Run: 2026-07-07-01KWZ5Q3NS79XQRD928TDN8WT5

Run Details

Model:
Aion 3.0
Duration:
44.2s
Cost:
$0.016552
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 came down like broken glass, each drop sharp and cold against Harlow Quinn's face as she rounded the corner onto Berwick Street. Her shoes slapped wet pavement. Three months of surveillance work, and the one night she chose to follow him on foot, the sky split open. Tomás Herrera moved twenty metres ahead, his dark jacket slick with rain, one hand pressed to his chest as if guarding something beneath the fabric. He walked fast but didn't run. Not yet. Quinn matched his pace, hanging back, keeping close to the shop fronts where the amber glow of streetlamps fought against the downpour. Her watch pressed cold against her wrist beneath her coat sleeve. The worn leather band had moulded to her skin over the years, a familiar weight that anchored her during nights like this. Morris used to tell her she checked it too often. An old habit now. A ghost of a habit. Herrera crossed Shaftesbury Avenue without waiting for the lights. A black cab swerved, its horn blaring through the wet air. Quinn followed, dodging between a bus shelter and a food stall pulling its awning down against the rain. The smell of fried onions and wet asphalt mixed in her throat. She'd flagged Herrera in her notes three weeks ago. An off-the-books medic, her contacts said. Someone the clique called when things went sideways and hospitals weren't an option. The file she'd built was thin — a few blurry photos, an address in Lambeth, a name that had surfaced in two unrelated witness statements. But tonight, she'd watched him leave The Raven's Nest through the back exit, glancing over his shoulder twice before he turned south. The Raven's Nest. She knew the place. Green neon sign, old maps on the walls. She'd been inside once, six months back, playing the part of a tourist looking for a quiet drink. The barman had watched her the entire time with flat eyes that tracked her movements across the room. Herrera picked up speed. Soho bled into the edges of Covent Garden, then the streets grew quieter as he cut northeast. Quinn's lungs burned. She hadn't eaten since noon and the rain was turning her coat into dead weight. He ducked into an alley between two shuttered storefronts. Quinn counted to five and followed. The alley ended at a fire escape and a pile of soaked cardboard boxes. No Herrera. She scanned the walls, the ground, the rusted ladder above her head. A grate in the pavement, half-hidden by a dumpster, sat slightly ajar. Water pooled around its edges, draining into the gap beneath. She crouched. Listened. The rain hammered the metal above her, but beneath it — footsteps. Fading footsteps, heading down. Quinn gripped the grate and lifted. A rusted ladder descended into darkness. The air that rose from the shaft smelled of old metal and something else, something that reminded her of copper and church incense mixed together. Her stomach turned. She climbed down. The ladder ended on a narrow platform lit by a single emergency bulb that flickered in its cage. Tunnel walls stretched ahead, curved and tiled in a pattern she recognized. An old Tube station. Signs had been ripped from the walls, but the architecture was unmistakable — the arched ceiling, the tiled pilasters, the ghost of a roundel on the wall where paint had been scraped away. Herrera's footsteps echoed somewhere ahead. She followed the sound. The tunnel branched. To the left, darkness and the drip of water. To the right, a faint light, warm and shifting. She turned right and the passage opened into a wider platform, the old tracks still embedded in the ground, and beyond them — Quinn stopped. A market. An actual market, spread across the abandoned platform and spilling into the tunnel beyond. Stalls constructed from packing crates and old ticket booths lined the curved walls, draped in cloth that ranged from velvet to what looked like skin. Candles burned in jars, in skulls, in hollowed-out books. The light they cast was honey-coloured and restless, throwing shadows that moved wrong. People moved between the stalls. She couldn't call them all people. Some stood too tall, their proportions off in ways that made her eyes water when she tried to focus. Others crouched low, their shapes hidden beneath layers of fabric. A woman with scales along her jaw examined a row of glass bottles. A man with no visible eyes haggled over something wrapped in cloth. And Herrera. He stood at a stall near the far end, his