NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHMMV4N75BBSWZXQE4P16R4Y
Run Details
Model:
Ministral 3B
Test:
Bad Writing Habits
Scenario:
Romance: separated couple reunites
Duration:
3.2s
Cost:
$0.000068
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="4415" name="Lucien Moreau" aliases="Lucien, Luc, the Frenchman" pronouns="he/him" species="Half-Demon" storyRole="Ally"> <eyeColor>heterochromatic — one amber, one black</eyeColor> <hair>slicked-back platinum blond</hair> <height>5'11"</height> <age>32</age> <cane>ivory-handled cane that conceals a thin blade</cane> <dress>tailored charcoal suits</dress> <description>An impeccably dressed fixer and information broker in London's supernatural underworld. He speaks four languages fluently.</description> <backstory>Born in Marseille to a human mother and a demon father from the realm of Avaros.</backstory> </character> <location id="858" name="Eva's Flat" aliases="Eva's place, the flat on Brick Lane" realm="Earth"> <cat>tabby cat named Ptolemy</cat> <security>three deadbolts on the front door</security> <description>A cramped one-bedroom flat above a curry house on Brick Lane, East London. Every surface is covered with books, scrolls, and research notes.</description> </location> </codex> Write a fully fleshed out scene of at least 1000 words in the romance genre. Two people who parted on complicated terms are forced together again when one shows up unannounced at the other's flat. There's history between them — attraction, hurt, and things left unsaid. Write the scene from the moment the door opens. 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 front door of Eva’s flat groaned under the
weight
of Lucien’s frame, the deadbolts clattering like a warning before they gave way. The moment the lock clicked, the air in the cramped space thickened, charged with something older than the scent of aged tea and old books—something sharp, electric. Aurora Carter didn’t turn around immediately. She stood at the window, the city’s neon glow bleeding through the grimy panes, her fingers tracing the scar on her wrist, the one that had been there since she was eight. *Remembering how it hurt.* Lucien exhaled, slow and deliberate, as if he’d been holding his breath for years. The cane he carried—ivory-handled, blade concealed—rested against the wall beside him, its polished surface catching the light. He wore a charcoal suit, tailored to perfection, the fabric whispering against his skin like a promise. "You’re here," he said, voice low, almost a whisper. "I didn’t expect you to answer." Aurora didn’t look at him. "You didn’t ask." A beat of silence. Then, the faintest rustle of fabric as he shifted, the cane’s tip brushing the floor. "I didn’t need to." His fingers twitched toward the blade, but he didn’t draw it. Instead, he stepped forward, closer than he should have been, the heat of his body radiating off him like a second skin. "You left me in London when you could’ve stayed." Her breath hitched. "And you came for me." He smirked, that crooked, knowing smile that had always made her stomach twist. "I came for the city. Not you." But his eyes—amber and black, shifting like a storm cloud—burned into hers. "You’re here now." The flat was small, but it was *her* flat. Bookshelves lined the walls, their spines worn from years of reading, scrolls and notebooks stacked haphazardly, the scent of ink and something older, something darker, clinging to the air. Ptolemy, the tabby cat, blinked up at them from his perch on the windowsill, tail flicking
lazily
. He didn’t move. Didn’t judge. Aurora turned
slowly
, her black hair falling just past her shoulders, the scar on her wrist catching the light. "You’re late," she said. Lucien’s gaze
flicked
to the door, then back to her. "I was waiting for you to come home." The words hung between them, heavy with
unspoken
meaning. She crossed her arms, the movement sharp against the fabric of her blouse. "You could’ve just called." "I didn’t want to." His voice was rough, like gravel underfoot. "I wanted to see you first." She scoffed, but her fingers tightened around the scar. "You always did have a way with words." He stepped closer, the cane still resting against the wall but the blade now hidden beneath his palm. "You were running from something, Aurora. Not just from me." The name on her lips was a question, but she didn’t ask it. Instead, she exhaled, the sound sharp. "I
was running
from everything." Lucien didn’t flinch. "Then let me help." The air between them crackled. The cat, Ptolemy, let out a low, satisfied mew, as if he understood the tension better than either of them. Aurora’s pulse hammered in her throat. "You’re not helping me." He tilted his head, studying her, the way he always had when he
was thinking
. "You’re not asking for it." She opened her mouth to argue, but the words died on her lips. Because he was right. She
wasn’t asking
for anything. She was just standing there, in the same flat she’d left behind, the same city that had swallowed her whole, and she wasn’t sure she wanted to go back. Lucien reached out, his fingers brushing hers—just for a second—before she could pull away. "Tell me what you need," he murmured. Aurora swallowed hard. "I don’t know." He smiled, that crooked, dangerous smile. "Then let me show you." The flat felt smaller now, the walls pressing in, the bookshelves
looming
like silent witnesses. But for the first time in years, Aurora didn’t feel like she
was running
. She felt like she was exactly where she
was meant
to be.
