Run: 2026-07-07-01KWZ5XK8XSH97DXJXGJD1WEGF

Run Details

Duration:
56.2s
Cost:
$0.004338
Provider:
AionLabs

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
Rain needled the back of her neck as Detective Harlow Quinn pressed herself flat against the brick wall of the alley, the rough surface scraping against her coat. The green neon of The Raven's Nest painted the puddles ahead of her in sickly jade, and she watched the door of Silas' bar with the patience of a woman who had learned, eighteen years into the job, that the best arrests happened when you waited for the suspect to come to you. Tomás Herrera emerged at 11:47 PM, pulling the collar of his jacket up against the downpour. The Saint Christopher medallion caught the light for a fraction of a second as he turned, the warm brown of his skin glistening with rain. Quinn saw his eyes sweep the street once, twice—a medical training that had taught him to assess a scene before entering it. But he didn't spot her. He never did. She let him get half a block before she stepped out of the alley, keeping to the shadows of the awnings, her footsteps swallowed by the hiss of tyres on wet asphalt. The leather watch on her left wrist ticked against her skin as she moved, a familiar rhythm she'd come to rely on in the lulls between the chaos. Herrera walked with purpose, shoulders curved against the weather, and he made his way north through Soho with the kind of deliberate pace that suggested he knew exactly where he was going. Quinn followed, her breath a white plume in the cold that tasted of diesel and rain. He turned down a narrow street lined with shuttered shops, and Quinn picked up her pace, the soles of her shoes slapping against the wet cobblestones. The sound echoed between the buildings, too loud in the silence of the empty street. Herrera's head snapped around, and their eyes met across the twenty metres of rain-soaked distance. Warm brown. Scarred forearm visible as his jacket rode up. The medallion swung as he bolted. "Stop! Police!" Quinn shouted, her voice a blade through the rain. She was already moving, her body launching into the chase before her mind had finished processing the command. Herrera was fast, but he moved with the awkward gait of someone who had learned to sprint in crowded hospital corridors, not on rain-slicked streets. He ducked through a gap between two buildings, and Quinn followed without hesitation, the sharp corner scraping against her shoulder as she forced herself through the narrow passage. The alley opened into a small courtyard where someone had left a stack of wooden pallets. Herrera vaulted them with surprising agility, the medallion flying out from his chest, and landed hard on the other side. Quinn took a different path, slamming her palm against the top of a brick wall and swinging herself over, her military training turning the obstacle into a fluid motion. She landed in a crouch, her hand going to the Glock holstered under her coat. She didn't draw it, not yet, but her fingers brushed against the familiar grip, a habit worn into her muscles by a decade and a half of carrying it. Herrera was already at the far end of the next street, his curly dark hair plastered to his head by the rain. He glanced back, and she saw the calculation in his eyes—the paramedic assessing the situation, looking for a way to de-escalate, to escape. But this wasn't a hospital room, and the patient wasn't coming to him. Quinn pushed harder, her lungs burning with the cold air, her legs eating up the distance between them. She was faster, stronger, and she knew it. Herrera was a former paramedic with good instincts and a guilty conscience, but Quinn had chased killers through the dark of London for years. They ran past the red brick of St. Pancras, the train station's clock face a pale yellow eye watching them from above. Herrera cut right, heading toward Camden, and Quinn felt a prickle of unease at the base of her skull. Camden meant the old Tube tunnels, the abandoned stations that had been sealed off after the war. And the Veil Market moved beneath Camden this time of month. She'd heard rumors. Whispered accounts from informants who had crossed the line between the world she policed and the one that existed in the shadows. A market that required a bone token for entry. Goods that couldn't exist in any catalog. People who treated with powers that had no place in a detective's notebook. Herrera reached the entrance to an old station, one that had been closed since the 1940s. The signs were faded, the iron gate rusted and chained, but Quinn saw that the chain hung loose, the padlock lying open on the ground. Herrera wrenched the gate open, the screech of rusted iron cutting through the rain, and plunged into the darkness beyond. Quinn stopped at the top of the steps. The rain still fell around her, cold and relentless. Water ran down her face, dripped from her sharp jaw, soaked into the collar of her coat. Below, the steps descended into a darkness that seemed thicker than the night should have been, the kind of dark that swallowed light before it had a chance to touch it. She could still hear Herrera's footsteps, the slap of his shoes on stone, descending deeper. She could hear something else, too—a low hum that vibrated through the ground, through the soles of her shoes, through her teeth. It wasn't a machine. It was too organic, too alive, too much like the sound of a heartbeat in the womb. Her hand went to her watch, fingers tracing the worn leather. Three years since Morris had died. Three years since she'd watched