back to her, his hand extended. The stall's owner — something with too many fingers and a voice like gravel in a blender — passed him a small leather case. Quinn pressed herself against the tiled wall. Her hand went to her hip, to the service weapon she carried. The metal of her holster was cold through the wet fabric. Three years ago, she'd stood in a doorway much like this one. Different location, different night. Morris had gone ahead of her into a building they'd been staking out. She'd heard him call out, then nothing. By the time she'd reached the room he'd entered, it was empty. No body. No blood. Just a smell like burning leaves and a symbol scorched into the floor that she'd photographed and shown to everyone she could think of. Nobody recognized it. Nobody wanted to talk about it. She'd spent three years telling herself there was an explanation that didn't involve the things she'd seen in her peripheral vision since she was a child. The shapes that vanished when she turned her head. The whispers in empty rooms. She'd built her career on logic, evidence, procedure. And now she stood in an abandoned Tube station watching a man buy something from a creature with seven fingers, and the logic was crumbling. A figure detached itself from the shadows near the entrance. It blocked her path back to the ladder. She couldn't make out its features beneath the hood it wore, but its height alone was enough to make her pulse hammer. "Token." The voice was neither male nor female. It vibrated in her chest. "What?" "Bone token. Entry requirement. You don't have one." Quinn kept her hand on her weapon. The figure didn't move. "I'm police. Detective Harlow Quinn, Metropolitan Police." She let the words hang in the air, testing whether they still carried weight in a place like this. The figure made a sound. Laughter, maybe, or something that served the same purpose. "We know what you are, Detective. The question is whether you know what you're walking into." Her eyes swept the market. Herrera had collected his case and was moving deeper into the crowd, heading toward a section of the platform she couldn't see from her position. If she lost him now, three months of work disappeared. Whatever the clique was involved in — the missing persons, the unexplained deaths, the cases that landed on her desk and went nowhere — this was where the threads connected. But the market stretched ahead of her, vast and incomprehensible. The stalls sold things she couldn't identify. Bottles of liquid that shifted colour when she looked at them. Bundles of dried herbs that moved on their own. A glass case containing what appeared to be a human heart, still beating. And the crowd. The crowd watched her. Every figure in that market had turned, subtle as a flock of birds, their attention fixed on the woman who smelled of rain and authority. Her radio crackled. She ignored it. Morris had gone into a place he didn't understand. He hadn't come out. The hooded figure tilted its head. Waiting. "I need to speak with the man who just entered. Tomás Herrera. He's a person of interest in an active investigation." "Herrera is known to us. He mends our wounded when no one else will. He has the token. He belongs." "I don't care if he belongs. I need to talk to him." "Then you need a token. Or you need permission. And you need to understand, Detective, that the things which protect this place do not answer to your badge." Quinn looked at the crowd. At the stalls. At the darkness beyond where Herrera had disappeared. Her career had taught her to read a room, to assess threat levels, to know when to push forward and when to call for backup. She had no backup here. Her phone showed no signal. Her radio spat static. The rain above was a distant memory, a sound from another world. Down here, the air tasted different. Older. It carried the weight of things she'd spent her life refusing to see. She released her weapon. Took a breath. "Then who do I talk to about getting permission?" The figure's hood shifted. Something that might have been a smile appeared in the dark beneath it. "That depends. How much are you willing to lose, Detective Quinn?" The market hummed around her. Somewhere in its depths, Herrera was meeting with the people she'd been hunting for months. The answers she needed were here. So was the thing that had taken Morris, she understood that now, the knowledge settling into her bones with the same certainty as the cold that seeped through her coat. She stepped forward, past the hooded figure, into the light of the Veil Market.
