Run: 2026-02-17-01KHNF9SKQNXWE4730QVBBM4EB

Run Details

Duration:
4.9s
Cost:
$0.001463
Provider:
Novita

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

AI
The rain came down in sheets, turning the Soho streets into a shimmering maze of neon reflections. Detective Harlow Quinn sprinted after the figure disappearing around the corner, her boots splashing through oily puddles. The suspect—some low-level dealer she'd been tailing for weeks—had finally led her somewhere interesting. Right to the doorstep of The Raven's Nest. She skidded to a stop outside the bar, catching her breath. The green neon sign buzzed overhead, casting an eerie glow on her salt-and-pepper hair. Through the rain-streaked window, she saw the dealer exchange quick words with the bartender before vanishing behind a bookshelf that didn't look like it should move. Quinn's sharp jaw tightened. She'd heard rumors about Silas' place, but this was the first time she'd seen proof of its secrets. The door creaked as she entered, the smell of whiskey and damp wool hitting her nostrils. Every eye in the place turned toward her—some curious, most hostile. She flashed her badge anyway. "Metropolitan Police. Looking for a man just came through here—" "Didn't see anyone," the bartender lied smoothly, polishing a glass with a rag that had seen better days. Quinn's worn leather watch ticked loudly against her wrist as she weighed her options. She could push it, demand to see the back room. But eighteen years on the force had taught her when to press and when to play along. She nodded curtly and turned on her heel, letting the door swing shut behind her. She didn't go far. Just around the corner, into the shadows of a service alley where she could watch the bar's rear exit. The rain soaked through her coat, but she stood motionless, military precision in her stance. Twenty-three minutes later—she counted—a figure slipped out the back. Not her dealer. Someone else. Taller. Moving with purpose. Tomás Herrera pulled his collar up against the rain, the Saint Christopher medallion glinting at his throat as he hurried down the alley. Quinn fell into step behind him, keeping her distance. The former paramedic had crossed her path before—always on the edges of cases that never quite added up. Tonight, he was heading somewhere in a hurry. They wound through backstreets, down into Camden, until Herrera stopped at a rusted service door beside an abandoned Tube station entrance. Quinn watched from behind a stack of pallets as he pulled something from his pocket—a small white object that looked like carved bone—and slipped it into a nearly invisible slot beside the door. The mechanism clicked. The Veil Market. She'd heard the whispers in the squad room, the stories cops told each other over bad station coffee. A place that shouldn't exist. Herrera disappeared inside, and Quinn found herself frozen at the threshold, hand hovering near her sidearm. Three years ago, Morris had chased a lead into shadows like these. They'd never found his body. Rain dripped from her hair as she made her decision. She reached into her coat pocket, fingers brushing the spare bone token she'd confiscated from a junkie last month. The dealer had babbled about "market prices" before clamming up. Now she understood. The door groaned as she pushed it open, revealing a narrow staircase descending into darkness. The air smelled of damp stone and something sharper—ozone and burnt herbs. At the bottom, flickering gas lamps illuminated a cavernous space where the old ticket hall had been. Stalls lined the walls, their proprietors hawking wares that made her stomach turn. Glass vials of swirling liquid. Books bound in what looked like human skin. A cage containing something with too many eyes. She kept her badge hidden, moving through the crowd with forced casualness. Up ahead, Herrera was speaking urgently with a hooded figure near a stall selling what appeared to be antique surgical tools. Quinn edged closer, pretending to examine a display of cursed jewelry. "—can't keep doing this," Herrera was saying in his Spanish-accented English. He rubbed the scar on his forearm absently. "They're getting closer every time." The hooded figure responded in a voice like grinding stones. "Then perhaps you should have chosen a different line of work, medic." Quinn's pulse jumped as Herrera's hand went to his medallion. She'd seen that gesture before—right before things went sideways in an interrogation room two years back. The air around them seemed to thicken, and she instinctively reached for her gun. A hand closed around her wrist. "I wouldn't do that here, detective." The voice at her ear was honeyed poison. She turned to find a woman with violet eyes smiling at her. "Newcomers should browse before they make trouble." Quinn yanked her arm free, but the moment was broken. When she looked back, Herrera and the hooded figure were gone. The woman with violet eyes melted into the crowd before Quinn could stop her. The detective stood there, rain still dripping from her clothes onto the ancient tiles. Somewhere in this den of nightmares was the truth about what happened to Morris. About what kept drawing her to these cases that defied explanation. She took a deep breath and stepped deeper into the market, following the trail of whispers that curled around her like smoke.
created_at"2026-02-17T09:36:06.018713+00:00" 2/17/2026, 9:36:06 AM
model"deepseek/deepseek-chat-v3-0324"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency340
moderation_latency(null)
generation_time4699
tokens_prompt914
tokens_completion1341
native_tokens_prompt829
native_tokens_completion1106
native_tokens_completion_images0
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"
usage0.00146255
router(null)
provider_responses
0
id"e681cc567ae6e58281d741589819da13"
status200
is_byokfalse
latency340
endpoint_id"3a816eb8-7a0b-4a9a-b497-e3a1efb349fc"
provider_name"Novita"
model_permaslug"deepseek/deepseek-chat-v3-0324"
api_type"completions"
id"gen-1771320960-utOlocsHhR7fha6H4rqH"
upstream_id"e681cc567ae6e58281d741589819da13"
total_cost0.00146255
cache_discount(null)
upstream_inference_cost0
provider_name"Novita"

