Run: 2026-05-27-01KSMEQ2DCQPZNRSBGWV81RP0E

Run Details

Duration:
23.5s
Cost:
$0.001227
Provider:
Parasail

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 pounded the cobbled streets, echoing off the relentless drizzle as Detective Harlow Quinn sprinted past the Yes But No Records store. Her carefully polished leather shoes splattered through the waterlogging with each hurried step. Another gust of wind tousled her closely cropped salt-and-pepper hair, plastering strands of it to her forehead as she squinted against the rain running down her sharp jawline. The worn leather watch on her left wrist caught the intermittent flicker of the street lamps, its hands blurring as she raced along. The suspect - a man in a long black coat with his hood pulled up - had been spotted exiting Silas' bar earlier this evening, known in some circles as The Raven's Nest. Sure, it was simply another rundown bar on a damp Thursday night in Soho, London. But Quinn had been tracking the suspect and his associates for weeks now. She knew more went on there behind closed doors. She'd slipped inside, searching the dimly lit room. The walls were a dizzying jumble of old maps and black-and-white photographs. Behind the bar, Silas gave her a curt nod. "Evening, Detective," he'd called with similar acquiescence and reserve each time they had met. "Sir, I'm looking for a man. Man in a black coat. Tall. Hood up. Anyone seen him?" She'd asked. "Hm, no can do. See him-?" Silas replied, turning his spa tantalizingly. She tried another angle, scoped the room, and when she knew - she knew - the perp had slipped out, she'd burst out of the bar, leaving Silas to stare after her in confusion. Quinn shot around the corner, boots pounding against damp cobblestone, heart pounding. Her prey was directly ahead, long stride eating up the rain-drenched pavement. Where the hell was he going? "Oi! Stop! Metropolitan Police!" She shouted, but the man didn't slow. She chased after him, but he was fast, coat billowing out behind him like a curtain. They raced from street to street, the manor houses and restaurants giving way to train station entrances. Quinn mentally mapped it. They were in Camden now. But where... The station was a maze of tunnels and detritus. Not ideal. The man slipped down a stairs, and she took it two at a time. It smelled of mildew and rust. The spirit of London's underground, a mixture of history and corruption, threatened to suffocate her as she pushed on, determined to bring the killer to justice. But it was getting harder. He was getting away. Up ahead, there was a dull glow, ominous, beckoning. Quinn knew she shouldn't follow. Trepidation raced through her blood. Her gut screamed. If this was a trap, she'd be walking into it willingly. If it was not, she would be a fool to keep going without support. But the trail was getting colder, the rain louder, the world more treacherous, and she had waited so long. Her partner's memories haunted her, waking and sleeping, floating in her head like old ghost stories. Detective Marlene Quinn watched the back of the hood, the obscured figure's actions, every delaying movement, from behind her cover, rain soaking though her clothing and into her skin, as the man in black ran on. She felt that thundering thumping in her chest. A premonition of pain. Like when her partner Julian Morris was killed. She clenched her eyes shut against memory. She had been tracking a man then, too. Without warning, she'd heard a shot - and then silence. Just after six a.m., the call came. Another homicide. But this was no ordinary murder victim. This was a cop. The family liaison told the tale: Imperial college professor. Suspect had come to him, seeking healing from injuries, both physical and mental. Afterward the professor was killed. Julian had reached out to his family and sought to resolve it himself, only to be discovered inside his own apartment, head of him,. She remembered the police tape fluttering in the early morning wind, the chaos in CSI and detectives trying to sort out an impossible crime. Quinn slowly exhaled, reopening her eyes. Not the past, now. This was the here and now. And she didn't have time to waste, ruminating. Her hand closed around the pistol on her hip. She didn't like guns. She didn't like their weight and power. And yet in moments like these, they brought a perverse sense to uncertainty. The suspect paused outside a closed door, backed up by the walls of the station passage. Quinn clicked off the safety of the gun. "Police. Last chance," she called, her voice carrying down the corridor. After a moment of tense silence, a metallic screech signaled that the door was opening. The man pulled it open and stepped forward - but it was immediately apparent to Harlow that this was no ordinary door. More of a portal. She took a deep breath, tasting a brief moment of cool, damp air before it was instantly replaced by the scent of something nearby that made her head spin. The man in black flashed her a cruel smile before he stepped through the portal. And the door was shut. Quinn stood alone in the abandoned tunnel, watching the door. There was no knob, no handle - the portal seemed to have vanished after closing. Water dripped down the ancient, rusted metal. She could feel the faint magic emanating from it, like a persistent hum. ' She wanted to follow him, she really did, but she knew it was too risky. There was no going back from that door, only the unknown on the other side. She took a last look at the portal - but it was already fading from view, becoming nothing more than another entry The detective, shivering, shook her head and stepped away, the cold rain and the blurred fog settling into her bones as she jogged away, pistol snap back into place.
