Run: 2026-02-24-01KJ8VYH1CCM5D5G4PJQMFGYWB

Run Details

Model:
Aion 2.0
Duration:
56.3s
Cost:
$0.004478
Provider:
AionLabs

Model input

System
You are an expert fiction writer. Always keep the following rules in mind: - Write in past tense and use General English spelling, grammar, and colloquialisms/slang. - Write in active voice - Always follow the "show, don't tell" principle. - Avoid adverbs and cliches and overused/commonly used phrases. Aim for fresh and original descriptions. - Convey events and story through dialogue. - Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. - Skip "he/she said said" dialogue tags and convey people's actions or face expressions through their speech - Avoid mushy dialog and descriptions, have dialogue always continue the action, never stall or add unnecessary fluff. Vary the descriptions to not repeat yourself. - Put dialogue on its own paragraph to separate scene and action. - Reduce indicators of uncertainty like "trying" or "maybe" When writing text: - NEVER conclude the scene on your own, follow the beat instructions very closely. - NEVER end with foreshadowing. - NEVER write further than what I prompt you with. - AVOID imagining possible endings, NEVER deviate from the instructions. - STOP EARLY if the continuation contains what was required in the instructions. You do not need to fill out the full amount of words possible.
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <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> Continue the story using the following instructions: <instructions> 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. </instructions>

