NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHMPBCH58PHG7XK2TR2STMKF
Run Details
Model:
GPT-4o, Aug. 6th (temp=0)
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
13.2s
Cost:
$0.014977
Provider:
Azure
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="4416" name="Detective Harlow Quinn" aliases="Quinn, Detective Quinn, Harlow" pronouns="she/her" species="Human" storyRole="Antagonist"> <eyeColor>brown</eyeColor> <hair>closely cropped salt-and-pepper</hair> <height>5'9"</height> <age>41</age> <jawline>sharp jaw</jawline> <watch>worn leather watch on her left wrist</watch> <bearing>military precision</bearing> <description>A Metropolitan Police detective with 18 years of decorated service who suspects the clique is involved in criminal activity.</description> <backstory>She lost her partner, DS Morris, during a case three years ago under unexplained circumstances that had supernatural origins she doesn't yet understand.</backstory> </character> <character id="4417" name="Tomás Herrera" aliases="Tommy, Tomás, Herrera" pronouns="he/him" species="Human" storyRole="Support"> <eyeColor>warm brown</eyeColor> <hair>short curly dark brown</hair> <height>5'10"</height> <age>29</age> <skinTone>olive skin</skinTone> <scar>scar running along his left forearm from a knife attack</scar> <medallion>Saint Christopher medallion around his neck</medallion> <birthplace>Seville, Spain</birthplace> <description>A former paramedic who provides off-the-books medical care for the clique.</description> <backstory>Born in Seville, Spain. He moved to London to work for the NHS but lost his license after administering unauthorized treatments to supernatural patients.</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> <location id="856" name="The Veil Market" aliases="Veil Market, the Market, underground market" realm="Earth"> <currentLocation>abandoned Tube station beneath Camden</currentLocation> <entryRequirement>bone token</entryRequirement> <schedule>moves locations every full moon</schedule> <description>A hidden supernatural black market that sells enchanted goods, banned alchemical substances, and information.</description> </location> </codex> Write a fully fleshed out scene of at least 1000 words in the thriller genre. A detective is pursuing a suspect through rain-soaked city streets at night. The chase takes them from the street level down into an underground market. The detective must decide whether to follow the suspect into unfamiliar and potentially dangerous territory. 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
Rain lashed the streets of Soho, turning the pavement into a slick, reflective surface that mirrored the neon glow of The Raven's Nest. Detective Harlow Quinn stood beneath the bar's distinctive green sign, her sharp jaw set with determination. The rain had soaked through her coat, but she barely noticed. Her eyes, dark and focused, scanned the street for any sign of her quarry. The suspect had slipped out of the bar moments before, a shadowy figure darting into the night. Quinn had been close, too close to let him vanish now. She adjusted the worn leather
watch
on her left wrist, a habit she had picked up from her late partner, DS Morris. The memory of him, and the case that had taken him, fueled her resolve. She caught a glimpse of movement—a flash of a dark coat disappearing around the corner. Quinn set off, her steps precise and purposeful, her mind a
calculated
machine. The rain pounded against her, but she moved with the unyielding precision of a soldier on a mission. The streets were nearly deserted, the usual bustle of Soho subdued by the downpour. Quinn's breath came in steady puffs, visible in the cold night air. She rounded the corner, her eyes narrowing as she spotted the suspect again, his silhouette briefly illuminated by a streetlamp before he plunged into the shadows of an alley. Quinn quickened her pace, her senses heightened. The alley was narrow, the walls closing in with a claustrophobic intimacy. She could hear the distant hum of the city, the rain a constant percussion against the backdrop of her pursuit. The suspect was fast, but Quinn was relentless. She followed him through the maze of alleys, her mind mapping the route with the precision of a seasoned detective. She
was gaining
