NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHMPCV21D4J5AAAMXAQEQA62
Run Details
Model:
Llama 3.1 Nemotron 70B
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
31.4s
Cost:
$0.002177
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 deserted streets of Soho, casting a misty veil over the already murky night. Detective Harlow Quinn's eyes, narrowed against the downpour, locked onto the fleeing figure of Tomás Herrera. His dark curls clung to his forehead as he darted between pedestrians, his olive skin
glistening
with rain. Quinn's sharp jaw set in determination; she'd been tracking this lead for weeks, and she wasn't about to let it slip away now. "Stop! Police!" Quinn's voice cut through the patter of raindrops, but Tomás didn't flinch. He vanished into the crowd gathering under the awning of a street food stall. Quinn weaved through the onlookers, her worn leather
watch
glinting
on her left wrist as she moved with military precision. She spotted Tomás's Saint Christopher medallion
glinting
briefly in the neon light of a nearby sign before he plunged into the night, heading toward the distinctive green neon sign of The Raven's Nest. Quinn's eyes never left his back as she tailed him into the dimly lit bar. The air inside reeked of stale beer and old books. Quinn's gaze swept the room, homing in on Tomás as he pushed past patrons and made a beeline for the bookshelf-lined rear wall. Without hesitation, he reached up and slid a section of shelves open, revealing a narrow passageway. Quinn's instincts screamed warning as Tomás slipped into the hidden room. For a moment, Quinn hesitated at the threshold, the sounds of the bar muffled by the thick bookshelves. Her mind replayed the briefing on potential supernatural hideouts in the city. The Veil Market, rumored to operate in the shadows, had
been mentioned
, but she'd never pinpointed its location. A hunch told her this might be the break she needed – if she dared to follow. She took a deep breath and stepped into the passageway, the shelf sliding shut behind her with a soft creak.
The air was heavy with
the scent of old dust and something else... incense, perhaps, or smoke. Her eyes adjusted
slowly
to the dim lighting, revealing a set of steep stairs descending into darkness. The murmur of hushed voices and the faint thrum of a generator drifted up from below. Quinn's hand instinctively went to her hip, only to remember she'd left her firearm locked in her car, anticipating a straightforward interview at The Raven's Nest.
A shiver ran down her spine
as she began her descent, the stairs creaking beneath her feet. At the bottom, Quinn found herself at the edge of an abandoned Tube station, the platforms and tracks transformed into a labyrinthine market. Lanterns and candles cast flickering shadows on the walls as vendors hawked their wares in hushed tones. The atmosphere reeked of illicit dealings, and Quinn's years of experience told her this was indeed the Veil Market. Tomás Herrera was already lost in the crowd, but Quinn spotted the flash of his medallion near a stall piled high with peculiar artifacts. As she moved to follow, a hand grasped her elbow, spinning her around. "Lost, detective?" A hooded figure
loomed
over her, voice low and gravelly. Quinn's gaze locked onto the figure's hand, her mind racing. "Just looking for someone." The figure chuckled, producing a small, polished bone from their cloak. "Entry token. You shouldn't be here without one. Now, you can either leave... or pay the price for admission." Quinn's grip on her left wrist tightened, the worn leather of her
watch
creaking
softly
. She weighed her options, her eyes darting toward Tomás's last known location. The investigation, the unanswered questions about DS Morris's death, all swirled together in her mind. With a deliberate movement, Quinn reached into her pocket and pulled out a small, unused SIM card. "Information's the currency I deal in. What's the price for letting me pass... and for telling me what's being peddled here tonight?" The hooded figure's gaze
flickered
, seemingly intrigued by Quinn's boldness. After a moment's deliberation, they nodded, accepting the SIM card. "Very well, Detective Harlow Quinn. Tonight's special: whispers of a new alchemist in town, peddling transmutation serums... and something far more
sinister
, from the shadows. Your entry's granted, but be warned: in the Veil Market, the lines between hunter and prey are easily blurred." With that, the figure vanished into the crowd, leaving Quinn to
navigate
the treacherous underworld alone, her eyes fixed on the spot where Tomás Herrera had last
been seen
. She took a deep breath, stepping into the heart of the market, ready to face whatever lay ahead.