created_at"2026-07-07T20:53:35.562Z" 7/7/2026, 8:53:35 PM
model"aion-labs/aion-3.0-20260707"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency439
moderation_latency(null)
generation_time44073
tokens_prompt1140
tokens_completion2885
native_tokens_prompt992
native_tokens_completion2383
native_tokens_completion_images(null)
native_tokens_reasoning541
native_tokens_cached321
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)
usage0.01655175
router(null)
provider_responses
0
endpoint_id"8c8f827d-2bef-468a-8f9e-8e27b470de5e"
id"28cf9c899a014c87aa1885a4a0c8a43d"
is_byokfalse
latency438
model_permaslug"aion-labs/aion-3.0-20260707"
provider_name"AionLabs"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer(null)
request_id"req-1783457615-mEmCBM52FL2i8qF5ZshY"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1783457615-eyuKtZJzW9SEQ3kl2wZZ"
upstream_id"28cf9c899a014c87aa1885a4a0c8a43d"
total_cost0.01655175
cache_discount0.00072225
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
totalTags1
adverbTagCount0
adverbTags(empty)
dialogueSentences11
tagDensity0.091
leniency0.182
rawRatio0
effectiveRatio0
96.79% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1559
totalAiIsmAdverbs1
found
0
adverb"slightly"
count1
highlights
0"slightly"
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)
45.48% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1559
totalAiIsms17
found
0
word"familiar"
count1
1
word"weight"
count3
2
word"scanned"
count1
3
word"footsteps"
count3
4
word"stomach"
count1
5
word"flickered"
count1
6
word"echoed"
count1
7
word"constructed"
count1
8
word"velvet"
count1
9
word"pulse"
count1
10
word"vibrated"
count1
11
word"carried the weight"
count1
12
word"depths"
count1
highlights
0"familiar"
1"weight"
2"scanned"
3"footsteps"
4"stomach"
5"flickered"
6"echoed"
7"constructed"
8"velvet"
9"pulse"
10"vibrated"
11"carried the weight"
12"depths"
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
narrationSentences137
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount2
narrationSentences137
filterMatches
0"watch"
hedgeMatches
0"tried to"
1"appeared to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences147
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen32
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1567
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions7
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions40
wordCount1433
uniqueNames16
maxNameDensity0.7
worstName"Quinn"
maxWindowNameDensity1.5
worstWindowName"Quinn"
discoveredNames
Harlow1
Quinn10
Berwick1
Street1
Herrera10
Shaftesbury1
Avenue1
Lambeth1
Raven2
Nest2
Covent1
Garden1
Tube2
Morris4
Veil1
Market1
persons
0"Harlow"
1"Quinn"
2"Herrera"
3"Raven"
4"Morris"
5"Market"
places
0"Berwick"
1"Street"
2"Shaftesbury"
3"Avenue"
4"Lambeth"
5"Covent"
6"Garden"
globalScore1
windowScore1
94.44% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences90
glossingSentenceCount2
matches
0"as if guarding something beneath the fabric"
1"looked like skin"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords0.638
wordCount1567
matches
0"neither male nor"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences147
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs50
mean31.34
std22.32
cv0.712
sampleLengths
049
155
252
350
475
551
639
715
850
919
1040
113
1267
139
1444
152
1663
1765
1842
1930
2085
2148
2225
2340
241
2512
261
278
2811
2926
3014
3116
3270
3350
3432
356
3613
377
3821
3920
4012
4128
4255
4332
447
459
4617
4711
4856
4914
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences137
matches
0"been ripped"
1"been scraped"
2"was involved"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs247
matches
0"was turning"
1"was crumbling"
2"was meeting"
26.24% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount8
semicolonCount0
flaggedSentences6
totalSentences147
ratio0.041
matches
0"The file she'd built was thin — a few blurry photos, an address in Lambeth, a name that had surfaced in two unrelated witness statements."
1"The rain hammered the metal above her, but beneath it — footsteps."
2"Signs had been ripped from the walls, but the architecture was unmistakable — the arched ceiling, the tiled pilasters, the ghost of a roundel on the wall where paint had been scraped away."
