Run: 2026-02-20-01KHY8PG07TXR918NZJW6C2VW9

Run Details

Duration:
10.0s
Cost:
$0.000282
Provider:
Mistral

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

AI
The door to Eva’s flat creaked open before Aurora could even reach for the deadbolt, the hinges protesting like an old man’s joints. The scent of cardamom and spiced lamb hit her first—Eva’s cooking, always lingering even when the kitchen was empty. Then came the sound of laughter, low and rich, cutting through the usual hum of the flat’s cluttered energy. Aurora froze, her fingers still curled around the brass knob. She knew that voice. Knew the way it slithered through her like a knife between ribs, sharp and precise. *Lucien.* Her pulse hammered in her throat as she stepped inside, the door swinging wide enough for her to see him—tall, impossibly so, his platinum blond hair slicked back like he’d just stepped out of a tailor’s parlor. He was leaning against the kitchen counter, one ankle crossed over the other, a glass of something amber in hand. The amber light from the streetlamp outside spilled through the half-drawn curtains, catching the gold in his left eye and making it look like a flame trapped behind glass. “Rory,” he said, as if she were a ghost he’d half-expected to see. The name rolled off his tongue like a secret. “You look like hell.” She exhaled through her nose, a laugh bubbling up before she could stop it. “And you look like you’ve been to hell and back and still have time to iron your cuffs.” His lips quirked, just for a second, before smoothing into something dangerously polite. “You’re welcome.” Aurora shut the door behind her, the weight of it final. “What are you doing here?” Lucien set his glass down with deliberate care, as if he were placing a bomb on the counter. “I need your help.” “With what?” She crossed her arms, the movement instinctive, protective. The flat was hers now, even if it still smelled like Eva’s books and the faintest trace of her perfume. She wasn’t letting him in that easily. “Information.” He tilted his head, studying her. “About a man named Evan.” The name hit her like a punch to the gut. Her fingers twitched at her sides. “Why?” “Because,” he said, stepping forward, “he’s asking questions about you.” Aurora’s breath caught. She hadn’t thought about Evan in months—not since she’d burned his letters, since she’d left London behind. But the way Lucien said it, like it was a fact, not a threat, sent a chill down her spine. “What kind of questions?” “Where you are. What you’re doing.” He reached into his jacket, pulled out a folded piece of paper, and slid it across the counter. It landed with a soft *thunk* between them. “He’s been asking around. At the bar. At the restaurant. People talk when they think no one’s listening.” Aurora picked up the paper, her fingers brushing against his. The contact was electric, jarring. She unfolded it carefully, her stomach twisting as she read the scrawled words—*Find her. She owes me.* Evan’s handwriting was sloppy, desperate, the kind of thing a man writes when he’s lost control. When he’s not just angry anymore. When he’s dangerous. “You shouldn’t have come,” she said, her voice quieter than she intended. Lucien’s gaze flicked to her wrist, where the scar from her childhood accident peeked out from beneath her sleeve. She pulled her arm back instinctively, as if she could hide it from him. “I had to.” “Why?” she demanded. “Because you’re a sentimental fool, or because you think you can fix this?” His expression darkened, just for a second, before he schooled it. “I think you’re in danger.” Aurora laughed, sharp and bitter. “And you care?” Lucien’s jaw tightened. “I care about people who can’t protect themselves.” She wanted to argue. Wanted to tell him she didn’t need protecting. But the words died in her throat because she knew, deep down, that he was right. Evan wasn’t the kind of man who forgot. And if he was asking questions, that meant he was getting closer. She set the paper down, her hands steady now. “Fine. But I’m not doing this for you.” “No,” he said, stepping closer, “you’re doing it because you’re still the only person who can get me what I need.” Aurora’s breath hitched as he reached out, his fingers brushing against the scar on her wrist. The touch was light, almost reverent, and it sent a shiver down her spine. “What do you need?” Lucien’s gaze locked onto hers, his amber eye gleaming in the dim light. “A favor.” And just like that, she was back in the middle of it—of him, of the way his voice could make her pulse race, of the way his presence filled the room until there was no space left for anything else. She should have walked away. Should have told him to leave and never come back. But she didn’t. Because some favors weren’t just about what you gave. They were about what you took in return.
created_at"2026-02-20T19:33:46.641Z" 2/20/2026, 7:33:46 PM
model"mistralai/ministral-8b-2512"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency271
moderation_latency(null)
generation_time9851
tokens_prompt808
tokens_completion1294
native_tokens_prompt772
native_tokens_completion1106
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.0002817
router(null)
provider_responses
0
endpoint_id"c85d26e1-1e0c-449b-9775-2afce7ae510b"
id"4cc4698fa81747b18266b7682dd78acf"
is_byokfalse
latency271
model_permaslug"mistralai/ministral-8b-2512"
provider_name"Mistral"
status200
api_type"completions"
id"gen-1771616026-MVGELK9i87TcMZSBsDwv"
upstream_id"4cc4698fa81747b18266b7682dd78acf"
total_cost0.0002817
cache_discount(null)
upstream_inference_cost0
provider_name"Mistral"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags8
adverbTagCount0
adverbTags(empty)
dialogueSentences25
tagDensity0.32
leniency0.64
rawRatio0
effectiveRatio0
93.98% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount830
totalAiIsmAdverbs1
found
0
adverb"carefully"
count1
highlights
0"carefully"
100.00% AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions(empty)
found(empty)
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
