Run: 2026-02-24-01KJ8TPA8X6MPPPEMHAE0PS6ZE

Run Details

Model:
Aion 2.0
Duration:
1m 7s
Cost:
$0.004701
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 relentless, cold curtain, turning the neon signs of Soho into smears of colour on the wet pavement. Detective Harlow Quinn leaned against the brick wall in the shadow of a delivery bay, the collar of her trench coat turned up, her eyes fixed on the distinctive green glow of The Raven’s Nest across the street. The worn leather strap of her watch felt tight against her wrist, a familiar pressure marking the passage of empty hours. She’d been here since dusk, waiting for a break in the quiet comings and goings of Silas’ bar. The maps and photographs inside, she knew from a previous reconnaissance, spoke of a curated history, a front for something older and far less savoury. Movement. The door opened, spilling a wedge of amber light onto the glistening street. A figure emerged, taller than the barman, pulling a hood up against the rain. They moved with a hurried, purposeful stride, turning north. Quinn pushed off the wall, her body falling into motion with the military precision drilled into her over eighteen years of service. Her shoes, sensible and rubber-soled, made little sound as she crossed the street, a ghost in the downpour. The suspect—she thought of them as ‘the Runner’—kept a brisk pace, cutting through side alleys and across broader avenues where late-night traffic hissed by. Quinn matched it, staying half a block behind, using reflections in shop windows and the cover of other pedestrians. The Runner’s hood stayed up, their face unseen. The rain plastered Quinn’s closely cropped salt-and-pepper hair to her scalp, and she felt a trickle of cold water trace the line of her sharp jaw. Her mind, however, was a dry, focused thing. *Where are you going?* They moved out of Soho, the character of the streets shifting. The Runner descended into the warren of tunnels at Tottenham Court Road station, but instead of heading for the platforms, they took a service door marked ‘Authorised Personnel Only’, propping it open with a discarded coffee cup before disappearing inside. Quinn hesitated for only a second. The memory of DS Morris, his laughter, the empty space where he should be, pressed against her ribs. Unexplained circumstances. She’d followed procedure then, and it had gotten her nowhere but a desk and a pension recommendation she’d refused. She pushed the door open. The air was warmer down here, thick with the smell of damp concrete and ozone. Dim emergency lighting cast long shadows. She heard footsteps echoing ahead, a rapid tap-tap-tap on metal stairs. She followed, descending deeper than the public lines, into a realm of maintenance tunnels and forgotten conduits. The sound of the rain was gone, replaced by the hum of distant machinery and the drip of water from unseen pipes. Her hand went to the holster under her arm, the cool grip of her service weapon a small comfort. The Runner was leading her to Camden. She knew these tunnels, theoretically; part of the old abandoned Northern line extensions. They were a known grey area for the Met, a place where things and people could slip through the cracks. Her breath began to fog in the cooler air. After twenty minutes of silent pursuit, the Runner pushed through a heavy, rusted door onto a disused platform. Quinn hung back in the tunnel mouth, peering out. The platform was not dark. It was lit by dozens of lanterns, candles, and strings of fairy lights powered by grumbling generators. Stalls made from repurposed shipping containers and moth-eaten drapes lined the space. The air was a complex soup of smells: incense, rotting flowers, ozone, and frying food. People—if they were all people—moved between the stalls. A figure with too-long limbs haggled over a jar of glowing moss. A woman with eyes like polished jet examined a row of intricate blades. This was no ordinary black market. This was the thing whispered about in the most classified briefings, the place Morris had tried to tell her about before he vanished. The Veil Market. The Runner had stopped at the platform’s edge, near the entrance to the market proper. They turned, and for the first time, the hood fell back. It was a young man, pale, with anxious eyes. He wasn’t looking at her; he was looking at the archway that served as the market’s gate. A hulking figure stood beside it, clad in leather and iron. The bouncer. The Runner fumbled in his pocket and produced a small, pale object. He handed it over. The bouncer examined it—a bone token, carved with runes—and nodded, stepping aside. The Runner vanished into the crowd. Quinn was exposed in the tunnel. She had a choice. Forward, into a world that defied her understanding, a world that had taken Morris. Or back, to the rain-soaked streets and the slow death of her career, chasing shadows that always slipped away. Her hand went to her own pocket. Not a bone token, but the Saint Christopher medallion she’d taken from Morris’s effects after the inquest. It was warm against her fingers. A stupid superstition. But it was all she had. She stepped onto the platform. The sounds of the market enveloped her: muttered conversations in languages she didn’t recognise, the clink of glass, a low, melodic humming from