3"She turned right and the passage opened into a wider platform, the old tracks still embedded in the ground, and beyond them —"
4"The stall's owner — something with too many fingers and a voice like gravel in a blender — passed him a small leather case."
5"Whatever the clique was involved in — the missing persons, the unexplained deaths, the cases that landed on her desk and went nowhere — this was where the threads connected."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1430
adjectiveStacks0
stackExamples(empty)
adverbCount27
adverbRatio0.01888111888111888
lyAdverbCount1
lyAdverbRatio0.0006993006993006993
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences147
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences147
mean10.66
std7.69
cv0.721
sampleLengths
024
15
220
325
46
52
622
711
822
910
104
115
129
1311
1418
1512
169
176
1813
1925
2022
213
224
238
2418
2518
264
2717
283
2915
309
316
3214
332
3412
3512
3610
372
381
3912
404
416
426
4325
443
453
4618
4712
484
4933
57.60% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats7
diversityRatio0.3741496598639456
totalSentences147
uniqueOpeners55
52.91% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences126
matches
0"Just a smell like burning"
1"Somewhere in its depths, Herrera"
ratio0.016
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount34
totalSentences126
matches
0"Her shoes slapped wet pavement."
1"He walked fast but didn't"
2"Her watch pressed cold against"
3"She'd flagged Herrera in her"
4"She knew the place."
5"She'd been inside once, six"
6"She hadn't eaten since noon"
7"He ducked into an alley"
8"She scanned the walls, the"
9"Her stomach turned."
10"She climbed down."
11"She followed the sound."
12"She turned right and the"
13"She couldn't call them all"
14"He stood at a stall"
15"Her hand went to her"
16"She'd heard him call out,"
17"She'd spent three years telling"
18"She'd built her career on"
19"It blocked her path back"
ratio0.27
43.33% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount105
totalSentences126
matches
0"The rain came down like"
1"Her shoes slapped wet pavement."
2"Tomás Herrera moved twenty metres"
3"He walked fast but didn't"
4"Quinn matched his pace, hanging"
5"Her watch pressed cold against"
6"The worn leather band had"
7"Morris used to tell her"
8"An old habit now."
9"A ghost of a habit."
10"Herrera crossed Shaftesbury Avenue without"
11"A black cab swerved, its"
12"Quinn followed, dodging between a"
13"The smell of fried onions"
14"She'd flagged Herrera in her"
15"An off-the-books medic, her contacts"
16"Someone the clique called when"
17"The file she'd built was"
18"The Raven's Nest."
19"She knew the place."
ratio0.833
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount4
totalSentences126
matches
0"To the left, darkness and"
1"To the right, a faint"
2"By the time she'd reached"
3"If she lost him now,"
ratio0.032
37.47% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences61
technicalSentenceCount9
matches
0"Tomás Herrera moved twenty metres ahead, his dark jacket slick with rain, one hand pressed to his chest as if guarding something beneath the fabric."
1"Quinn matched his pace, hanging back, keeping close to the shop fronts where the amber glow of streetlamps fought against the downpour."
2"The air that rose from the shaft smelled of old metal and something else, something that reminded her of copper and church incense mixed together."
3"The ladder ended on a narrow platform lit by a single emergency bulb that flickered in its cage."
4"The light they cast was honey-coloured and restless, throwing shadows that moved wrong."
5"She'd spent three years telling herself there was an explanation that didn't involve the things she'd seen in her peripheral vision since she was a child."
6"Whatever the clique was involved in — the missing persons, the unexplained deaths, the cases that landed on her desk and went nowhere — this was where the threa…"
7"Bottles of liquid that shifted colour when she looked at them."
8"So was the thing that had taken Morris, she understood that now, the knowledge settling into her bones with the same certainty as the cold that seeped through h…"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags1
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
88.4755%