33.73% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount830
totalAiIsms11
found
0
word"pulse"
count2
1
word"weight"
count1
2
word"chill"
count1
3
word"down her spine"
count2
4
word"electric"
count1
5
word"stomach"
count1
6
word"flicked"
count1
7
word"gleaming"
count1
8
word"race"
count1
highlights
0"pulse"
1"weight"
2"chill"
3"down her spine"
4"electric"
5"stomach"
6"flicked"
7"gleaming"
8"race"
66.67% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches2
maxInWindow2
found
0
label"sent a shiver through"
count2
highlights
0"sent a chill down"
1"sent a shiver down"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences57
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences57
filterMatches
0"look"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences74
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen41
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans3
markdownWords7
totalWords824
ratio0.008
matches
0"Lucien."
1"thunk"
2"Find her. She owes me."
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions8
unquotedAttributions0
matches(empty)
98.45% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions20
wordCount679
uniqueNames5
maxNameDensity1.03
worstName"Aurora"
maxWindowNameDensity1.5
worstWindowName"Aurora"
discoveredNames
Eva3
Aurora7
Evan3
London1
Lucien6
persons
0"Eva"
1"Aurora"
2"Evan"
3"Lucien"
places
0"London"
globalScore0.985
windowScore1
93.18% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences44
glossingSentenceCount1
matches
0"smelled like Eva’s books and the faintest"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount824
matches(empty)
76.58% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount2
totalSentences74
matches
0"knew that voice"
1"like that, she"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs30
mean27.47
std19.47
cv0.709
sampleLengths
061
130
286
326
432
515
616
722
837
912
1017
1110
1244
1350
1457
1512
1636
1716
1816
198
2011
2148
2217
2321
2434
2515
2655
273
289
298
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences57
matches(empty)
0.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount4
totalVerbs127
matches
0"were placing"
1"wasn’t letting"
2"was asking was getting"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount5
semicolonCount0
flaggedSentences5
totalSentences74
ratio0.068
matches
0"The scent of cardamom and spiced lamb hit her first—Eva’s cooking, always lingering even when the kitchen was empty."
1"Her pulse hammered in her throat as she stepped inside, the door swinging wide enough for her to see him—tall, impossibly so, his platinum blond hair slicked back like he’d just stepped out of a tailor’s parlor."
2"She hadn’t thought about Evan in months—not since she’d burned his letters, since she’d left London behind."
3"She unfolded it carefully, her stomach twisting as she read the scrawled words—*Find her."
4"And just like that, she was back in the middle of it—of him, of the way his voice could make her pulse race, of the way his presence filled the room until there was no space left for anything else."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount685
adjectiveStacks0
stackExamples(empty)
adverbCount27
adverbRatio0.03941605839416058
lyAdverbCount5
lyAdverbRatio0.0072992700729927005
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences74
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences74
mean11.14
std7.82
cv0.703
sampleLengths
023
119
219
310
44
515
61
737
820
929
1013
119
124
1314
1418
1513
162
1711
185
1918
204
2110
2220
237
247
255
2610
276
281
2910
303
3117
3220
334
3424
358
3618
3710
385
3914
4019
416
423
4312
4419
4514
463
473
4813
4911
63.51% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.40540540540540543
totalSentences74
uniqueOpeners30
60.61% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences55
matches
0"Then came the sound of"
ratio0.018
45.45% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount24
totalSentences55
matches
0"She knew that voice."
1"Her pulse hammered in her"
2"He was leaning against the"
3"he said, as if she"
4"She exhaled through her nose,"
5"His lips quirked, just for"
6"She crossed her arms, the"
7"She wasn’t letting him in"
8"He tilted his head, studying"
9"Her fingers twitched at her"
10"he said, stepping forward"
11"She hadn’t thought about Evan"
12"He reached into his jacket,"
13"It landed with a soft"
14"She unfolded it carefully, her"
15"She owes me.* Evan’s handwriting"
16"she said, her voice quieter"
17"She pulled her arm back"
18"His expression darkened, just for"
19"She wanted to argue."
ratio0.436
69.09% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount43
totalSentences55
matches
0"The door to Eva’s flat"
1"The scent of cardamom and"
2"Aurora froze, her fingers still"
3"She knew that voice."
4"Her pulse hammered in her"
5"He was leaning against the"
6"The amber light from the"
7"he said, as if she"
8"The name rolled off his"
9"She exhaled through her nose,"
10"His lips quirked, just for"
11"Aurora shut the door behind"
12"Lucien set his glass down"
13"She crossed her arms, the"
14"The flat was hers now,"
15"She wasn’t letting him in"
16"He tilted his head, studying"
17"The name hit her like"
18"Her fingers twitched at her"
19"he said, stepping forward"
ratio0.782
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount2
totalSentences55
matches
0"When he’s dangerous."
1"Because some favors weren’t just"
ratio0.036
93.60% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences29
technicalSentenceCount2
matches
0"She pulled her arm back instinctively, as if she could hide it from him."
1"And if he was asking questions, that meant he was getting closer."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags8
uselessAdditionCount2
matches
0"he said, as if she were a ghost he’d half-expected to see"
1"she said, her voice quieter than she intended"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags5
fancyCount1
fancyTags
0"she demanded (demand)"
dialogueSentences25
tagDensity0.2
leniency0.4
rawRatio0.2
effectiveRatio0.08
79.8284%