NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-17-01KHMMC98CNQQ5QV52KKNTD18J
Run Details
Model:
GPT-4o, May 13th (temp=0)
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
9.0s
Cost:
$0.024550
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
85.56%
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)
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)
87.50%
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)
94.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
57.10%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
41.62%
Pronoun-first sentence starts
(details)
20.81%
Subject-first sentence starts
(details)
0.00%
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)
79.5530%
Overall
Model input
System
You are an expert novelist with a gift for vivid, immersive prose. You write in tight third-person limited point of view with a strong narrative voice. Your prose is clean, precise, and engaging — you favor strong verbs, concrete details, and natural-sounding dialogue. You will be given a story bible (codex) containing canonical details about characters, locations, items, and lore. Use these details to ground your writing in the established world. Stay consistent with the codex. Write only the prose of the scene. Do not include titles, chapter headings, markdown formatting, or any commentary before or after the scene.
User/Human
<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> 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.
Model response
Messages
Meta
AI
Aurora Carter pushed open the
heavy wooden door of The Raven's Nest, the
familiar
creak of its hinges a welcome sound.
The dim lighting inside was
a
stark
contrast to the garish neon of Soho's streets, and she paused for a moment to let her eyes adjust.
The bar was just as
she remembered: walls adorned with old maps and black-and-white photographs, the air thick with the scent of aged wood and whiskey.
She glanced up at the
distinctive green neon sign above the entrance, a
beacon
that had guided her here more times than she could count.
Silas Blackwood stood behind the
bar, his grey-streaked auburn hair catching the low light. He
was polishing
a glass, his movements slow and deliberate.
His hazel eyes flicked up
as she entered, and a small smile tugged at the corners of his mouth. "Rory,"
he greeted, his voice a
gravelly rumble. "It's been a while." "Too long, Si,"
she replied, making her way
to the bar. She slid onto a stool, the leather creaking beneath her. "How's the knee?"
Silas chuckled, a sound like
dry leaves rustling. "Still attached, last I checked. What brings you here tonight?" "Just needed a drink,"
she said, her eyes scanning
the room. "And maybe some company."
Silas nodded, setting the polished
glass down and reaching for a bottle of whiskey.
He poured her a generous
measure, sliding the glass across the bar. "On the house." "Thanks,"
she said, lifting the glass
to her lips.
The whiskey burned pleasantly as
it went down, warming her from the inside out.
She set the glass down
and sighed, the
weight
of the day settling on her shoulders. The door creaked open 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 flee to London all those years ago. But Eva had changed.
Her once vibrant red hair
was now a muted auburn, and there were lines around her eyes that hadn't been there before. She looked older, wearier. Eva's eyes
scanned
the room, landing on Aurora. For a moment, they just stared at each other, the
weight
of years and
unspoken
words hanging between them. Then Eva smiled, a small, tentative thing, and made her way to the bar. "Rory,"
she said, her voice soft
. "It's been a long time." "Eva,"
Aurora replied, her own voice barely above a whisper
. "It has." Silas, sensing the
tension
, excused himself to the back room, leaving the two women alone. Aurora gestured to the stool beside her, and Eva sat down, her movements slow and deliberate. "You look good," Eva said, her eyes taking in Aurora's straight shoulder-length black hair and bright blue eyes. "Different, but good." "Thanks,"
Aurora replied, her fingers tracing the rim of her glass
. "You too."
They sat in silence for
a moment, the sounds of the bar around them a distant hum. Finally, Eva spoke. "I heard about Evan,"
she said, her voice barely
above a
whisper
. "I'm so sorry, Rory." Aurora's grip tightened on her glass, the small crescent-shaped scar on her left wrist catching the light. "It's in the past,"
she said, her voice steady
. "I'm moving on." Eva nodded, her eyes filled with
unspoken
regret. "I should have been there for you,"
she said, her voice breaking
. "I should have done more." "You did what you could,"
Aurora replied, her voice softening
. "You got me out of there. That's more than enough." Eva looked down at her hands, her fingers twisting together. "I just... I wish things had been different." "Me too,"
Aurora said, her voice barely above a whisper
. "But we can't change the past."
They sat in silence for
a moment, the
weight
of their shared history hanging between them.
Finally, Eva looked up, her
eyes meeting Aurora's. "Do you remember the summer we spent at the lake?"
she asked, a small smile tugging at her lips
. "We thought we were so grown up, sneaking out at night to swim." Aurora laughed, the sound light and free. "I remember. We got caught by your dad, and he made us clean the entire cabin as punishment." Eva laughed too, the sound like music. "We were so mad at him, but looking back, it was one of the best summers of my life." "Mine too,"
Aurora said, her smile fading
. "I miss those days." "Me too,"
Eva said, her voice soft
. "But we're here now, and that's what matters." Aurora nodded, her eyes meeting Eva's. "Yeah, we're here."