Model response

AI
The rain fell in steady, cold sheets, turning the neon glow of Soho into smears of colour on slick black asphalt. Detective Harlow Quinn leaned against a damp brick wall in the shadow of a fire escape, the collar of her trench coat turned up. The worn leather watch on her left wrist felt heavy with moisture. Her eyes, brown and unblinking, were fixed on the distinctive green neon sign that spelled out ‘The Raven’s Nest’. Water dripped from the closely cropped salt-and-pepper hair plastered to her scalp. Movement at the door. The heavy oak door swung inward, spilling a wedge of amber light and the low thrum of conversation onto the wet pavement. A figure emerged, pulling a hood up against the rain. Even in the poor light, Quinn recognised the set of the shoulders, the way he moved with a paramedic’s efficient grace. Tomás Herrera. He glanced left, then right, his hand going to the Saint Christopher medallion at his throat. A nervous tell. Quinn pushed off the wall, her movement a study in military precision. She’d been waiting three hours for this. Three years of dead ends and the ghost of Morris’s laugh in her ear, and tonight, maybe, a thread to pull. She kept a half-block behind, using the evening crowd as cover—theatre-goers huddled under umbrellas, late-shift workers hurrying home. Herrera moved with purpose, not haste, down Dean Street, then cut through a narrow alley that stank of wet garbage and stale beer. The rain muffled her footsteps, but he was alert. He looked over his shoulder once, twice, and then his pace quickened. “Herrera! Metropolitan Police! Stop right there!” Her voice cut through the drumming rain. He froze for a split second, then broke into a sprint. Quinn cursed under her breath and gave chase. Her shoes slipped on the greasy cobbles of the alley. He was fast, younger, fueled by panic. He burst out onto a broader street, dodging between a black cab and a delivery van, the horn blaring. Quinn followed, her sharp jaw set, breath burning in her lungs. Eighteen years on the force, but desk work had softened her edges. She pushed the thought of Morris away. “Tomás! It doesn’t have to be like this!” He didn’t answer. He vaulted over a low iron railing, dropped into a sunken service area, and was gone. Quinn skidded to the edge. A metal staircase led down into darkness. She hesitated for only a heartbeat, then descended, hand on the service pistol at her hip. The air grew colder, smelling of damp concrete and something else—ozone, and a faint, coppery tang. The staircase ended in a brick-lined tunnel, part of the old utility labyrinth beneath the city. A single, flickering bulb illuminated a junction. She heard running footsteps echoing from the left-hand passage. She ran, the tunnel walls closing in. The sound of the rain faded, replaced by the drip of water and her own ragged breathing. The tunnel opened abruptly into a vast, cavernous space. The abandoned Tube station. Camden Town, the old Northern line platform. But it wasn’t abandoned now. Quinn stopped dead, her hand falling away from her gun. The platform was alive. Dozens of stalls constructed from scrap wood and moth-eaten velvet lined the walls, lit by lanterns that burned with a weird, greenish flame. Figures moved in the gloom—some human, some decidedly not. A creature with skin like tree bark haggled over a bundle of dried herbs. A woman with eyes that reflected the light like a cat’s examined a row of gleaming blades. The air hummed with low conversation, the clink of glass, and that same ozone smell, now overwhelming. The Veil Market. And there, thirty yards away, standing at a stall, was Tomás Herrera. He was talking urgently to a hooded vendor, gesturing with his hands. The scar on his left forearm was visible as his sleeve rode up. He hadn’t seen her yet. Between Quinn and the market floor was a makeshift archway of rusted train tracks and animal bones. A figure stood beneath it, blocking the way. Tall, thin, wrapped in a long coat that seemed to drink the light. Its face was hidden in shadow, but one long-fingered hand was extended, palm up. Quinn took a step forward. The figure did not move. “You lack the token.” The voice was dry, like leaves scraping over stone. “Metropolitan Police. I’m in pursuit of a suspect.” A low, rasping sound that might have been laughter. “Your authority ends at the arch, detective. This is not your city. The token.” She looked past the guardian. Herrera was finishing his transaction, accepting a small, cloth-wrapped package from the vendor. He turned, his eyes scanning the crowd, and then they locked onto hers. His face went pale. He mouthed a single word that looked like “Don’t,” then melted back into the throng, heading for a darker tunnel at the far end of the platform. Her every instinct screamed to go after him. This was it. The lead. The thing Morris had stumbled into. A hidden world operating right under their noses. But the guardian was still there, an immovable object. She saw no weapon, but the air around it crackled with static. The green lantern light glinted off things in the shadows that she couldn’t quite identify—shapes that moved wrong. She could rush it. Draw her weapon. Announce herself. She was Harlow Quinn, with eighteen years and a commendation for bravery. She had faced armed robbers, knife-wielding addicts, a serial killer with a taste for trophies. But she had never faced anything that made the hair on her neck stand up like this. Morris had been a good detective, a better partner. He’d followed a hunch into a warehouse in Wapping one night and never walked out. The official report said structural collapse. Quinn had seen the photos. The concrete had looked… melted. And in the rubble, they’d found a single, perfect feather that shone like oil on water. She’d kept it in her desk drawer for a year before throwing it into the Thames. Herrera was getting away. The package in his hand could be evidence. Medicine for the clique, or something worse. Banned alchemical substances. Information. The guardian’s hand remained outstretched. “The token, or you turn back.” The rain from the world above was a distant memory. Here, the only water was the perpetual drip from the curved ceiling. The market’s din was a low, alien chorus. She was exposed on the threshold, a woman in a sodden trench coat in a place where the rules were written in something other than law. She could step back. Return to the rain-slick streets, to her case files and her cold, empty flat. She could file a report no one would believe. She could let the ghost of Morris fade a little more, becoming just another regret. Or she could step forward.
