NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHMPD5DSN7RCB0VWE6TW1E5Z
Run Details
Model:
Llama 3.1 70B
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
26.0s
Cost:
$0.000742
Provider:
DeepInfra
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 down on the city streets, drumming a relentless beat on the pavement. Detective Harlow Quinn sprinted through the downpour, her eyes fixed on the figure dodging pedestrians and leaping over puddles ahead. The suspect, a young man with dark curly hair, had led her on a wild goose chase through the winding alleys of Soho, but she refused to back off. She pumped her arms, her worn leather
watch
on her left wrist
glinting
in the faint light of a nearby streetlamp. Her sharp jaw was set in a determined line as she took a sharp right turn, her military precision-trained reflexes on high alert. The chase had been going on for what felt like hours, and she
was determined
to catch the slippery suspect. As she turned the corner onto Dean Street, the green neon sign of the Raven's Nest bar
loomed
ahead, casting an eerie glow over the rain-soaked sidewalk. The suspect vanished into the entrance, and Harlow hesitated for a split second before following. The warm, dimly lit interior enveloped her, a welcome respite from the cold rain. The bar's patrons – an assortment of shady-looking characters and regulars – turned to regard her with a mixture of curiosity and hostility. Harlow's eyes scanned the room, locking onto the figure she'd been chasing as he dodged behind the bar, past the barkeep's gruff protestations.
The air was thick with
the smell of stale beer and damp wood. "Tomás!" the barkeep, Silas, bellowed after him. "What've you got yourself into now, mate?" Harlow shouldered through the crowd, ignoring the barkeep's queries and pressing into the narrow space behind the bar. A shelf-lined doorway, previously hidden from view, swung open as Tomás pushed through it. The door creaked shut behind him, and Harlow
was left
staring at the dusty book spines and dark wood paneling. The hidden room. A glance at Silas, who
was polishing
a mug with a dirty rag, yielded no useful information. "Haven't seen anything, officer," he growled, meeting her gaze with a mixture of hostility and wariness. Harlow's gut told her Tomás
was heading
somewhere he didn't want her to follow. But the streets above were a labyrinth; she'd never track him down again. The possibilities sent a cold dread creeping up her spine. Wherever Tomás was headed, she had to assume it was connected to the strange occurrences plaguing the city – occurrences that bore an unsettling resemblance to the case that had claimed her partner's life. She slipped through the doorway, into the narrow passageway. Cool air, heavy with the scent of damp earth, enveloped her, and she blinked away the bright lights of the bar. Flickering fluorescent lights above illuminated the passageway, leading her deeper into the hidden underbelly of the city. As the passageway sloped downward, the sound of dripping water and distant murmurs grew louder. The air thickened with an
otherworldly
scent, like ozone and smoke. Harlow's instincts screamed warning, but her training kept her moving forward. She descended into the unknown, her heart pounding in her chest. A bone token,
etched
with strange symbols, lay on the ground ahead. The entry requirement for the Veil Market, whispered rumors had told her. The underground market that
seemed to
be a hub for the
very
people and things she
was trying
to investigate. The fluorescent lights above
flickered
once, twice, and then died. Darkness swallowed her, and Harlow stood frozen, the token a tiny, glowing landmark on the ground. With a deep breath, she stepped forward, leaving the faint light of the Raven's Nest behind. She found herself at the edge of a cavernous space, the ceiling lost in darkness. The abandoned Tube station beneath Camden, lit by flickering lanterns and crowded with shadowy figures, str
etched
out before her like an underworld realm. The sound of haggling and muted conversations created a constant hum, while figures darted between stalls, hawking wares that defied the laws of nature and the real world. A sign creaked in the faint breeze: "Veil Market – Enchanted Goods and Information". Harlow's stomach twisted with unease as she spotted Tomás, a tiny figure in the distance, vanishing into the crowd. This was it – the point of no return. Pursuing him deeper into the market could mean walking into a den of inhuman predators, with no backup, no cover, and no way out. Yet, something compelled her forward. Perhaps it was the memory of her partner, DS Morris, whose unexplained death still haunted her dreams. Or perhaps it was the sheer determination that had driven her to become a detective in the first place. Whatever the reason, Harlow Quinn stepped into the unknown, her eyes locked on the retreating figure of Tomás Herrera, ready to face whatever dangers lay ahead.