created_at"2026-05-27T10:12:07.225Z" 5/27/2026, 10:12:07 AM
model"thedrummer/skyfall-36b-v2"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency206
moderation_latency(null)
generation_time23415
tokens_prompt914
tokens_completion1437
native_tokens_prompt840
native_tokens_completion1268
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached832
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
service_tier(null)
usage0.0012268
router(null)
provider_responses
0
endpoint_id"1eb01ded-ae11-49e6-8aa6-3067584070bd"
id"chatcmpl-b841f6ee956af219"
is_byokfalse
latency206
model_permaslug"thedrummer/skyfall-36b-v2"
provider_name"Parasail"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.15.0; linux; x64))"
http_referer(null)
request_id"req-1779876727-UTvHWUGd2NiSiJ8VCNf8"
session_id(null)
api_type"completions"
id"gen-1779876727-lVOY1CqU1zHK56noLiJU"
upstream_id"chatcmpl-b841f6ee956af219"
total_cost0.0012268
cache_discount0.0002496
upstream_inference_cost0
provider_name"Parasail"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags6
adverbTagCount0
adverbTags(empty)
dialogueSentences5
tagDensity1
leniency1
rawRatio0
effectiveRatio0
84.60% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount974
totalAiIsmAdverbs3
found
0
adverb"carefully"
count1
1
adverb"slowly"
count1
2
adverb"really"
count1
highlights
0"carefully"
1"slowly"
2"really"
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)
23.00% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount974
totalAiIsms15
found
0
word"echoing"
count1
1
word"flicker"
count1
2
word"raced"
count3
3
word"pounding"
count2
4
word"determined"
count1
5
word"trepidation"
count1
6
word"treacherous"
count1
7
word"silence"
count2
8
word"resolve"
count1
9
word"weight"
count1
10
word"could feel"
count1
highlights
0"echoing"
1"flicker"
2"raced"
3"pounding"
4"determined"
5"trepidation"
6"treacherous"
7"silence"
8"resolve"
9"weight"
10"could feel"
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
emotionTells1
narrationSentences79
matches
0"r in confusion"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences79
filterMatches
0"watch"
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences79
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen50
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords983
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions6
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions28
wordCount937
uniqueNames14
maxNameDensity0.96
worstName"Quinn"
maxWindowNameDensity1.5
worstWindowName"Quinn"
discoveredNames
Detective2
Harlow2
Quinn9
Records1
Sure1
Thursday1
Soho1
London2
Silas3
Camden1
Marlene1
Julian2
Morris1
Imperial1
persons
0"Detective"
1"Harlow"
2"Quinn"
3"Records"
4"Silas"
5"Marlene"
6"Julian"
7"Morris"
places
0"Soho"
1"London"
2"Camden"
globalScore1
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences61
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount983
matches(empty)
82.28% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount2
totalSentences79
matches
0"felt that thundering"
1"signaled that the"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs18
mean54.61
std28.35
cv0.519
sampleLengths
087
170
243
319
446
530
627
785
856
935
1048
11128
1273
1319
1490
1546
1652
1729
91.94% Passive voice overuse
Target: ≤2% passive sentences
passiveCount3
totalSentences79
matches
0"been spotted"
1"was killed"
2"was killed"
46.74% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount4
totalVerbs174
matches
0"was getting"
1"was getting"
2"was opening"
3"was already fading"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount8
semicolonCount0
flaggedSentences6
totalSentences79
ratio0.076
matches
0"The suspect - a man in a long black coat with his hood pulled up - had been spotted exiting Silas' bar earlier this evening, known in some circles as The Raven's Nest."
