Run: 2026-02-24-01KJ8VANX7KQY7F8M4C8F8RQDC

Run Details

Model:
Aion 2.0
Duration:
51.1s
Cost:
$0.003998
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
The rain fell in a persistent, cold drizzle, turning the neon signs of Soho into smears of colour on wet pavement. Detective Harlow Quinn pressed herself into the shadowed doorway of a closed boutique, her breath a pale plume in the damp air. Fifty yards ahead, the man she’d been tailing for three hours paused under the distinctive green glow of The Raven’s Nest, pulling his collar up against the weather. Tomás Herrera. Former paramedic. Unofficial medic to a circle of people Quinn was increasingly certain were not just eccentric, but criminal. And connected, somehow, to the hole Morris’s death had blown in the world. She watched as Herrera glanced left and right, his movements economical, alert. The scar on his left forearm was just visible below his pushed-up sleeve as he checked his watch. Quinn’s own worn leather strap felt heavy on her wrist, a familiar anchor. She didn’t need to check the time. She had the patience of eighteen years on the job, and the specific, grinding patience of three years without answers. Herrera moved off, not heading for a bus or a taxi rank, but east, towards Covent Garden. Quinn waited a three-count, then stepped out, her boots silent on the slick cobbles. Her stride was precise, a relic of her brief, earlier life in uniform, her sharp jaw set. The salt-and-pepper of her closely cropped hair was beaded with moisture. The chase was a slow, tense ballet. Herrera knew the streets, cutting through service alleys and across quiet squares. Quinn hung back, using reflections in shop windows, the occasional slowing at a crosswalk to close the gap. He was leading her on a circuitous route, a man wary of a tail. Good. That meant he had something to hide. The drizzle intensified into a proper downpour as they crossed into Camden. The tourist crowds had vanished, leaving the streets to the rain and the occasional hurrying figure. Herrera suddenly ducked into an alleyway between a shuttered record store and a kebab shop. Quinn quickened her pace, reaching the mouth of the alley in time to see him disappear through a rusted, graffiti-tagged gate that should have been locked. She approached, hand resting on the butt of her service pistol under her jacket. The gate swung open to a set of worn stone steps leading down into darkness. Not a basement. The air that wafted up was cold, carrying the distant, metallic scent of the underground and something else—ozone, and a faint, coppery tang. *Abandoned Tube station.* Morris had been found near one. His notes, before they’d gone missing from evidence, had mentioned “bone tokens” and “market nights.” Quinn had dismissed it as the ramblings of a partner under too much stress. Now, standing at the top of those steps, the hair on the back of her neck prickled. She descended, the sound of the rain fading behind her. At the bottom, a narrow service tunnel stretched into gloom, lit by a single, flickering emergency light. At the far end, she saw a figure silhouetted against a brighter, warmer glow. Herrera. He was standing before a heavy, riveted metal door. As she watched, hidden behind a pillar, he took something from his pocket—a small, pale object—and slotted it into a crevice beside the door. There was a click, a grind of old mechanisms, and the door swung inwards. The warm light spilled out, and with it a cacophony of muted sounds: chatter, the clink of glass, a strange, melodic humming. Herrera stepped through and the door began to swing shut. Quinn moved. She covered the distance in a silent sprint, her heart hammering against her ribs. She caught the door just before it sealed, her fingers curling around the cold iron edge. She pulled it open a crack and peered inside. The sight stole her breath. The abandoned Camden Town station platform had been transformed. Dozens of stalls, lit by lanterns and strings of faerie lights that burned with colours she couldn’t name, lined the old tiles. The air was thick with the smell of incense, strange spices, and that coppery tang. People—if they were all people—moved through the