her partner walk into a warehouse in Rotherhithe and never walk out. The official report said misadventure, a tragic accident, but Quinn had seen the state of his body, the expression on his face, the way his eyes had looked like they'd seen something that had burned them from the inside out. She didn't know then. She understood now—a little, not enough, but enough to know that Morris hadn't died by accident. He'd died because he'd found something, the kind of something that got a person killed and then written out of the official records. Herrera was her link to that world. He treated the people who had been touched by it, the ones who came back from the Veil with injuries that hospitals called impossible and police called unsolved. He knew the names. He knew the places. He knew what had happened to Morris. The bone token. She didn't have one. Entry to the Veil Market without one was forbidden, a violation that would mark her as an outsider, a threat. If she went down those steps, she was leaving the world she knew behind, the rules of her badge, the safety of her jurisdiction. But Morris's face waited for her in the dark of her mind, and she had been waiting for this moment for three years. Quinn drew her Glock, the familiar weight settling into her hand. She checked the chamber, felt the round seated there. Then she stepped onto the first descending stair, the rain still falling behind her, and let the dark swallow her whole.
created_at"2026-07-07T20:57:08.147Z" 7/7/2026, 8:57:08 PM
model"aion-labs/aion-3.0-mini-20260707"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency788
moderation_latency(null)
generation_time55865
tokens_prompt914
tokens_completion3191
native_tokens_prompt826
native_tokens_completion2744
native_tokens_completion_images(null)
native_tokens_reasoning1425
native_tokens_cached157
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)
usage0.00433816
router(null)
provider_responses
0
endpoint_id"0ad7ab68-a351-4a96-b2ef-fa8fe13adae3"
id"8efee9f04576415086285c65c731f365"
is_byokfalse
latency786
model_permaslug"aion-labs/aion-3.0-mini-20260707"
provider_name"AionLabs"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer(null)
request_id"req-1783457828-GwDFNB91wvz0KS2JjBqg"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1783457828-QbWmvjQmKozY2eE2Egft"
upstream_id"8efee9f04576415086285c65c731f365"
total_cost0.00433816
cache_discount0.00008164
upstream_inference_cost0
provider_name"AionLabs"
response_cache_source_id(null)
data_region"global"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags2
adverbTagCount0
adverbTags(empty)
dialogueSentences1
tagDensity1
leniency1
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1224
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)
55.07% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1224
totalAiIsms11
found
0
word"glistening"
count1
1
word"footsteps"
count2
2
word"familiar"
count3
3
word"echoed"
count1
4
word"silence"
count1
5
word"vibrated"
count1
6
word"tracing"
count1
7
word"weight"
count1
highlights
0"glistening"
1"footsteps"
2"familiar"
3"echoed"
4"silence"
5"vibrated"
6"tracing"
7"weight"
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
narrationSentences73
matches
0"felt a prickle"
64.58% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount2
hedgeCount2
narrationSentences73
filterMatches
0"watch"
hedgeMatches
0"happened to"
1"try to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences73
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen53
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1220
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions2
unquotedAttributions0
matches(empty)
91.03% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions52
wordCount1187
uniqueNames19
maxNameDensity1.18
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Detective1
Harlow1
Quinn14
Raven1
Nest1
Tomás1
Herrera12
Saint1
Christopher1
Soho1
Glock2
London1
St1
Camden3
Tube1
Veil3
Market2
Morris4
Rotherhithe1
persons
0"Harlow"
1"Quinn"
2"Raven"
3"Nest"
4"Tomás"
5"Herrera"
6"Saint"
7"Christopher"
8"Market"
9"Morris"
places
0"Detective"
1"Soho"
2"London"
3"St"
4"Veil"
5"Rotherhithe"
globalScore0.91
windowScore1
70.63% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences63
glossingSentenceCount2
matches
0"seemed thicker than the night should have been, the kind of dark that swallowed light before it had a chance to touch it"
1"looked like they'd seen something that ha"
36.07% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches2
per1kWords1.639
wordCount1220
matches
0"not yet, but her fingers brushed against the familiar grip, a habit worn"
1"not enough, but enough to know"
75.34% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount2
totalSentences73
matches
0"saw that the"
1"know that Morris"
54.95% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs24
mean50.83
std17.4
cv0.342
sampleLengths
081
171
260
348
456
516
629
753
865
944
1058
1150
1269
1354
1461
158
1657
1758
1874
1943
2050
2151
2223
2341
81.23% Passive voice overuse
Target: ≤2% passive sentences
passiveCount5
totalSentences73
matches
0"been sealed"
1"been closed"
2"were faded"
3"been touched"
4"was forbidden"
56.63% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount4
totalVerbs186
matches
0"was going"
1"was already moving"
2"wasn't coming"
3"was leaving"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount4
semicolonCount0
flaggedSentences4
totalSentences73
ratio0.055
matches
0"Quinn saw his eyes sweep the street once, twice—a medical training that had taught him to assess a scene before entering it."