1"She tried another angle, scoped the room, and when she knew - she knew - the perp had slipped out, she'd burst out of the bar, leaving Silas to stare after her in confusion."
2"Without warning, she'd heard a shot - and then silence."
3"The man pulled it open and stepped forward - but it was immediately apparent to Harlow that this was no ordinary door."
4"There was no knob, no handle - the portal seemed to have vanished after closing."
5"She took a last look at the portal - but it was already fading from view, becoming nothing more than another entry The detective, shivering, shook her head and stepped away, the cold rain and the blurred fog settling into her bones as she jogged away, pistol snap back into place."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount129
adjectiveStacks0
stackExamples(empty)
adverbCount2
adverbRatio0.015503875968992248
lyAdverbCount2
lyAdverbRatio0.015503875968992248
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences79
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences79
mean12.43
std8.84
cv0.711
sampleLengths
023
113
228
323
433
515
613
79
88
912
109
1114
1219
1312
1434
1512
1612
176
1811
1916
2017
214
225
232
249
252
2614
276
2826
295
304
319
325
335
343
3511
3614
3719
3816
3936
408
414
428
437
448
4510
467
472
487
494
66.24% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats6
diversityRatio0.4430379746835443
totalSentences79
uniqueOpeners35
88.89% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences75
matches
0"Just after six a.m., the"
1"More of a portal."
ratio0.027
81.33% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount26
totalSentences75
matches
0"Her carefully polished leather shoes"
1"She knew more went on"
2"She'd slipped inside, searching the"
3"he'd called with similar acquiescence"
4"She tried another angle, scoped"
5"Her prey was directly ahead,"
6"She shouted, but the man"
7"She chased after him, but"
8"They raced from street to"
9"They were in Camden now."
10"It smelled of mildew and"
11"He was getting away."
12"Her gut screamed."
13"Her partner's memories haunted her,"
14"She felt that thundering thumping"
15"She clenched her eyes shut"
16"She had been tracking a"
17"She remembered the police tape"
18"Her hand closed around the"
19"She didn't like guns."
ratio0.347
100.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount53
totalSentences75
matches
0"The rain pounded the cobbled"
1"Her carefully polished leather shoes"
2"Another gust of wind tousled"
3"The worn leather watch on"
4"The suspect - a man"
5"She knew more went on"
6"She'd slipped inside, searching the"
7"The walls were a dizzying"
8"he'd called with similar acquiescence"
9"Silas replied, turning his spa"
10"She tried another angle, scoped"
11"Quinn shot around the corner,"
12"Her prey was directly ahead,"
13"She shouted, but the man"
14"She chased after him, but"
15"They raced from street to"
16"Quinn mentally mapped it."
17"They were in Camden now."
18"The station was a maze"
19"The man slipped down a"
ratio0.707
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount2
totalSentences75
matches
0"If this was a trap,"
1"If it was not, she"
ratio0.027
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences34
technicalSentenceCount0
matches(empty)
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount2
matches
0"She shouted, but the man didn't slow"
1"she called, her voice carrying down the corridor"
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags3
fancyCount1
fancyTags
0"She shouted (shout)"
dialogueSentences5
tagDensity0.6
leniency1
rawRatio0.333
effectiveRatio0.333
82.1675%