created_at
"2026-02-17T02:21:17.822345+00:00"
2/17/2026, 2:21:17 AM
model
"nvidia/llama-3.1-nemotron-70b-instruct"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
306
moderation_latency
(null)
generation_time
31273
tokens_prompt
959
tokens_completion
1165
native_tokens_prompt
817
native_tokens_completion
997
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
0.0021768
router
(null)
provider_responses
0
id
"cmpl-cab9a5d447994d878e222c8134c00a7f"
status
200
is_byok
false
latency
218
endpoint_id
"d2a33d30-5d41-47d3-a816-1cc067b5a7dd"
provider_name
"DeepInfra"
model_permaslug
"nvidia/llama-3.1-nemotron-70b-instruct"
api_type
"completions"
id
"gen-1771294846-pannitbKF4bRkhUiz7o1"
upstream_id
"cmpl-cab9a5d447994d878e222c8134c00a7f"
total_cost
0.0021768
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
0
adverbTagCount
0
adverbTags
(empty)
60.1594%
AI-ism adverb frequency
Target: <1% AI-ism adverbs (57 tracked)
wordCount
753
totalAiIsmAdverbs
3
found
0
adverb
"slowly"
count
1
1
adverb
"softly"
count
1
2
adverb
"very"
count
1
highlights
0
"slowly"
1
"softly"
2
"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)
7.0385%
AI-ism word frequency
Target: <1% AI-ism words (140 tracked)
wordCount
753
totalAiIsms
7
found
0
word
"flickered"
count
1
1
word
"glistening"
count
1
2
word
"glinting"
count
2
3
word
"sinister"
count
1
4
word
"loomed"
count
1
5
word
"navigate"
count
1
highlights
0
"flickered"
1
"glistening"
2
"glinting"
3
"sinister"
4
"loomed"
5
"navigate"
66.6667%
Cliche density
Target: ≤1 cliche(s) per 800-word window
totalCliches
2
maxInWindow
2
found
0
label
"shiver down spine"
count
1
1
label
"air was thick with"
count
1
highlights
0
"A shiver ran down her spine"
1
"The air was heavy with"
100.0000%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
40
matches
(empty)
100.0000%
Filter word density
Target: ≤12% sentences with filter/hedge words
filterCount
2
hedgeCount
0
narrationSentences
40
filterMatches
0
"watch"
hedgeMatches
(empty)
100.0000%
Overuse of "that" (subordinate clause padding)
Target: ≤10% sentences with "that" clauses
thatCount
0
totalSentences
44
matches
(empty)
64.9871%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
16
mean
47.06
std
17.76
cv
0.377
sampleLengths
0
75
1
48
2
48
3
60
4
65
5
70
6
43
7
59
8
37
9
12
10
14
11
30
12
42
13
39
14
64
15
47
100.0000%
Passive voice overuse
Target: ≤5% passive sentences
passiveCount
2
totalSentences
40
matches
0
"been mentioned"
1
"been seen"
100.0000%
Past progressive (was/were + -ing) overuse
Target: ≤10% past progressive verbs
pastProgressiveCount
0
totalVerbs
109
matches
(empty)
94.0000%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
660
adjectiveStacks
1
stackExamples
0
"bookshelf-lined rear wall."
adverbCount
14
adverbRatio
0.021212121212121213
lyAdverbCount
8
lyAdverbRatio
0.012121212121212121
100.0000%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
44
echoCount
0
echoWords
(empty)
100.0000%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
44
mean
17.11
std
7.02
cv
0.41
sampleLengths
0
18
1
16
2
18
3
23
4
14
5
14
6
20
7
33
8
15
9
10
10
23
11
16
12
11
13
18
14
12
15
18
16
17
17
20
18
13
19
4
20
17
21
16
22
26
23
17
24
23
25
17
26
19
27
24
28
13
29
12
30
10
31
4
32
11
33
19
34
15
35
12
36
15
37
17
38
22
39
10
40
10
41
44
42
29
43
18
90.9091%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
0
diversityRatio
0.5454545454545454
totalSentences
44
uniqueOpeners
24
100.0000%
Dialogue tag variety (said vs. fancy)
Target: ≤30% fancy dialogue tags
totalTags
0
fancyCount
0
fancyTags
(empty)
87.2800%