space. A woman with eyes like polished jet sold vials of swirling liquid. A hulking figure with skin like bark haggled over what looked like a bundle of dried feathers. At the far end, where the tunnel mouth should have been, a shimmering curtain of light pulsed like a living thing. The Veil Market. It had to be. Herrera was already melting into the crowd, heading towards a stall stacked with medical-looking supplies and jars of unidentifiable herbs. Quinn stood on the threshold, the damp of the tunnel at her back, the impossible marketplace before her. Every instinct honed over two decades screamed at her to call for backup, to treat this as a potential terrorist cell, a massive, organized crime operation. But what would she say? *I followed a suspect to a magical flea market under Camden?* They’d pull her badge. They’d think she’d gone the way Morris was supposed to have gone. Morris. He’d tried to tell her. *“It’s not what we think, Harlow. It’s older. It’s under everything.”* She’d told him to get some sleep. The memory was a cold knife in her gut. This was the territory. The unexplained circumstances. This was where the truth about her partner’s death was traded, along with enchanted goods and banned substances. She looked at Herrera, now in conversation with the herbalist, his Saint Christopher medallion glinting in the weird light. He was her only link. Quinn took a deep breath, the air tasting of magic and mildew. She had no bone token. She had only her warrant card, her gun, and a debt to a dead man. She stepped through the door, letting it sigh shut behind her, sealing her in. The sounds of the market seemed to swell for a moment, as if noting her entrance. A few nearby faces turned towards her—pale, curious, assessing. She kept her bearing rigid, her face a mask of detached authority, and began to move through the crowd, her eyes locked on the dark curls of Tomás Herrera. She was in the deep end now. All she could do was swim.
created_at"2026-02-24T22:11:46.735Z" 2/24/2026, 10:11:46 PM
model"aion-labs/aion-2.0-20260223"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2197
moderation_latency(null)
generation_time51061
tokens_prompt914
tokens_completion2339
native_tokens_prompt930
native_tokens_completion2034
native_tokens_completion_images(null)
native_tokens_reasoning773
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"
usage0.0039984
router(null)
provider_responses
0
endpoint_id"1e93b0bb-eb0f-49bc-8fda-947105413b86"
id"e6861f66-78c8-4a91-a3c1-e65d38a714cc"
is_byokfalse
latency130
model_permaslug"aion-labs/aion-2.0-20260223"
provider_name"AionLabs"
status200
api_type"completions"
id"gen-1771971106-rsCd6Mk2qZneC82bpWep"
upstream_id"e6861f66-78c8-4a91-a3c1-e65d38a714cc"
total_cost0.0039984
cache_discount(null)
upstream_inference_cost0
provider_name"AionLabs"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags2
adverbTagCount0
adverbTags(empty)
dialogueSentences2
tagDensity1
leniency1
rawRatio0
effectiveRatio0
95.22% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1047
totalAiIsmAdverbs1
found
0
adverb"suddenly"
count1
highlights
0"suddenly"
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)
61.80% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1047
totalAiIsms8
found
0
word"familiar"
count1
1
word"quickened"
count1
2
word"gloom"
count1
3
word"cacophony"
count1
4
word"hulking"
count1
5
word"pulsed"
count1
6
word"potential"
count1
7
word"glinting"
count1
highlights
0"familiar"
1"quickened"
2"gloom"
3"cacophony"
4"hulking"
5"pulsed"
6"potential"
7"glinting"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"air was thick with"
count1
highlights
0"The air was thick with"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences81
matches(empty)
54.67% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount4
narrationSentences81
filterMatches
0"watch"
hedgeMatches
0"began to"
1"tried to"
2"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences81
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen29
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans3
markdownWords25
totalWords1041
ratio0.024
matches
0"Abandoned Tube station."
1"I followed a suspect to a magical flea market under Camden?"
