NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-17-01KHMPC53Q50E3639YXM1Q12VC
Run Details
Model:
Rocinante 12B
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
15.8s
Cost:
$0.000869
Provider:
Infermatic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
74.25%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
58.81%
AI-ism word frequency
(details)
100.00%
Cliché density
(details)
100.00%
Emotion telling (show vs. tell)
(details)
100.00%
Filter word density
(details)
100.00%
Gibberish response detection
(details)
100.00%
Markdown formatting overuse
(details)
100.00%
Missing dialogue indicators (quotation marks)
(details)
66.67%
Name drop frequency
(details)
47.96%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
100.00%
Paragraph length variance
(details)
100.00%
Passive voice overuse
(details)
60.14%
Past progressive (was/were + -ing) overuse
(details)
75.63%
Em-dash & semicolon overuse
(details)
86.60%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
58.04%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
7.50%
Pronoun-first sentence starts
(details)
77.19%
Subject-first sentence starts
(details)
78.13%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
83.0304%
Overall
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="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</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> </codex> Write a fully fleshed out scene of at least 1000 words in the literary fiction genre. Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret. 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
Aurora made her way down
the narrow, neon-lit streets of Soho, her breath creating soft clouds in the
chill
London air.
The night was young, but
she was tired. Being on her feet all day, running errands for Yu-Fei, had taken more out of her than she cared to admit. Lost in thought, she barely noticed the distinctive green sign above the entrance until she was nearly past it. "The Raven's Nest?"
she whispered, surprised
.
She hadn't set foot in
this place since she fell out with Silas nearly three years ago. But it was warm, inviting even, and the prospect of sinking into a booth and losing herself for a while seemed too good to pass up.
The door creaked open, and
the
warmth
enveloped her as she stepped inside.
It was just as she
remembered - dim lighting, the smell of aged whiskey and pipe tobacco, the low murmur of voices. And there, behind the bar, was Silas himself, his grey-streaked auburn hair and neatly trimmed beard barely longer than she recalled. He
was polishing
a glass, his movements slow and precise.
He looked up, and their
eyes met. For a moment, he just stared.
Then, slowly, a smile spread
across his face. "Rory,"
he said softly, almost reverently
. She felt herself flush. "Si,"
she replied, surprised at the
stew of emotions his presence evoked - joy, longing, regret, anger. She looked away,
suddenly
unsure. "Mind if I...?" "Of course not,"
he said, gesturing to an
empty booth. "Can I get you anything? Usual?"
She nodded, sinking into the
worn leather.
She watched him pour her
a double shot of Pappy Van Winkle, the amber liquid catching the dim light.
He set it down in
front of her, his hand lingering on the glass for just a moment. "You're a sight for sore eyes,"
he said, sliding into the
booth across from her. "What brings you here after all this time?"
Aurora took a sip, savoring
the
warmth
as it spread through her. "Long story,"
she said, and smiled wryly
. "How have you been? I always... I always meant to come by, but... well, you know."
He shrugged, but she noticed
the way his eyes clouded. "I've been alright," he said. "The bar keeps me busy. Ah, basic indisposed."
He made a small gesture
with his hands, the universal sign of "working." Aurora nodded, looking down at her glass. "Yeah, me too," she said. "Just temping, but it pays the bills, I guess." There was a beat of
silence
. Then Silas cleared his throat. "I heard you and Eva had a falling out,"
he said, his eyes searching
her face. Aurora stiffened. "Yeah,"
she said, her voice tight
. "She... she betrayed me. Used me to get what she wanted, just like everyone else." Silas nodded, his face sympathetic. "I'm sorry, Rory," he said. "I know how much she meant to you." "Is that why you didn't reach out?"
she asked, her voice quavering
slightly
. "Because you thought I was still with her?" He looked away, his hand tightening on his glass. "No,"
he said, his voice low
. "No, that's not why." Aurora felt her heart sink. "Then why?"
she asked, her voice barely a whisper
. He sighed, running a hand through his hair. "I don't know, Rory,"
he said, his voice heavy with regret
. "I just... I didn't know what to say. I messed up, and I knew it. I thought... I thought maybe it was better to just let you go." Aurora felt the tears pricking at the corners of her eyes. She blinked them back, looking down at her glass. "You could have tried,"
she said, her voice low and thick with emotion
. "You could have picked up the phone, sent a message, anything." Silas was silent for a long moment.
