced"
count
1
14
word
"echoing"
count
1
15
word
"sense of"
count
2
highlights
0
"scanning"
1
"practiced ease"
2
"familiar"
3
"tension"
4
"weight"
5
"glint"
6
"warmth"
7
"stark"
8
"tracing"
9
"footsteps"
10
"whisper"
11
"silence"
12
"unspoken"
13
"traced"
14
"echoing"
15
"sense of"
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"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
94
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
2
narrationSentences
94
filterMatches
(empty)
hedgeMatches
0
"began to"
1
"tended to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
111
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
22
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1219
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
24
unquotedAttributions
0
matches
(empty)
100.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
22
wordCount
1060
uniqueNames
10
maxNameDensity
0.66
worstName
"Rory"
maxWindowNameDensity
1
worstWindowName
"Rory"
discoveredNames
Raven
1
Nest
1
Carter
1
Rory
7
Golden
1
Empress
1
Blackwood
1
Evan
5
Silas
3
London
1
persons
0
"Raven"
1
"Nest"
2
"Carter"
3
"Rory"
4
"Empress"
5
"Blackwood"
6
"Evan"
7
"Silas"
places
0
"London"
globalScore
1
windowScore
1
89.76%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
83
glossingSentenceCount
2
matches
0
"seemed absorbed in thought, his fingers tracing the rim of his glass"
1
"seemed more composed the restless energy she remembered now tempered by experience"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1219
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
111
matches
0
"left that life"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
52
mean
23.44
std
17.92
cv
0.764
sampleLengths
0
89
1
63
2
14
3
10
4
10
5
59
6
57
7
6
8
54
9
52
10
13
11
12
12
18
13
44
14
14
15
23
16
13
17
18
18
20
19
15
20
9
21
33
22
11
23
9
24
13
25
19
26
11
27
8
28
18
29
24
30
13
31
12
32
13
33
12
34
22
35
45
36
9
37
19
38
19
39
25
40
19
41
9
42
47
43
31
44
9
45
18
46
11
47
18
48
8
49
12
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
94
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
199
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
1
semicolonCount
0
flaggedSentences
1
totalSentences
111
ratio
0.009
matches
0
"\"Evan,\" she said, her voice carrying a mix of surprise and something else—something unresolved."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1063
adjectiveStacks
0
stackExamples
(empty)
adverbCount
30
adverbRatio
0.028222013170272814
lyAdverbCount
8
lyAdverbRatio
0.007525870178739417
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
111
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
111
mean
10.98
std
4.67
cv
0.425
sampleLengths
0
20
1
19
2
20
3
18
4
12
5
17
6
12
7
18
8
16
9
14
10
8
11
2
12
8
13
2
14
18
15
12
16
16
17
13
18
12
19
11
20
16
21
18
22
3
23
3
24
11
25
11
26
19
27
13
28
14
29
12
30
10
31
16
32
6
33
7
34
12
35
7
36
11
37
7
38
16
39
9
40
12
41
14
42
8
43
10
44
5
45
6
46
7
47
12
48
6
49
8
60.66%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
6
diversityRatio
0.3963963963963964
totalSentences
111
uniqueOpeners
44
0.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
0
totalSentences
94
matches
(empty)
ratio
0
0.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
62
totalSentences
94
matches
0
"She wore a leather jacket"
1
"Her bright blue eyes, sharp"
2
"She moved towards the bar,"
3
"He nodded, acknowledging her presence"
4
"he greeted, his voice a"
5
"she replied, sliding onto a"
6
"he said, setting the glass"
7
"She nodded, and he poured"
8
"She glanced around, her gaze"
9
"She frowned, trying to place"
10
"Her breath caught."
11
"It was Evan."
12
"He looked different, older, the"
13
"His hair, once a deep"
14
"He wore a tailored suit,"
15
"He seemed absorbed in thought,"
16
"She had left that life"
17
"he asked, his tone neutral"
18
"she replied, her voice steady"
19
"He moved away, giving her"
ratio
0.66
0.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
88
totalSentences
94
matches
0
"The Raven's Nest hummed with"
1
"The green neon sign outside"
2
"Aurora Carter, known to most"
3
"She wore a leather jacket"
4
"Her bright blue eyes, sharp"
5
"She moved towards the bar,"
6
"The weight of the day"
7
"Silas Blackwood, the bar's owner,"
8
"He nodded, acknowledging her presence"
9
"he greeted, his voice a"
10
"she replied, sliding onto a"
11
"he said, setting the glass"
12
"She nodded, and he poured"
13
"Rory took a sip, savoring"
14
"She glanced around, her gaze"
15
"Each one told a story,"
16
"A man, seated at the"
17
"Something about the way he"
18
"She frowned, trying to place"
19
"Her breath caught."
ratio
0.936
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
94
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
52
technicalSentenceCount
3
matches
0
"She glanced around, her gaze lingering on the old maps and photographs that adorned the walls."
1
"Rory hesitated, the past rushing back with a force that left her momentarily breathless."
2
"He chuckled, a sound that held a hint of self-deprecation."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
28
uselessAdditionCount
17
matches
0
"he greeted, his voice a low rumble that matched the bar's ambiance"
1
"he asked, his tone neutral"
2
"she replied, her voice steady despite the turmoil within"
3
"he breathed, the name a whisper on his lips"
4
"he replied, a faint smile tugging at his lips"
5
"he said, his tone equally noncommittal"
6
"he remarked, his gaze lingering on her face"
7
"she said, her voice guarded"
8
"he asked suddenly, his eyes searching hers"
9
"he agreed, his expression thoughtful"
10
"she replied, a hint of irony in her voice"
11
"Evan said, his voice softer now,"
12
"he continued, his expression earnest"
13
"she said, her voice steady"
14
"he agreed, a hint of sadness in his voice"
15
"she replied, a small smile playing on her lips"
16
"she said, her voice sincere"
19.57%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
23
fancyCount
6
fancyTags
0
"he breathed (breathe)"
1
"she agreed (agree)"
2
"she admitted (admit)"
3
"he agreed (agree)"
4
"he continued (continue)"
5
"he agreed (agree)"
dialogueSentences
45
tagDensity
0.511
leniency
1
rawRatio
0.261
effectiveRatio
0.261
74.3423%