a nearby stall selling wind chimes made of bird skulls. She approached the archway, her bearing straight, her face a mask of authority she no longer felt. The bouncer looked down at her. He was well over six and a half feet tall, his nose a flattened ruin. “Token,” he grunted, his voice like gravel in a drum. “I don’t have one,” Quinn said, her voice steady. “I’m with the Metropolitan Police. I need to speak with someone in charge.” A low chuckle rumbled from the bouncer. “No token, no entry. That’s the only law here, copper.” “My partner died because of what comes out of places like this,” she said, the words leaving her lips before she could stop them. It wasn’t procedure. It was just truth. The bouncer’s amusement faded. He studied her, his gaze lingering on the sharp lines of her face, the determined set of her shoulders. “Lost someone to the deep, did you?” He sighed, a sound of vast indifference. “Wait here.” He turned and lumbered into the market. Quinn stood, feeling the weight of a hundred unseen eyes upon her. She kept her hand near her weapon, her heart a hard, rapid beat against her ribs. After a minute, the bouncer returned, followed by a smaller man. He was in his late twenties, with olive skin and short, curly dark brown hair. He wore a simple grey sweater, the sleeves pushed up to his elbows, revealing a long, pale scar running along his left forearm. A Saint Christopher medallion, twin to the one in her pocket, gleamed at his throat. His warm brown eyes took her in with a paramedic’s assessing calm. “Detective,” Tomás Herrera said, his accent soft, Seville woven into the London vowels. “You are a long way from your jurisdiction.” He didn’t seem surprised to see her. “You know who I am,” Quinn stated. “I know you’ve been asking questions about the people who use my services,” he said. “I provide medical care. That is not a crime.” “It is when you lose your license,” Quinn shot back. “And when your patients are involved in things that get people killed.” Tomás’s expression was unreadable. “Your Runner, the boy with the fever? He is safe. He came for medicine I could not get him through your NHS. That is all this is, for most who come here. A chance to live.” He gestured to the market behind him. “But you did not come for him. You came for answers. They are here. But they are not free, and they are not safe.” He stepped closer, lowering his voice. “You have no token. I can vouch for you, once. But if you step through that arch, you step into my world. The rules you know mean nothing. Your badge means less. You will see things you cannot unsee. And you may not leave the same person.” He paused, letting the hum of the market fill the space between them. “Morris knew that. He was a good man. He came here once, asking similar questions.” The name was a physical blow. Quinn’s breath caught. “You knew him?” “I tried to treat him, after. It was too late.” Tomás’s eyes held a genuine sorrow. “The choice is yours, Detective. Go back to the rain. File your report. Live with the not-knowing. Or come inside, and learn why your partner really died.” The rain seemed a thousand miles away, a memory of a simpler, colder world. Here, the air was thick with possibility and peril. Quinn looked past Tomás, into the labyrinth of light and shadow. She thought of Morris’s empty chair, his unfinished notes, the quiet horror of a death with no cause. She thought of the slow erosion of truth by bureaucracy. She met Tomás’s gaze. “Lead the way.”
created_at"2026-02-24T22:00:39.461Z" 2/24/2026, 10:00:39 PM
model"aion-labs/aion-2.0-20260223"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2192
moderation_latency(null)
generation_time66654
tokens_prompt914
tokens_completion2833
native_tokens_prompt930
native_tokens_completion2473
native_tokens_completion_images(null)
native_tokens_reasoning551
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"
usage0.0047008
router(null)
provider_responses
0
endpoint_id"1e93b0bb-eb0f-49bc-8fda-947105413b86"
id"e45e68b6-37f7-46bb-94c0-51ea4745f8d3"
is_byokfalse
latency187
model_permaslug"aion-labs/aion-2.0-20260223"
provider_name"AionLabs"
status200
api_type"completions"
id"gen-1771970439-UAibGz39UyWONueq96ZW"
upstream_id"e45e68b6-37f7-46bb-94c0-51ea4745f8d3"
total_cost0.0047008
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
totalTags15
adverbTagCount0
adverbTags(empty)
dialogueSentences22
tagDensity0.682
leniency1
rawRatio0
effectiveRatio0
96.71% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1520
totalAiIsmAdverbs1
found
0
adverb"really"
count1
highlights
0"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)
63.82% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1520
totalAiIsms11
found
0
word"familiar"
count1
1
word"glistening"
count1
2
word"footsteps"
count1
3
word"echoing"
count1
4
word"complex"
count1
5
word"intricate"
count1
6
word"hulking"
count1
7
word"determined"
count1
8
word"weight"
count1
9
word"unreadable"
count1
10
word"peril"
count1
highlights
0"familiar"
1"glistening"
2"footsteps"
3"echoing"
4"complex"
5"intricate"
6"hulking"
7"determined"
8"weight"
9"unreadable"
10"peril"
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
narrationSentences105
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount2
narrationSentences105
filterMatches
0"watch"