Evaluation details

Result Evaluator Details Meta Data
25.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags4
adverbTagCount1
adverbTags
0"the bartender lied smoothly [smoothly]"
dialogueSentences8
tagDensity0.5
leniency1
rawRatio0.25
effectiveRatio0.25
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount877
totalAiIsmAdverbs0
found(empty)
highlights(empty)
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)
82.90% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount877
totalAiIsms3
found
0
word"glinting"
count1
1
word"stomach"
count1
2
word"pulse"
count1
highlights
0"glinting"
1"stomach"
2"pulse"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches0
maxInWindow0
found(empty)
highlights(empty)
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences68
matches(empty)
58.82% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount3
narrationSentences68
filterMatches
0"watch"
hedgeMatches
0"appeared to"
1"seemed to"
2"happened to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences72
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen35
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords860
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions3
unquotedAttributions0
matches(empty)
86.95% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions28
wordCount793
uniqueNames13
maxNameDensity1.26
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Soho1
Harlow1
Quinn10
Raven1
Nest1
Herrera6
Saint1
Christopher1
Camden1
Tube1
Veil1
Market1
Morris2
persons
0"Harlow"
1"Quinn"
2"Raven"
3"Herrera"
4"Saint"
5"Christopher"
6"Morris"
places
0"Soho"
1"Camden"
globalScore0.869
windowScore1
59.09% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences55
glossingSentenceCount2
matches
0"looked like carved bone—and slipped it in"
1"looked like human skin"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount860
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences72
matches
0"seen that gesture"
54.20% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs18
mean47.78
std16.23
cv0.34
sampleLengths
056
173
242
318
456
556
658
757
859
942
1078
1144
1224
1322
1440
1539
1635
1761
94.94% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences68
matches
0"was honeyed"
1"were gone"
61.11% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs144
matches
0"was heading"
1"was speaking"
2"was saying"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount10
semicolonCount0
flaggedSentences7
totalSentences72
ratio0.097
matches
0"The suspect—some low-level dealer she'd been tailing for weeks—had finally led her somewhere interesting."
1"Every eye in the place turned toward her—some curious, most hostile."
2"Twenty-three minutes later—she counted—a figure slipped out the back."
3"The former paramedic had crossed her path before—always on the edges of cases that never quite added up."
4"Quinn watched from behind a stack of pallets as he pulled something from his pocket—a small white object that looked like carved bone—and slipped it into a nearly invisible slot beside the door."
5"The air smelled of damp stone and something sharper—ozone and burnt herbs."
6"She'd seen that gesture before—right before things went sideways in an interrogation room two years back."
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount827
adjectiveStacks1
stackExamples
0"other over bad station"
adverbCount26
adverbRatio0.03143893591293833
lyAdverbCount9
lyAdverbRatio0.010882708585247884
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences72
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences72
mean11.94
std6.08
cv0.509
sampleLengths
017
117
214
38
411
514
626
74
818
916
1011
115
1210
1318
1414
1510
1617
1715
184
1919
2015
219
223
232
241
253
2623
279
2818
298
3021
3133
323
333
3418
355
3616
3712
385
3910
4019
4110
423
4315
4412
4517
4613
475
488
498
80.09% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats4
diversityRatio0.5138888888888888
totalSentences72
uniqueOpeners37
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences66
matches
0"Right to the doorstep of"
1"Just around the corner, into"
2"Somewhere in this den of"
ratio0.045
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount15
totalSentences66
matches
0"She skidded to a stop"
1"She'd heard rumors about"
2"She flashed her badge anyway."
3"She could push it, demand"
4"She nodded curtly and turned"
5"She didn't go far."
6"They wound through backstreets, down"
7"She'd heard the whispers in"
8"They'd never found his body."
9"She reached into her coat"
10"She kept her badge hidden,"
11"He rubbed the scar on"
12"She'd seen that gesture before—right"
13"She turned to find a"
14"She took a deep breath"
ratio0.227
66.06% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount52
totalSentences66
matches
0"The rain came down in"
1"Detective Harlow Quinn sprinted after"
2"The suspect—some low-level dealer she'd"
3"She skidded to a stop"
4"The green neon sign buzzed"
5"Quinn's sharp jaw tightened."
6"She'd heard rumors about"
7"The door creaked as she"
8"Every eye in the place"
9"She flashed her badge anyway."
10"the bartender lied smoothly, polishing"
11"Quinn's worn leather watch ticked"
12"She could push it, demand"
13"She nodded curtly and turned"
14"She didn't go far."
15"The rain soaked through her"
16"Tomás Herrera pulled his collar"
17"Quinn fell into step behind"
18"The former paramedic had crossed"
19"Tonight, he was heading somewhere"
ratio0.788
75.76% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences66
matches
0"Now she understood."
ratio0.015
59.80% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences43
technicalSentenceCount5
matches
0"Detective Harlow Quinn sprinted after the figure disappearing around the corner, her boots splashing through oily puddles."
1"Through the rain-streaked window, she saw the dealer exchange quick words with the bartender before vanishing behind a bookshelf that didn't look like it should…"
2"Quinn watched from behind a stack of pallets as he pulled something from his pocket—a small white object that looked like carved bone—and slipped it into a near…"
3"Stalls lined the walls, their proprietors hawking wares that made her stomach turn."
4"She took a deep breath and stepped deeper into the market, following the trail of whispers that curled around her like smoke."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags4
uselessAdditionCount0
matches(empty)
25.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags1
fancyCount1
fancyTags
0"the bartender lied smoothly (lie)"
dialogueSentences8
tagDensity0.125
leniency0.25
rawRatio1
effectiveRatio0.25
80.7907%