Then, slowly, he reached out
and covered her hand with his own. "I'm sorry, Rory,"
he said, his voice raw
. "I was a fool. I should have tried harder to make things right." Aurora looked up at him, her blue eyes bright with unshed tears. She squeezed his hand, a small, bittersweet smile playing at the corners of her mouth. "It's alright,"
she said, her voice soft
. "We've both made mistakes. We're here now." Silas nodded, his own eyes
glistening
. He raised his glass, and she raised hers to clink against it. "To new beginnings," he said. "And old friends," she replied, and they drank. And there, in that dimly lit booth, surrounded by the
warmth
and the noise and the ghosts of the past, Aurora felt
something like hope kindling in her chest
.
If she and Silas could
find their way back to each other after all this time, maybe there was still hope for her, for her future, for everything.
Maybe it wasn't too late
to make things right, to start over, to become who she was always meant to be. Silas looked at her, his hazel eyes searching her face. "So,"
he said, his voice gentle
. "What do you say we start again? Fresh slate, clean page, all that?" Aurora smiled, and it
felt like the sun breaking through the
clouds. "I'd like that," she said. "I'd like that a lot." And so they talked, and laughed, and reminisced long into the night, the ghosts of the past drifting away like smoke on the London air. They
were never going
to be the same people they were before, but maybe that was okay.
Maybe it was time to
start again, to write a new story, one where they could be better, braver, kinder. And as the night wore on, and the fire burned low, Aurora felt something ease inside her, a
tension
she hadn't even realized she
was carrying
. Silas was here, and she was here, and together, they could face anything. Anything at all.
created_at
"2026-02-17T02:20:39.894942+00:00"
2/17/2026, 2:20:39 AM
model
"thedrummer/rocinante-12b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
279
moderation_latency
(null)
generation_time
15680
tokens_prompt
889
tokens_completion
1381
native_tokens_prompt
857
native_tokens_completion
1309
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
0.00086875
router
(null)
provider_responses
0
id
"chatcmpl-58061734-2d6b-49c5-9937-5bd0070b56c4"
status
200
is_byok
false
latency
147
endpoint_id
"caf29916-6adb-45f8-b895-dd863415d3ed"
provider_name
"Infermatic"
model_permaslug
"thedrummer/rocinante-12b"
api_type
"completions"
id
"gen-1771294823-flSPeN53njyDBc5XL8wg"
upstream_id
"chatcmpl-58061734-2d6b-49c5-9937-5bd0070b56c4"
total_cost
0.00086875
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Infermatic"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
23
adverbTagCount
1
adverbTags
0
"he said softly [softly]"
dialogueSentences
38
tagDensity
0.605
leniency
1
rawRatio
0.043
effectiveRatio
0.043
74.25%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
971
totalAiIsmAdverbs
5
found
0
adverb
"slowly"
count
2
1
adverb
"softly"
count
1
2
adverb
"suddenly"
count
1
3
adverb
"slightly"
count
1
highlights
0
"slowly"
1
"softly"
2
"suddenly"
3
"slightly"
100.00%
AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0
"Blackwood"
found
(empty)
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
58.81%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
971
totalAiIsms
8
found
0
word
"chill"
count
1
1
word
"warmth"
count
3
2
word
"silence"
count
1
3
word
"whisper"
count
1
4
word
"glistening"
count
1
5
word
"tension"
count
1
highlights
0
"chill"
1
"warmth"
2
"silence"
3
"whisper"
4
"glistening"
5
"tension"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
0
maxInWindow
0
found
(empty)
highlights
(empty)
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
1
narrationSentences
70
matches
0
"y with regret"
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
1
narrationSentences
70
filterMatches
(empty)
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
85
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
29
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
973
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
25
unquotedAttributions
0
matches
(empty)
66.67%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
26
wordCount
742
uniqueNames
8
maxNameDensity
1.35
worstName
"Aurora"
maxWindowNameDensity
3
worstWindowName
"Aurora"
discoveredNames
Soho
1
London
2
Yu-Fei
1
Silas
9
Pappy
1
Van
1
Winkle
1
Aurora
10
persons
0
"Yu-Fei"
1
"Silas"
2
"Pappy"
3
"Van"
4
"Winkle"
5
"Aurora"
places
0
"Soho"
1
"London"
globalScore
0.826
windowScore
0.667
47.96%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
49
glossingSentenceCount
2
matches
0
"something like hope kindling in her chest"
1
"felt like the sun breaking through the"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
973
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
85
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
28
mean
34.75
std
18.11
cv
0.521
sampleLengths
0
50
1
68
2
73
3
20
4
29
5
16
6
44
7
23
8
35
9
36
10
21
11
27
12
23
13
18
14
21
15
19
16
14
17
47
18
44
19
40
20
41
21
23
22
8
23
78
24
29
25
22
26
62
27
42
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
70
matches
(empty)
60.14%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
3
totalVerbs
143
matches
0
"was polishing"
1
"were never going"
2
"was carrying"
75.63%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
2
semicolonCount
0
flaggedSentences
2
totalSentences
85
ratio
0.024
matches
0
"It was just as she remembered - dim lighting, the smell of aged whiskey and pipe tobacco, the low murmur of voices."