on him, the distance between them shrinking with every stride. Suddenly, the suspect veered left, disappearing into a doorway that led down into the depths of the city. Quinn hesitated for a fraction of a second, her instincts screaming caution. She knew the stories of the underground, the whispers of places that existed beneath the surface, hidden from the eyes of the uninitiated. But she couldn't let him get away. Not now. Quinn descended the stairs, her
footsteps
echoing
in the confined space. The air grew cooler, the sounds of the city fading as she ventured deeper. She reached the bottom, finding herself in a dimly lit corridor that stretched out before her like a tunnel into another world. The Veil Market. She had heard of it, the tales of a hidden supernatural black market that moved with the cycles of the moon. It
was said
to be a place of danger and intrigue, where the lines between reality and the arcane blurred. Quinn's
heart pounded in her chest
, but she pressed on, her determination
unwavering
. She could see the suspect ahead, his figure a shadow against the
flicker
ing lights of the market. He moved with purpose, weaving through the crowd that thronged the underground space. The market was a
cacophony
of sights and sounds, a
surreal
blend of the familiar and the fantastical. Stalls lined the walls, their wares displayed with a casual disregard for legality. Enchanted goods glimmered under the dim lights, and
the air was thick with
the scent of alchemical substances. Quinn pushed through the crowd, her eyes locked on the suspect. He
was heading
deeper into the market, towards a section that seemed even more shadowed, more secretive. She could feel the eyes of the market's denizens on her, their gazes curious and wary. As she moved, she caught sight of a familiar face—Tomás Herrera, the former paramedic turned underground healer. He stood by a stall, his warm brown eyes meeting hers with
a flicker of recognition
. He nodded subtly, a silent acknowledgment of her presence in this hidden world. Quinn pressed on, her focus unbroken. The suspect was close now, his path leading him towards a heavy curtain that marked the entrance to a more secluded area of the market. She hesitated, the
weight
of the decision pressing down on her. To follow him meant stepping further into the unknown, into a realm where the rules she knew might not apply. But to let him go was unthinkable. She had come too far, risked too much. With a deep breath, Quinn pushed through the curtain, her senses on high alert. The space beyond was dimly lit, the air thick with the scent of incense and something more elusive, something
otherworldly
. The suspect was there, his back to her as he spoke in hushed tones with a figure cloaked in shadows. Quinn moved closer, her
footsteps
silent on the worn stone floor. She could hear snippets of their conversation, words that hinted at secrets and deals that defied the mundane. Her presence was soon noticed, the suspect turning to face her with a look of surprise and something akin to respect. He knew she had followed him, that she had dared to enter this place. "Detective Quinn," he said, his voice smooth and unhurried. "I didn't expect you to be so... persistent." Quinn met his gaze, her own
unwavering
. "You should have known better," she replied, her voice steady. "Now, why don't you tell me what you're doing here?" The figure in the shadows shifted, their presence a silent reminder of the danger that lurked in this place. Quinn could feel the tension in the air, the
unspoken
threat that hung between them. But she stood her ground, her resolve unshaken. She had come this far, and she would see it through. Whatever secrets the Veil Market held, whatever truths lay hidden in its depths, she
was determined
to uncover them. The suspect smiled, a slow,
calculating
expression that spoke of secrets and shadows. "Perhaps we can come to an understanding," he said, his words a
tantalizing
promise. Quinn's
eyes narrowed
, her mind racing with possibilities. She knew the risks, the dangers that lay in making deals in a place like this. But she also knew the value of information, the power it held. As the rain continued to fall above, a relentless rhythm against the city streets, Detective Harlow Quinn stood at the crossroads of choice and consequence, her path uncertain but her purpose clear.
