Run: 2026-02-24-01KJ8X8HDFHAXE21WAPWZMRFJ0

Run Details

Model:
Aion 2.0
Duration:
1m 20s
Cost:
$0.004563
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 relentless, diagonal sheets, turning the Soho pavement into a black mirror of neon and sodium light. Detective Harlow Quinn’s breath came in sharp clouds, her boots slapping against the wet concrete with a rhythm that matched her pounding heart. Twenty yards ahead, a dark-clad figure darted around the corner onto Dean Street, a blur against the glittering curtain of water. She pushed harder, the muscles in her legs burning. Her worn leather watch strap chafed against her wrist beneath her sodden coat sleeve. Three years. Three years since a chase like this had ended with Morris’s empty chair in the incident room, with a case file stamped ‘UNSOLVED’ in black letters that felt like a physical blow. She shoved the memory down, locking it behind the professional focus that had kept her going for eighteen years. The figure—male, lean, wearing a dark hoodie—glanced back, his face a pale oval under the streetlamp before he vanished into an alleyway. Quinn skidded around the corner, her hand going to the hip where her service pistol sat in its holster. She didn’t draw it. Not yet. “Met Police! Stop!” Her command was swallowed by the drumming rain and the distant wail of a siren. The alley was a canyon of dripping fire escapes and overflowing bins. The suspect was already at the far end, heaving open a rusted metal gate. He slipped through. Quinn sprinted, rainwater streaming from the salt-and-pepper hair plastered to her scalp. She reached the gate, shoved it wider with a metallic screech. Beyond was a service yard, then another street. He was heading north, towards Tottenham Court Road. She followed, her mind mapping the grid. He was moving with purpose, not random panic. This was a route. He cut across the traffic on Charing Cross Road, drawing a symphony of angry horns. Quinn wove through the stalled cars, her sharp jaw set. She caught a better glimpse as he passed under a bus shelter light: olive skin, a flash of a scar on a bare forearm. The hood fell back for a second, revealing short, dark curly hair. A name clicked into place from a weeks-old surveillance log. Tomás Herrera. Former paramedic. Associate of the clique she’d been watching from the dim booths of The Raven’s Nest. The man who’d lost his license for playing doctor to things that shouldn’t exist. “Herrera!” she yelled. He faltered for a half-step, his head turning. Their eyes met across thirty feet of rain-slicked asphalt. His were wide, not with fear, but with a frantic urgency. He didn’t stop. He raised a hand, not in surrender, but as if to ward her off. Then he ran faster. The chase stretched into a blur of exhaustion. Through the theatre district, across the sprawl of Covent Garden, into the darker, quieter streets of Bloomsbury. Quinn’s lungs were raw. Her clothes were a second skin of cold water. But the gap was closing. Herrera was tiring, his strides becoming less sure. He ducked into the brick archway of a disused railway viaduct. Quinn followed, slowing to a jog, her hand now resting on the butt of her pistol. The archway tunnel was long, dark, and smelled of damp earth and urine. A single bare bulb flickered at the far end. Herrera was there, fumbling at a heavy, padlocked chain on a metal door set into the brickwork. “It’s over, Herrera. Don’t make it worse.” He spun, his back against the door. His chest heaved. The Saint Christopher medallion around his neck glinted in the poor light. “You don’t understand. You can’t be here.” “I understand you’re running. I understand you’re involved with people who break the law. Talk to me. Now.” “The law?” A harsh, breathless laugh escaped him. “Your laws don’t matter down here. This is a bad idea, Detective. Go back to your warm office.” “Down where?” Instead of answering, he yanked something from his pocket—a small, pale object. He pressed it against the center of the metal door. There was a sound like a heavy lock disengaging, deep within the wall. The door swung inward, revealing not a room, but a descending staircase, lit by a faint, sourceless greenish glow. A wave of air washed out—cold, carrying the scent of ozone, exotic spices, and something metallic, like old blood. Herrera gave her one last, pitying look. “Forget you saw me. Forget this door. For your own sake.” Then he plunged down the stairs, disappearing into the glow. Quinn approached the doorway. The stairs were narrow, carved from old, worn stone, leading down into the earth. The green light pulsed faintly. From the depths, she heard a murmur—the distant, chaotic buzz of a crowd, the clink of glass, a low, melodic chant that raised the hairs on her arms. The