NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHMPD7NCQYMVWK53M9RAJEC6
Run Details
Model:
Rocinante 12B
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
9.6s
Cost:
$0.000640
Provider:
Infermatic
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
The rain was a relentless downpour, pounding the cobblestones of Soho like a thousand impatient fingers. Detective Harlow Quinn's boots splashed through puddles as she sprinted down the narrow alley, her breath coming in sharp gasps. The woman she pursued—blood-mેએred arms outstretched, unnatural grace in her every step—glanced back with a cruel grin that gleamed fang-white in the dim glow of a gas lamp. "C'mon, copper. You're losing your touch," the woman taunted, her voice a throaty purr. Quinn snarled and redoubled her efforts, ignoring the
throb
of her . Ahead, the woman skidded to a halt at a dead end, a wall of damp brick barring her path. She turned, a slow, predatory pivot, and flashed a smirk. "Looks like my lucky night." But as Quinn closed in, the woman lunged, not at her, but the wall. Her hand closed around a rusted door handle, hidden in the shadows. With a curse, Quinn dove, fingers scrambling for purchase as the door swung shut, plunging the alley into darkness. For a moment, the detective sprawled on the wet ground, the cool, stinking rain plastering her hair to her skull. Then she was on her feet, groping feverishly for the handle. The door yielded with a groan, revealing a narrow flight of . She took the stairs three at a time, the pain in her ribs forgotten in the heat of pursuit. The stairs ended in a vast,
echoing
space. Quinn blinked, rainwater dripping from her lashes. An abandoned station, ancient brick arches stretching into shadow. The , bones bleached and
glistening
under the sickly fluorescent lights. A dozen pedestals topped with cloaked figures, low murmurs of conversation. The market
was laid
out before her like a feast. Her suspect stood a few yards away, leaning against a cracked pillar, ankles crossed as if waiting for a bus. "Took you long enough," she said, enjoying the detective's surprise. Quinn planted her feet, every sense on high alert. "Where is it?" she demanded, touching the . "Tell me now, and walk away." The woman laughed, a cold, sharp sound. "You
really
have no idea where you are, do you?" She pushed off from the pillar and sauntered closer, hips swaying. "Welcome to the Veil Market, Detective. The place where your kind isn't welcome." Quinn's grip tightened on her baton. Her experience told her to run, to get help, to surround the area. But her instincts screamed to pursue. Three years, three years since Morris disappeared, and her last lead
was staring
her in the face, smirking like it had a secret. She couldn't let her slip away. "Last chance," Quinn said, leveling the baton. The woman rolled her eyes and spun on her heel, disappearing into the Market's maw. The detective followed at a wary trot, her gaze darting from stall to stall. A peddler in a shabby cloak offered her worn tomes with flowery titles like "Rituals of the Old Religion" and "The Summoner's Compendium." A stall frequented by pale, translucent figures jostled for space, reaching rotting fingers for a vile that glowed an angry red. Quinn's nose wrinkled at the rank, metallic scent. Her quarry led her to a dead-end - a handful of stalls radiating an aura of menace. The wall of a . "Bomei." A tall figure in a
stark
white lab coat emerged from the shadows, gold-spectacled gaze fixed on Quinn. "And who have you brought me?" The woman, Bomei, inclined her head in deference. "Detective Quin, I present Doctor fulfillment stacks Doctor Kesari. She and her colleagues specialise in off-the-books treatments."
created_at
"2026-02-17T02:21:09.169703+00:00"
2/17/2026, 2:21:09 AM
model
"thedrummer/rocinante-12b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
273
moderation_latency
(null)
generation_time
9377
tokens_prompt
936
tokens_completion
899
native_tokens_prompt
871
native_tokens_completion
845
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
0.00064025
router
(null)
provider_responses
0
id
"chatcmpl-020f2014-44c7-4e87-84c9-be2ae8903c90"
status
200
is_byok
false
latency
130
endpoint_id
"caf29916-6adb-45f8-b895-dd863415d3ed"
provider_name
"Infermatic"
model_permaslug
"thedrummer/rocinante-12b"
api_type
"completions"
id
"gen-1771294858-f2Jjg1t54cJHN1iX1TRO"
upstream_id
"chatcmpl-020f2014-44c7-4e87-84c9-be2ae8903c90"
total_cost
0.00064025
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Infermatic"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
4
adverbTagCount
0
adverbTags
(empty)
83.2776%
AI-ism adverb frequency
Target: <1% AI-ism adverbs (57 tracked)
wordCount
598
totalAiIsmAdverbs
1
found
0
adverb
"really"
count
1
highlights
0
"really"
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)
33.1104%
AI-ism word frequency
Target: <1% AI-ism words (140 tracked)
wordCount
598
totalAiIsms
4
found
0
word
"throb"
count
1
1
word
"glistening"
count
1
2
word
"stark"
count
1
3
word
"echoing"
count
1
highlights
0
"throb"
1
"glistening"
2
"stark"
3
"echoing"
100.0000%
Cliche density
Target: ≤1 cliche(s) per 800-word window
totalCliches
0
maxInWindow
0
found
(empty)
highlights
(empty)
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
0
hedgeCount
0
narrationSentences
40
filterMatches
(empty)
hedgeMatches
(empty)
100.0000%
Overuse of "that" (subordinate clause padding)
Target: ≤10% sentences with "that" clauses
thatCount
0
totalSentences
45
matches
(empty)
100.0000%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
16
mean
37.19
std
20.68
cv
0.556
sampleLengths
0
64
1
14
2
12
3
34
4
45
5
62
6
56
7
30
8
23
9
41
10
54
11
7
12
81
13
22
14
25
15
25
100.0000%
Passive voice overuse
Target: ≤5% passive sentences
passiveCount
1
totalSentences
40
matches
0
"was laid"
100.0000%
Past progressive (was/were + -ing) overuse
Target: ≤10% past progressive verbs
pastProgressiveCount
1
totalVerbs
89
matches
0
"was staring"
100.0000%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
515
adjectiveStacks
0
stackExamples
(empty)
adverbCount
8
adverbRatio
0.015533980582524271
lyAdverbCount
2
lyAdverbRatio
0.003883495145631068
100.0000%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
45
echoCount
0
echoWords
(empty)
100.0000%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
45
mean
13.22
std
7.21
cv
0.546
sampleLengths
0
16
1
20
2
28
3
14
4
12
5
19
6
10
7
5
8
14
9
12
10
19
11
20
12
11
13
12
14
19
15
8
16
7
17
9
18
11
19
11
20
10
21
20
22
10
23
9
24
8
25
6
26
7
27
21
28
13
29
6
30
13
31
6
32
23
33
6
34
7
35
15
36
14
37
44
38
8
39
17
40
5
41
19
42
6
43
8
44
17
82.9630%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
1
diversityRatio
0.5111111111111111
totalSentences
45
uniqueOpeners
23
0.0000%
Dialogue tag variety (said vs. fancy)
Target: ≤30% fancy dialogue tags
totalTags
4
fancyCount
4
fancyTags
0
"the woman taunted, her voice a throaty purr (taunt, voice)"
1
"she said, enjoying the detective's surprise (say, enjoy)"
2
"demanded (demand)"
3
"Quinn said, leveling the baton (say, level)"
88.1971%