2"“It’s not what we think, Harlow. It’s older. It’s under everything.”"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions3
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions41
wordCount1026
uniqueNames17
maxNameDensity0.97
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Soho1
Harlow1
Quinn10
Raven1
Nest1
Herrera10
Morris4
Covent1
Garden1
Camden3
Tube1
Town1
Veil1
Market1
Saint1
Christopher1
Tomás2
persons
0"Harlow"
1"Quinn"
2"Raven"
3"Nest"
4"Herrera"
5"Morris"
6"Market"
7"Saint"
8"Christopher"
9"Tomás"
places
0"Soho"
1"Covent"
2"Garden"
3"Camden"
4"Town"
globalScore1
windowScore1
71.88% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences64
glossingSentenceCount2
matches
0"looked like a bundle of dried feathers"
1"as if noting her entrance"
7.88% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches2
per1kWords1.921
wordCount1041
matches
0"not just eccentric, but criminal"
1"not heading for a bus or a taxi rank, but east, towards Covent Garden"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences81
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs22
mean47.32
std32
cv0.676
sampleLengths
071
134
270
359
459
569
655
73
852
9121
1041
115
12104
137
1420
1576
161
1723
1834
1924
2032
2181
79.27% Passive voice overuse
Target: ≤2% passive sentences
passiveCount6
totalSentences81
matches
0"was beaded"
1"been locked"
2"been found"
3"been transformed"
4"was supposed"
5"was traded"
71.79% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs156
matches
0"was leading"
1"was standing"
2"was already melting"
1.76% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount6
semicolonCount0
flaggedSentences4
totalSentences81
ratio0.049
matches
0"The air that wafted up was cold, carrying the distant, metallic scent of the underground and something else—ozone, and a faint, coppery tang."
1"As she watched, hidden behind a pillar, he took something from his pocket—a small, pale object—and slotted it into a crevice beside the door."
2"People—if they were all people—moved through the space."
3"A few nearby faces turned towards her—pale, curious, assessing."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1038
adjectiveStacks0
stackExamples(empty)
adverbCount16
adverbRatio0.015414258188824663
lyAdverbCount5
lyAdverbRatio0.004816955684007707
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences81
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences81
mean12.85
std7.14
cv0.555
sampleLengths
021
122
228
32
42
517
613
712
818
913
107
1120
1217
1314
1417
1511
167
1712
1818
1914
201
217
2212
2316
2415
2526
2614
2715
283
2923
303
316
3229
3317
3410
3517
3614
371
389
3924
4014
4122
4210
432
4414
4516
469
475
489
4922
52.26% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats11
diversityRatio0.3950617283950617
totalSentences81
uniqueOpeners32
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences75
matches(empty)
ratio0
92.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount24
totalSentences75
matches
0"She watched as Herrera glanced"
1"She didn’t need to check"
2"She had the patience of"
3"Her stride was precise, a"
4"He was leading her on"
5"She approached, hand resting on"
6"His notes, before they’d gone"
7"She descended, the sound of"
8"He was standing before a"
9"She covered the distance in"
10"She caught the door just"
11"She pulled it open a"
12"It had to be."
13"*I followed a suspect to"
14"They’d think she’d gone the"
15"He’d tried to tell her."
16"She’d told him to get"
17"She looked at Herrera, now"
18"He was her only link."
19"She had no bone token."
ratio0.32
53.33% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount61
totalSentences75
matches
0"The rain fell in a"
1"Detective Harlow Quinn pressed herself"
2"She watched as Herrera glanced"
3"The scar on his left"
4"Quinn’s own worn leather strap"
5"She didn’t need to check"
6"She had the patience of"
7"Herrera moved off, not heading"
8"Quinn waited a three-count, then"
9"Her stride was precise, a"
10"The salt-and-pepper of her closely"
11"The chase was a slow,"
12"Herrera knew the streets, cutting"
13"Quinn hung back, using reflections"
14"He was leading her on"
15"That meant he had something"
16"The drizzle intensified into a"
17"The tourist crowds had vanished,"
18"Herrera suddenly ducked into an"
19"Quinn quickened her pace, reaching"
ratio0.813
66.67% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences75
matches
0"Now, standing at the top"
ratio0.013
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences52
technicalSentenceCount3
matches
0"Fifty yards ahead, the man she’d been tailing for three hours paused under the distinctive green glow of The Raven’s Nest, pulling his collar up against the wea…"
1"Quinn quickened her pace, reaching the mouth of the alley in time to see him disappear through a rusted, graffiti-tagged gate that should have been locked."
2"The air that wafted up was cold, carrying the distant, metallic scent of the underground and something else—ozone, and a faint, coppery tang."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags2
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
80.2847%