Veil Market. The name surfaced from a fragment of an interview, a whisper from a terrified informant she’d discounted as delusional. A black market that moved. A place for things that belonged in nightmares. Her radio crackled on her shoulder, a burst of static. She ignored it. Every instinct honed by her years of service screamed at her to call for backup, to cordon off the area, to follow procedure. Procedure had filled out Morris’s death certificate with a lie. Procedure had closed the case while the truth festered in the dark. She remembered the look in Herrera’s eyes. Not guilt. Warning. The rain dripped from the archway onto her neck, a cold trickle. Down there was the unknown. The unexplained. The thing that had taken her partner and left no trace. Her hand tightened on the doorframe. The worn leather of her watch strap dug into her skin. She could turn around. Walk back into the rain, the familiar misery of the city, the cold case files. She could be smart. Quinn took her first step onto the top stair.
created_at"2026-02-24T22:45:33.751Z" 2/24/2026, 10:45:33 PM
model"aion-labs/aion-2.0-20260223"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2134
moderation_latency(null)
generation_time79531
tokens_prompt1140
tokens_completion2678
native_tokens_prompt1106
native_tokens_completion2299
native_tokens_completion_images(null)
native_tokens_reasoning1183
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"
usage0.0045632
router(null)
provider_responses
0
endpoint_id"1e93b0bb-eb0f-49bc-8fda-947105413b86"
id"2a34b66f-3d88-460a-905e-aa549da8afdc"
is_byokfalse
latency186
model_permaslug"aion-labs/aion-2.0-20260223"
provider_name"AionLabs"
status200
api_type"completions"
id"gen-1771973133-EQRAEi1LYX7LuO4yhVOZ"
upstream_id"2a34b66f-3d88-460a-905e-aa549da8afdc"
total_cost0.0045632
cache_discount(null)
upstream_inference_cost0
provider_name"AionLabs"

Evaluation details

Result Evaluator Details Meta Data
0.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags4
adverbTagCount1
adverbTags
0"Then he plunged [Then]"
dialogueSentences9
tagDensity0.444
leniency0.889
rawRatio0.25
effectiveRatio0.222
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount985
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)
54.31% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount985
totalAiIsms9
found
0
word"pounding"
count1
1
word"streaming"
count1
2
word"symphony"
count1
3
word"flickered"
count1
4
word"pulsed"
count1
5
word"depths"
count1
6
word"chaotic"
count1
7
word"whisper"
count1
8
word"familiar"
count1
highlights
0"pounding"
1"streaming"
2"symphony"
3"flickered"
4"pulsed"
5"depths"
6"chaotic"
7"whisper"
8"familiar"
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
narrationSentences87
matches
0"t with fear"
93.60% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount3
hedgeCount0
narrationSentences87
filterMatches
0"watch"
1"look"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences93
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen32
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords981
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions1
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions34
wordCount902
uniqueNames21
maxNameDensity0.89
worstName"Quinn"
maxWindowNameDensity1.5
worstWindowName"Quinn"
discoveredNames
Soho1
Harlow1
Quinn8
Dean1
Street1
Morris2
Tottenham1
Court1
Road2
Charing1
Cross1
Herrera5
Raven1
Nest1
Covent1
Garden1
Bloomsbury1
Saint1
Christopher1
Veil1
Market1
persons
0"Harlow"
1"Quinn"
2"Morris"
3"Herrera"
4"Raven"
5"Saint"
6"Christopher"
places
0"Soho"
1"Dean"
2"Street"
3"Tottenham"
4"Court"
5"Road"
6"Charing"
7"Cross"
8"Covent"
9"Garden"
globalScore1
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences63
glossingSentenceCount0
matches(empty)
0.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches3
per1kWords3.058
wordCount981
matches
0"not with fear, but with a frantic urgency"
1"not in surrender, but as if to ward her off"
2"not a room, but a descending staircase, lit by a faint, sourceless greenish"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences93
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs26
mean37.73
std22.73
cv0.602
sampleLengths
064
176
247
33
444
558
661
743
83
949
1051
1166
127
1329
1418
1526
162
1773
1828
1951
2035
2158
2210
2347
2423
259
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences87
matches
0"was swallowed"
97.44% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs130
matches
0"was heading"
1"was tiring"
19.97% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount5
semicolonCount0
flaggedSentences4
totalSentences93
ratio0.043
matches
0"The figure—male, lean, wearing a dark hoodie—glanced back, his face a pale oval under the streetlamp before he vanished into an alleyway."