created_at
"2026-02-17T02:21:23.073753+00:00"
2/17/2026, 2:21:23 AM
model
"meta-llama/llama-3.1-70b-instruct"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
368
moderation_latency
(null)
generation_time
25977
tokens_prompt
959
tokens_completion
1220
native_tokens_prompt
817
native_tokens_completion
1038
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
0.000742
router
(null)
provider_responses
0
id
"cmpl-f466a3f3ac824d2ab188eb2881773145"
status
200
is_byok
false
latency
78
endpoint_id
"036dfa0a-ebbb-4a51-aa90-091a75c2cadb"
provider_name
"DeepInfra"
model_permaslug
"meta-llama/llama-3.1-70b-instruct"
api_type
"completions"
id
"gen-1771294856-HTAITwxDmcia28RtTTWG"
upstream_id
"cmpl-f466a3f3ac824d2ab188eb2881773145"
total_cost
0.000742
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
2
adverbTagCount
0
adverbTags
(empty)
87.4055%
AI-ism adverb frequency
Target: <1% AI-ism adverbs (57 tracked)
wordCount
794
totalAiIsmAdverbs
1
found
0
adverb
"very"
count
1
highlights
0
"very"
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)
37.0277%
AI-ism word frequency
Target: <1% AI-ism words (140 tracked)
wordCount
794
totalAiIsms
5
found
0
word
"flickered"
count
1
1
word
"glinting"
count
1
2
word
"otherworldly"
count
1
3
word
"loomed"
count
1
4
word
"etched"
count
1
highlights
0
"flickered"
1
"glinting"
2
"otherworldly"
3
"loomed"
4
"etched"
100.0000%
Cliche density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"air was thick with"
count
1
highlights
0
"The air was thick with"
100.0000%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
47
matches
(empty)
100.0000%
Filter word density
Target: ≤12% sentences with filter/hedge words
filterCount
1
hedgeCount
1
narrationSentences
47
filterMatches
0
"watch"
hedgeMatches
0
"seemed to"
100.0000%
Overuse of "that" (subordinate clause padding)
Target: ≤10% sentences with "that" clauses
thatCount
0
totalSentences
48
matches
(empty)
37.2471%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
15
mean
53
std
14.86
cv
0.28
sampleLengths
0
63
1
64
2
56
3
59
4
14
5
55
6
33
7
71
8
47
9
48
10
44
11
42
12
66
13
66
14
67
90.7801%
Passive voice overuse
Target: ≤5% passive sentences
passiveCount
3
totalSentences
47
matches
0
"was determined"
1
"was left"
2
"was headed, was connected"
100.0000%
Past progressive (was/were + -ing) overuse
Target: ≤10% past progressive verbs
pastProgressiveCount
3
totalVerbs
123
matches
0
"was polishing"
1
"was heading"
2
"was trying"
100.0000%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
776
adjectiveStacks
0
stackExamples
(empty)
adverbCount
17
adverbRatio
0.02190721649484536
lyAdverbCount
5
lyAdverbRatio
0.006443298969072165
100.0000%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
48
echoCount
0
echoWords
(empty)
96.3534%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
48
mean
16.56
std
6.47
cv
0.391
sampleLengths
0
14
1
20
2
29
3
21
4
23
5
20
6
27
7
15
8
14
9
23
10
23
11
13
12
7
13
7
14
18
15
14
16
20
17
3
18
17
19
16
20
14
21
13
22
10
23
34
24
9
25
21
26
17
27
15
28
11
29
11
30
11
31
12
32
12
33
20
34
10
35
16
36
16
37
15
38
23
39
28
40
14
41
19
42
9
43
24
44
5
45
17
46
19
47
26
67.3611%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
6
diversityRatio
0.4791666666666667
totalSentences
48
uniqueOpeners
23
0.0000%
Dialogue tag variety (said vs. fancy)
Target: ≤30% fancy dialogue tags
totalTags
2
fancyCount
2
fancyTags
0
"bellowed (bellow)"
1
"he growled, meeting her gaze with a mixture of hostility and wariness (growl, meet)"
83.3044%