1
"\"Si,\" she replied, surprised at the stew of emotions his presence evoked - joy, longing, regret, anger."
86.60%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
743
adjectiveStacks
1
stackExamples
0
"narrow, neon-lit streets"
adverbCount
36
adverbRatio
0.04845222072678331
lyAdverbCount
14
lyAdverbRatio
0.018842530282637954
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
85
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
85
mean
11.45
std
6.63
cv
0.58
sampleLengths
0
21
1
8
2
21
3
19
4
6
5
17
6
26
7
13
8
22
9
21
10
10
11
7
12
6
13
8
14
6
15
4
16
17
17
5
18
3
19
10
20
6
21
7
22
19
23
18
24
15
25
8
26
12
27
7
28
16
29
10
30
5
31
21
32
7
33
5
34
9
35
6
36
5
37
16
38
2
39
6
40
15
41
5
42
5
43
8
44
13
45
8
46
9
47
6
48
4
49
5
58.04%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
9
diversityRatio
0.4117647058823529
totalSentences
85
uniqueOpeners
35
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
5
totalSentences
64
matches
0
"Then, slowly, a smile spread"
1
"Then Silas cleared his throat."
2
"Then, slowly, he reached out"
3
"Maybe it wasn't too late"
4
"Maybe it was time to"
ratio
0.078
7.50%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
34
totalSentences
64
matches
0
"she whispered, surprised"
1
"She hadn't set foot in"
2
"It was just as she"
3
"He was polishing a glass,"
4
"He looked up, and their"
5
"he said softly, almost reverently"
6
"She felt herself flush."
7
"she replied, surprised at the"
8
"She looked away, suddenly unsure."
9
"he said, gesturing to an"
10
"She nodded, sinking into the"
11
"She watched him pour her"
12
"He set it down in"
13
"he said, sliding into the"
14
"she said, and smiled wryly"
15
"He shrugged, but she noticed"
16
"He made a small gesture"
17
"he said, his eyes searching"
18
"she said, her voice tight"
19
"she asked, her voice quavering"
ratio
0.531
77.19%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
49
totalSentences
64
matches
0
"Aurora made her way down"
1
"The night was young, but"
2
"she whispered, surprised"
3
"She hadn't set foot in"
4
"The door creaked open, and"
5
"It was just as she"
6
"He was polishing a glass,"
7
"He looked up, and their"
8
"he said softly, almost reverently"
9
"She felt herself flush."
10
"she replied, surprised at the"
11
"She looked away, suddenly unsure."
12
"he said, gesturing to an"
13
"She nodded, sinking into the"
14
"She watched him pour her"
15
"He set it down in"
16
"he said, sliding into the"
17
"Aurora took a sip, savoring"
18
"she said, and smiled wryly"
19
"He shrugged, but she noticed"
ratio
0.766
78.13%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
64
matches
0
"If she and Silas could"
ratio
0.016
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
28
technicalSentenceCount
0
matches
(empty)
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
23
uselessAdditionCount
10
matches
0
"he said, his eyes searching her face"
1
"she said, her voice tight"
2
"she asked, her voice quavering slightly"
3
"he said, his voice low"
4
"she asked, her voice barely a whisper"
5
"he said, his voice heavy with regret"
6
"she said, her voice low and thick with emotion"
7
"he said, his voice raw"
8
"she said, her voice soft"
9
"he said, his voice gentle"
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
22
fancyCount
1
fancyTags
0
"she whispered (whisper)"
dialogueSentences
38
tagDensity
0.579
leniency
1
rawRatio
0.045
effectiveRatio
0.045
83.0304%