Evaluation details
Result
Evaluator
Details
Meta Data
22.2222%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
3
adverbTagCount
1
adverbTags
0
"he said, voice low, almost a whisper [almost]"
70.7602%
AI-ism adverb frequency
Target: <1% AI-ism adverbs (57 tracked)
wordCount
684
totalAiIsmAdverbs
2
found
0
adverb
"lazily"
count
1
1
adverb
"slowly"
count
1
highlights
0
"lazily"
1
"slowly"
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)
41.5205%
AI-ism word frequency
Target: <1% AI-ism words (140 tracked)
wordCount
684
totalAiIsms
4
found
0
word
"flicked"
count
1
1
word
"looming"
count
1
2
word
"unspoken"
count
1
3
word
"weight"
count
1
highlights
0
"flicked"
1
"looming"
2
"unspoken"
3
"weight"
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
48
matches
(empty)
100.0000%
Filter word density
Target: ≤12% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
48
filterMatches
(empty)
hedgeMatches
(empty)
100.0000%
Overuse of "that" (subordinate clause padding)
Target: ≤10% sentences with "that" clauses
thatCount
0
totalSentences
64
matches
(empty)
100.0000%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
23
mean
29.39
std
22.13
cv
0.753
sampleLengths
0
92
1
63
2
8
3
65
4
8
5
35
6
60
7
23
8
18
9
26
10
17
11
17
12
28
13
24
14
7
15
25
16
10
17
20
18
51
19
21
20
6
21
11
22
41
100.0000%
Passive voice overuse
Target: ≤5% passive sentences
passiveCount
1
totalSentences
48
matches
0
"was meant"
100.0000%
Past progressive (was/were + -ing) overuse
Target: ≤10% past progressive verbs
pastProgressiveCount
3
totalVerbs
105
matches
0
"was thinking"
1
"wasn’t asking"
2
"was running"
96.7570%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
572
adjectiveStacks
0
stackExamples
(empty)
adverbCount
25
adverbRatio
0.043706293706293704
lyAdverbCount
5
lyAdverbRatio
0.008741258741258742
100.0000%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
64
echoCount
0
echoWords
(empty)
100.0000%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
64
mean
10.56
std
7.29
cv
0.69
sampleLengths
0
23
1
27
2
6
3
32
4
4
5
14
6
17
7
17
8
9
9
6
10
5
11
3
12
4
13
15
14
15
15
22
16
9
17
3
18
5
19
13
20
19
21
3
22
9
23
29
24
17
25
3
26
2
27
19
28
4
29
10
30
8
31
9
32
13
33
4
34
11
35
6
36
9
37
8
38
18
39
10
40
13
41
6
42
5
43
3
44
4
45
5
46
20
47
6
48
4
49
15
43.7500%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
4
diversityRatio
0.296875
totalSentences
64
uniqueOpeners
19
8.3333%
Dialogue tag variety (said vs. fancy)
Target: ≤30% fancy dialogue tags
totalTags
3
fancyCount
2
fancyTags
0
"he said, voice low, almost a whisper (say, voice)"
1
"he murmured (murmur)"
81.3731%