created_at"2026-02-24T22:22:37.112Z" 2/24/2026, 10:22:37 PM
model"aion-labs/aion-2.0-20260223"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2362
moderation_latency(null)
generation_time56150
tokens_prompt1140
tokens_completion2597
native_tokens_prompt1106
native_tokens_completion2246
native_tokens_completion_images(null)
native_tokens_reasoning851
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"
usage0.0044784
router(null)
provider_responses
0
endpoint_id"1e93b0bb-eb0f-49bc-8fda-947105413b86"
id"9563eadb-b7ad-4998-be68-a4a8834ab826"
is_byokfalse
latency183
model_permaslug"aion-labs/aion-2.0-20260223"
provider_name"AionLabs"
status200
api_type"completions"
id"gen-1771971757-gMcWUWCFCQ7vjK8mQsSv"
upstream_id"9563eadb-b7ad-4998-be68-a4a8834ab826"
total_cost0.0044784
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)
dialogueSentences7
tagDensity0.286
leniency0.571
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1158
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)
52.50% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1158
totalAiIsms11
found
0
word"efficient"
count1
1
word"footsteps"
count2
2
word"quickened"
count1
3
word"echoing"
count1
4
word"constructed"
count1
5
word"velvet"
count1
6
word"gloom"
count1
7
word"gleaming"
count1
8
word"scanning"
count1
9
word"perfect"
count1
highlights
0"efficient"
1"footsteps"
2"quickened"
3"echoing"
4"constructed"
5"velvet"
6"gloom"
7"gleaming"
8"scanning"
9"perfect"
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
narrationSentences105
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences105
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)
analyzedSentences110
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen28
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1153
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions2
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions38
wordCount1103
uniqueNames18
maxNameDensity1
worstName"Quinn"
maxWindowNameDensity1.5
worstWindowName"Quinn"
discoveredNames
Soho1
Harlow2
Quinn11
Water1
Herrera5
Saint1
Christopher1
Morris5
Dean1
Street1
Tube1
Town1
Northern1
Veil1
Market1
Tomás2
Wapping1
Thames1
persons
0"Harlow"
1"Quinn"
2"Water"
3"Herrera"
4"Saint"
5"Christopher"
6"Morris"
7"Tomás"
places
0"Soho"
1"Dean"
2"Street"
3"Town"
4"Wapping"
5"Thames"
globalScore1
windowScore1
52.60% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences77
glossingSentenceCount3
matches
0"coat that seemed to drink the light"
1"looked like then melted back into the thr"
2"quite identify—shapes that moved wrong"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1153
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences110
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs28
mean41.18
std27.65
cv0.672
sampleLengths
088
178
240
362
46
518
674
78
863
956
1025
1110
1287
1342
1452
1510
1613
178
1823
1962
2066
2136
2289
2323
2411
2556
2642
275
91.90% Passive voice overuse
Target: ≤2% passive sentences
passiveCount4
totalSentences105
matches
0"were fixed"
1"was gone"
2"was hidden"
3"was exposed"
4"were written"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs164
matches
0"was talking"
1"was finishing"
38.96% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount5
semicolonCount0
flaggedSentences4
totalSentences110
ratio0.036
matches
0"She kept a half-block behind, using the evening crowd as cover—theatre-goers huddled under umbrellas, late-shift workers hurrying home."
1"The air grew colder, smelling of damp concrete and something else—ozone, and a faint, coppery tang."
2"Figures moved in the gloom—some human, some decidedly not."
3"The green lantern light glinted off things in the shadows that she couldn’t quite identify—shapes that moved wrong."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount107
adjectiveStacks0
stackExamples(empty)
adverbCount1
adverbRatio0.009345794392523364
lyAdverbCount0
lyAdverbRatio0
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences110
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences110
mean10.48
std5.97
cv0.569
sampleLengths
021
124
212
319
412
54
622
710
821
92
1016
113
1212
137
1421
1518
1623
179
1812
196
207
2111
228
2310
247
2519
2611
2712
287
298
303
3116
325
337
3416
3516
3616
377
389
397
4017
419
424
437
445
4510
464
4723
489
4914
43.33% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats14
diversityRatio0.33636363636363636
totalSentences110
uniqueOpeners37
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences100
matches(empty)
ratio0
84.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount34
totalSentences100
matches
0"Her eyes, brown and unblinking,"
1"He glanced left, then right,"
2"She’d been waiting three hours"
3"She kept a half-block behind,"
4"He looked over his shoulder"
5"Her voice cut through the"
6"He froze for a split"
7"Her shoes slipped on the"
8"He was fast, younger, fueled"
9"He burst out onto a"
10"She pushed the thought of"
11"He didn’t answer."
12"He vaulted over a low"
13"She hesitated for only a"
14"She heard running footsteps echoing"
15"She ran, the tunnel walls"
16"He was talking urgently to"
17"He hadn’t seen her yet."
18"Its face was hidden in"
19"She looked past the guardian."
ratio0.34
30.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount86
totalSentences100
matches
0"The rain fell in steady,"
1"Detective Harlow Quinn leaned against"
2"The worn leather watch on"
3"Her eyes, brown and unblinking,"
4"Water dripped from the closely"
5"Movement at the door."
6"The heavy oak door swung"
7"A figure emerged, pulling a"
8"He glanced left, then right,"
9"A nervous tell."
10"Quinn pushed off the wall,"
11"She’d been waiting three hours"
12"She kept a half-block behind,"
13"Herrera moved with purpose, not"
14"The rain muffled her footsteps,"
15"He looked over his shoulder"
16"Her voice cut through the"
17"He froze for a split"
18"Quinn cursed under her breath"
19"Her shoes slipped on the"
ratio0.86
50.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences100
matches
0"Even in the poor light,"
ratio0.01
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences51
technicalSentenceCount2
matches
0"Dozens of stalls constructed from scrap wood and moth-eaten velvet lined the walls, lit by lanterns that burned with a weird, greenish flame."
1"Herrera was finishing his transaction, accepting a small, cloth-wrapped package from the vendor."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags2
uselessAdditionCount0
matches(empty)
7.14% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags1
fancyCount1
fancyTags
0"He mouthed (mouth)"
dialogueSentences7
tagDensity0.143
leniency0.286
rawRatio1
effectiveRatio0.286
81.6812%