They sat in silence for
a moment, the
weight
of their shared history hanging between them. Finally, Aurora spoke. "So, what brings you to London?"
she asked, her voice curious
. Eva sighed, her shoulders slumping. "I needed a change,"
she said, her voice tired
. "Things back home... they weren't working out." Aurora nodded, understanding all too well. "Well, you're here now,"
she said, her voice steady
. "And you've got me." Eva smiled, a small, tentative thing. "Thanks, Rory. That means a lot."
They sat in silence for
a moment, the
weight
of their shared history hanging between them. Finally, Aurora spoke. "Do you want to get out of here?"
she asked, her voice soft
. "We could go for a walk, catch up." Eva nodded, her eyes brightening. "I'd like that." They stood, leaving their glasses on the bar. Aurora glanced back at Silas, who
was watching
them from the doorway to the back room. He gave her a small nod, and she smiled in return. "Let's go," she said, leading the way to the door. They stepped out into the cool night air, the sounds of Soho around them. For a moment, they just stood there, taking it all in. "Where to?"
Eva asked, her voice curious
. "Anywhere,"
Aurora replied, her voice steady
. "As long as we're together." They walked down the street, their
footsteps
echoing
in the night. The
weight
of time and
unspoken
regret hung between them, but for the first time in years, Aurora felt
a glimmer of hope
. They couldn't change the past, but they could face the future together. And that was enough.
created_at
"2026-02-17T01:45:40.391831+00:00"
2/17/2026, 1:45:40 AM
model
"openai/gpt-4o-2024-05-13"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
374
moderation_latency
(null)
generation_time
8388
tokens_prompt
867
tokens_completion
1540
native_tokens_prompt
809
native_tokens_completion
1367
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
0.02455
router
(null)
provider_responses
0
id
"chatcmpl-DA4RXYoyVPHTBTYsrBKl3ZVgji2b9"
status
200
is_byok
false
latency
358
endpoint_id
"3d6584e7-a2bb-48d6-903d-24e3d90e7e55"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-4o-2024-05-13"
api_type
"completions"
id
"gen-1771292730-Xj9tsUoLQes63sUnh4qB"
upstream_id
"chatcmpl-DA4RXYoyVPHTBTYsrBKl3ZVgji2b9"
total_cost
0.02455
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
23
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
50
tagDensity
0.46
leniency
0.92
rawRatio
0
effectiveRatio
0
85.56%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1039
totalAiIsmAdverbs
3
found
0
adverb
"barely above a whisper"
count
3
highlights
0
"barely above a whisper"
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
1039
totalAiIsms
26
found
0
word
"familiar"
count
1
1
word
"stark"
count
1
2
word
"beacon"
count
1
3
word
"flicked"
count
1
4
word
"scanning"
count
1
5
word
"weight"
count
6
6
word
"scanned"
count
1
7
word
"unspoken"
count
3
8
word
"whisper"
count
3
9
word
"tension"
count
1
10
word
"tracing"
count
1
11
word
"silence"
count
4
12
word
"footsteps"
count
1
13
word
"echoing"
count
1
highlights
0
"familiar"
1
"stark"
2
"beacon"
3
"flicked"
4
"scanning"
5
"weight"
6
"scanned"
7
"unspoken"
8
"whisper"
9
"tension"
10
"tracing"
11
"silence"
12
"footsteps"
13
"echoing"
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"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
74
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
74
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
101
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
28
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1039
ratio
0
matches
(empty)
87.50%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
20
unquotedAttributions
3
matches
0
"Finally, Eva spoke."
1
"Finally, Aurora spoke."
2
"Finally, Aurora spoke."