1"He glanced back, and she saw the calculation in his eyes—the paramedic assessing the situation, looking for a way to de-escalate, to escape."
2"She could hear something else, too—a low hum that vibrated through the ground, through the soles of her shoes, through her teeth."
3"She understood now—a little, not enough, but enough to know that Morris hadn't died by accident."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount50
adjectiveStacks0
stackExamples(empty)
adverbCount1
adverbRatio0.02
lyAdverbCount1
lyAdverbRatio0.02
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences73
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences73
mean16.71
std9.74
cv0.583
sampleLengths
028
153
216
325
422
55
63
732
828
932
1016
1126
1215
1315
142
158
166
1711
1818
1925
2028
2116
2220
2329
2415
2529
2622
2723
2813
2918
308
3124
328
3314
3419
3517
3611
373
3822
399
407
4113
4216
4325
4420
458
469
4717
4831
4915
50.68% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats8
diversityRatio0.3698630136986301
totalSentences73
uniqueOpeners27
46.30% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences72
matches
0"Then she stepped onto the"
ratio0.014
81.11% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount25
totalSentences72
matches
0"He never did."
1"She let him get half"
2"He turned down a narrow"
3"She was already moving, her"
4"He ducked through a gap"
5"She landed in a crouch,"
6"She didn't draw it, not"
7"He glanced back, and she"
8"She was faster, stronger, and"
9"They ran past the red"
10"She'd heard rumors."
11"She could still hear Herrera's"
12"She could hear something else,"
13"It wasn't a machine."
14"It was too organic, too"
15"Her hand went to her"
16"She didn't know then."
17"She understood now—a little, not"
18"He'd died because he'd found"
19"He treated the people who"
ratio0.347
36.39% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount61
totalSentences72
matches
0"Rain needled the back of"
1"The green neon of The"
2"Tomás Herrera emerged at 11:47"
3"The Saint Christopher medallion caught"
4"Quinn saw his eyes sweep"
5"He never did."
6"She let him get half"
7"The leather watch on her"
8"Herrera walked with purpose, shoulders"
9"Quinn followed, her breath a"
10"He turned down a narrow"
11"The sound echoed between the"
12"Herrera's head snapped around, and"
13"The medallion swung as he"
14"Quinn shouted, her voice a"
15"She was already moving, her"
16"Herrera was fast, but he"
17"He ducked through a gap"
18"The alley opened into a"
19"Herrera vaulted them with surprising"
ratio0.847
69.44% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences72
matches
0"If she went down those"
ratio0.014
69.97% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences49
technicalSentenceCount5
matches
0"Quinn followed, her breath a white plume in the cold that tasted of diesel and rain."
1"She was already moving, her body launching into the chase before her mind had finished processing the command."
2"Herrera was fast, but he moved with the awkward gait of someone who had learned to sprint in crowded hospital corridors, not on rain-slicked streets."
3"Quinn pushed harder, her lungs burning with the cold air, her legs eating up the distance between them."
4"The official report said misadventure, a tragic accident, but Quinn had seen the state of his body, the expression on his face, the way his eyes had looked like…"
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags2
uselessAdditionCount1
matches
0"Quinn shouted, her voice a blade through the rain"
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags1
fancyCount1
fancyTags
0"Quinn shouted (shout)"
dialogueSentences1
tagDensity1
leniency1
rawRatio1
effectiveRatio1
71.3141%