created_at
"2026-02-17T02:20:11.873117+00:00"
2/17/2026, 2:20:11 AM
model
"openai/gpt-4o-2024-08-06"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
798
moderation_latency
(null)
generation_time
13082
tokens_prompt
914
tokens_completion
1573
native_tokens_prompt
811
native_tokens_completion
1295
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
0.0149775
router
(null)
provider_responses
0
id
"chatcmpl-DA4ysnP198I8gwwNk6cjlNhj3e0KT"
status
200
is_byok
false
latency
384
endpoint_id
"59ea8d2a-1b1b-47f1-83de-a358a724caeb"
provider_name
"Azure"
model_permaslug
"openai/gpt-4o-2024-08-06"
api_type
"completions"
id
"gen-1771294798-7V64JyUk7Ck1CuYGPNAb"
upstream_id
"chatcmpl-DA4ysnP198I8gwwNk6cjlNhj3e0KT"
total_cost
0.0149775
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Azure"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
3
adverbTagCount
0
adverbTags
(empty)
90.4943%
AI-ism adverb frequency
Target: <1% AI-ism adverbs (57 tracked)
wordCount
1052
totalAiIsmAdverbs
1
found
0
adverb
"suddenly"
count
1
highlights
0
"suddenly"
100.0000%
AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
100.0000%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
0.0000%
AI-ism word frequency
Target: <1% AI-ism words (140 tracked)
wordCount
1052
totalAiIsms
14
found
0
word
"cacophony"
count
1
1
word
"flicker"
count
1
2
word
"otherworldly"
count
1
3
word
"surreal"
count
1
4
word
"calculated"
count
1
5
word
"calculating"
count
1
6
word
"unwavering"
count
2
7
word
"unspoken"
count
1
8
word
"tantalizing"
count
1
9
word
"weight"
count
1
10
word
"footsteps"
count
2
11
word
"echoing"
count
1
highlights
0
"cacophony"
1
"flicker"
2
"otherworldly"
3
"surreal"
4
"calculated"
5
"calculating"
6
"unwavering"
7
"unspoken"
8
"tantalizing"
9
"weight"
10
"footsteps"
11
"echoing"
0.0000%
Cliche density
Target: ≤1 cliche(s) per 800-word window
totalCliches
4
maxInWindow
4
found
0
label
"heart pounded in chest"
count
1
1
label
"eyes widened/narrowed"
count
1
2
label
"air was thick with"
count
1
3
label
"flicker of emotion"
count
1
highlights
0
"heart pounded in her chest"
1
"eyes narrowed"
2
"the air was thick with"
3
"a flicker of recognition"
100.0000%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
70
matches
(empty)
100.0000%
Filter word density
Target: ≤12% sentences with filter/hedge words
filterCount
1
hedgeCount
0
narrationSentences
70
filterMatches
0
"watch"
hedgeMatches
(empty)
100.0000%
Overuse of "that" (subordinate clause padding)
Target: ≤10% sentences with "that" clauses
thatCount
0
totalSentences
72
matches
(empty)
43.8598%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
26
mean
40.38
std
12.26
cv
0.304
sampleLengths
0
64
1
64
2
46
3
55
4
39
5
41
6
53
7
9
8
47
9
44
10
43
11
49
12
44
13
46
14
42
15
35
16
34
17
49
18
35
19
17
20
27
21
34
22
38
23
27
24
36
25
32
100.0000%
Passive voice overuse
Target: ≤5% passive sentences
passiveCount
2
totalSentences
70
matches
0
"was said"
1
"was determined"
100.0000%
Past progressive (was/were + -ing) overuse
Target: ≤10% past progressive verbs
pastProgressiveCount
2
totalVerbs
156
matches
0
"was gaining"
1
"was heading"
94.0000%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1020
adjectiveStacks
1
stackExamples
0
"former paramedic turned underground healer."
adverbCount
20
adverbRatio
0.0196078431372549
lyAdverbCount
9
lyAdverbRatio
0.008823529411764706
100.0000%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
72
echoCount
0
echoWords
(empty)
94.4000%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
72
mean
14.58
std
5.63
cv
0.386
sampleLengths
0
23
1
16
2
11
3
14
4
17
5
11
6
22
7
14
8
15
9
13
10
18
11
14
12
12
13
29
14
7
15
12
16
20
17
8
18
20
19
13
20
18
21
12
22
23
23
7
24
2
25
11
26
14
27
22
28
3
29
21
30
20
31
13
32
17
33
13
34
18
35
13
36
18
37
11
38
17
39
16
40
17
41
16
42
13
43
6
44
25
45
11
46
20
47
7
48
8
49
14
44.4444%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
4
diversityRatio
0.2916666666666667
totalSentences
72
uniqueOpeners
21
91.6667%
Dialogue tag variety (said vs. fancy)
Target: ≤30% fancy dialogue tags
totalTags
3
fancyCount
1
fancyTags
0
"he said, his voice smooth and unhurried (say, unhurry)"
79.9332%