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
53
wordCount
791
uniqueNames
10
maxNameDensity
2.53
worstName
"Aurora"
maxWindowNameDensity
5
worstWindowName
"Aurora"
discoveredNames
Carter
1
Raven
1
Nest
1
Soho
2
Blackwood
1
Silas
5
Aurora
20
Eva
17
London
1
Finally
4
persons
0
"Carter"
1
"Raven"
2
"Blackwood"
3
"Silas"
4
"Aurora"
5
"Eva"
places
0
"Soho"
1
"London"
globalScore
0.236
windowScore
0
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
54
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1039
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
101
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
42
mean
24.74
std
17.48
cv
0.706
sampleLengths
0
98
1
43
2
12
3
24
4
18
5
15
6
29
7
39
8
78
9
41
10
11
11
12
12
31
13
21
14
13
15
20
16
16
17
29
18
25
19
20
20
18
21
16
22
24
23
32
24
25
25
26
26
11
27
15
28
9
29
19
30
11
31
21
32
19
33
12
34
19
35
21
36
8
37
35
38
35
39
7
40
11
41
50
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
74
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
2
totalVerbs
140
matches
0
"was polishing"
1
"was watching"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
101
ratio
0
matches
(empty)
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
796
adjectiveStacks
1
stackExamples
0
"small crescent-shaped scar"
adverbCount
19
adverbRatio
0.02386934673366834
lyAdverbCount
9
lyAdverbRatio
0.011306532663316583
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
101
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
101
mean
10.29
std
5.8
cv
0.564
sampleLengths
0
21
1
26
2
26
3
25
4
14
5
10
6
19
7
8
8
4
9
11
10
10
11
3
12
8
13
10
14
11
15
4
16
14
17
12
18
3
19
9
20
14
21
16
22
13
23
15
24
20
25
4
26
22
27
4
28
8
29
19
30
14
31
6
32
5
33
10
34
2
35
15
36
16
37
18
38
3
39
11
40
2
41
17
42
3
43
12
44
4
45
17
46
9
47
3
48
8
49
12
57.10%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
4
diversityRatio
0.36633663366336633
totalSentences
101
uniqueOpeners
37
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
5
totalSentences
74
matches
0
"Then Eva smiled, a small,"
1
"Finally, Eva spoke."
2
"Finally, Eva looked up, her"
3
"Finally, Aurora spoke."
4
"Finally, Aurora spoke."
ratio
0.068
41.62%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
33
totalSentences
74
matches
0
"She glanced up at the"
1
"He was polishing a glass,"
2
"His hazel eyes flicked up"
3
"he greeted, his voice a"
4
"she replied, making her way"
5
"She slid onto a stool,"
6
"she said, her eyes scanning"
7
"He poured her a generous"
8
"she said, lifting the glass"
9
"She set the glass down"
10
"Her breath caught in her"
11
"It was Eva, her childhood"
12
"Her once vibrant red hair"
13
"She looked older, wearier."
14
"she said, her voice soft"
15
"They sat in silence for"
16
"she said, her voice barely"
17
"she said, her voice steady"
18
"she said, her voice breaking"
19
"They sat in silence for"
ratio
0.446
20.81%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
65
totalSentences
74
matches
0
"Aurora Carter pushed open the"
1
"The dim lighting inside was"
2
"The bar was just as"
3
"She glanced up at the"
4
"Silas Blackwood stood behind the"
5
"He was polishing a glass,"
6
"His hazel eyes flicked up"
7
"he greeted, his voice a"
8
"she replied, making her way"
9
"She slid onto a stool,"
10
"Silas chuckled, a sound like"
11
"she said, her eyes scanning"
12
"Silas nodded, setting the polished"
13
"He poured her a generous"
14
"she said, lifting the glass"
15
"The whiskey burned pleasantly as"
16
"She set the glass down"
17
"The door creaked open again,"
18
"Her breath caught in her"
19
"It was Eva, her childhood"
ratio
0.878
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
74
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
33
technicalSentenceCount
1
matches
0
"She glanced up at the distinctive green neon sign above the entrance, a beacon that had guided her here more times than she could count."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
23
uselessAdditionCount
19
matches
0
"he greeted, his voice a gravelly rumble"
1
"she said, her eyes scanning the room"
2
"she said, her voice soft"
3
"Aurora replied, her own voice barely above a whisper"
4
"Aurora replied, her fingers tracing the rim of her glass"
5
"she said, her voice barely above a whisper"
6
"she said, her voice steady"
7
"she said, her voice breaking"
8
"Aurora replied, her voice softening"
9
"Aurora said, her voice barely above a whisper"
10
"she asked, a small smile tugging at her lips"
11
"Aurora said, her smile fading"
12
"Eva said, her voice soft"
13
"she asked, her voice curious"
14
"she said, her voice tired"
15
"she said, her voice steady"
16
"she asked, her voice soft"
17
"Eva asked, her voice curious"
18
"Aurora replied, her voice steady"
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
22
fancyCount
0
fancyTags
(empty)
dialogueSentences
50
tagDensity
0.44
leniency
0.88
rawRatio
0
effectiveRatio
0
79.5530%