hedgeMatches
0"began to"
1"tried to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences115
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen60
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans1
markdownWords4
totalWords1515
ratio0.003
matches
0"Where are you going?"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions11
unquotedAttributions0
matches(empty)
83.33% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions50
wordCount1212
uniqueNames21
maxNameDensity1.07
worstName"Quinn"
maxWindowNameDensity2.5
worstWindowName"Quinn"
discoveredNames
Soho2
Harlow1
Quinn13
Raven1
Nest1
Runner7
Tottenham1
Court1
Road1
Morris5
Camden1
Northern1
Met1
Veil1
Market1
Saint2
Christopher2
Herrera1
Seville1
London1
Tomás5
persons
0"Harlow"
1"Quinn"
2"Raven"
3"Runner"
4"Morris"
5"Saint"
6"Christopher"
7"Herrera"
8"Tomás"
places
0"Soho"
1"Tottenham"
2"Court"
3"Road"
4"Camden"
5"Market"
6"Seville"
7"London"
globalScore0.964
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences84
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords0.66
wordCount1515
matches
0"Not a bone token, but the Saint Christopher medallion she’d taken from Morris’s ef"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences115
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs29
mean52.24
std33.31
cv0.638
sampleLengths
0124
177
289
3101
490
576
6114
793
86
943
1039
1155
1231
1322
1417
1531
1639
1746
1865
1928
207
2124
2222
2371
2481
2512
2643
2762
287
95.24% Passive voice overuse
Target: ≤2% passive sentences
passiveCount3
totalSentences105
matches
0"was gone"
1"was lit"
2"was exposed"
91.30% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs184
matches
0"was leading"
1"was looking"
2"wasn’t looking"
18.63% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount5
semicolonCount2
flaggedSentences5
totalSentences115
ratio0.043
matches
0"The suspect—she thought of them as ‘the Runner’—kept a brisk pace, cutting through side alleys and across broader avenues where late-night traffic hissed by."
1"She knew these tunnels, theoretically; part of the old abandoned Northern line extensions."
2"People—if they were all people—moved between the stalls."
3"He wasn’t looking at her; he was looking at the archway that served as the market’s gate."
4"The bouncer examined it—a bone token, carved with runes—and nodded, stepping aside."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount325
adjectiveStacks0
stackExamples(empty)
adverbCount5
adverbRatio0.015384615384615385
lyAdverbCount2
lyAdverbRatio0.006153846153846154
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences115
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences115
mean13.17
std9.1
cv0.691
sampleLengths
022
138
221
318
425
51
613
714
89
922
1018
1124
1219
138
1426
158
164
1711
1840
196
2018
212
2219
235
2415
256
2611
2717
2822
2919
307
3113
3220
339
3418
359
365
3717
3812
3915
408
4112
4213
436
4423
453
4615
4711
489
4917
36.81% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats16
diversityRatio0.30434782608695654
totalSentences115
uniqueOpeners35
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences100
matches(empty)
ratio0
52.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount42
totalSentences100
matches
0"She’d been here since dusk,"
1"They moved with a hurried,"
2"Her shoes, sensible and rubber-soled,"
3"Her mind, however, was a"
4"They moved out of Soho,"
5"She’d followed procedure then, and"
6"She pushed the door open."
7"She heard footsteps echoing ahead,"
8"She followed, descending deeper than"
9"Her hand went to the"
10"She knew these tunnels, theoretically;"
11"They were a known grey"
12"Her breath began to fog"
13"It was lit by dozens"
14"They turned, and for the"
15"It was a young man,"
16"He wasn’t looking at her;"
17"He handed it over."
18"She had a choice."
19"Her hand went to her"
ratio0.42
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount92
totalSentences100
matches
0"The rain fell in a"
1"Detective Harlow Quinn leaned against"
2"The worn leather strap of"
3"She’d been here since dusk,"
4"The maps and photographs inside,"
5"The door opened, spilling a"
6"A figure emerged, taller than"
7"They moved with a hurried,"
8"Quinn pushed off the wall,"
9"Her shoes, sensible and rubber-soled,"
10"The suspect—she thought of them"
11"Quinn matched it, staying half"
12"The Runner’s hood stayed up,"
13"The rain plastered Quinn’s closely"
14"Her mind, however, was a"
15"They moved out of Soho,"
16"The Runner descended into the"
17"Quinn hesitated for only a"
18"The memory of DS Morris,"
19"She’d followed procedure then, and"
ratio0.92
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences100
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences52
technicalSentenceCount0
matches(empty)
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags15
uselessAdditionCount4
matches
0"Quinn said, her voice steady"
1"she said, the words leaving her lips before she could stop them"
2"He sighed, a sound of vast indifference"
3"Tomás Herrera said, his accent soft, Seville woven into the London vowels"
13.64% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags7
fancyCount3
fancyTags
0"he grunted (grunt)"
1"He sighed (sigh)"
2"Quinn stated (state)"
dialogueSentences22
tagDensity0.318
leniency0.636
rawRatio0.429
effectiveRatio0.273
75.0495%