1"Instead of answering, he yanked something from his pocket—a small, pale object."
2"A wave of air washed out—cold, carrying the scent of ozone, exotic spices, and something metallic, like old blood."
3"From the depths, she heard a murmur—the distant, chaotic buzz of a crowd, the clink of glass, a low, melodic chant that raised the hairs on her arms."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount164
adjectiveStacks0
stackExamples(empty)
adverbCount1
adverbRatio0.006097560975609756
lyAdverbCount0
lyAdverbRatio0
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences93
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences93
mean10.55
std6.58
cv0.624
sampleLengths
020
123
221
39
414
52
632
719
822
919
104
112
123
1315
1412
1514
163
1712
1811
198
208
217
228
234
2415
2510
2624
2712
2810
292
302
3115
3214
333
348
359
3611
373
3814
394
408
4117
424
439
445
458
4611
4716
4813
499
54.12% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats8
diversityRatio0.3763440860215054
totalSentences93
uniqueOpeners35
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences79
matches
0"Then he ran faster."
1"Instead of answering, he yanked"
2"Then he plunged down the"
ratio0.038
78.23% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount28
totalSentences79
matches
0"She pushed harder, the muscles"
1"Her worn leather watch strap"
2"She shoved the memory down,"
3"She didn’t draw it."
4"Her command was swallowed by"
5"He slipped through."
6"She reached the gate, shoved"
7"He was heading north, towards"
8"She followed, her mind mapping"
9"He was moving with purpose,"
10"He cut across the traffic"
11"She caught a better glimpse"
12"He faltered for a half-step,"
13"Their eyes met across thirty"
14"His were wide, not with"
15"He didn’t stop."
16"He raised a hand, not"
17"Her clothes were a second"
18"He ducked into the brick"
19"He spun, his back against"
ratio0.354
29.62% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount68
totalSentences79
matches
0"The rain fell in relentless,"
1"Detective Harlow Quinn’s breath came"
2"She pushed harder, the muscles"
3"Her worn leather watch strap"
4"She shoved the memory down,"
5"The figure—male, lean, wearing a"
6"Quinn skidded around the corner,"
7"She didn’t draw it."
8"Her command was swallowed by"
9"The alley was a canyon"
10"The suspect was already at"
11"He slipped through."
12"Quinn sprinted, rainwater streaming from"
13"She reached the gate, shoved"
14"He was heading north, towards"
15"She followed, her mind mapping"
16"He was moving with purpose,"
17"This was a route."
18"He cut across the traffic"
19"Quinn wove through the stalled"
ratio0.861
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences79
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences44
technicalSentenceCount2
matches
0"Detective Harlow Quinn’s breath came in sharp clouds, her boots slapping against the wet concrete with a rhythm that matched her pounding heart."
1"From the depths, she heard a murmur—the distant, chaotic buzz of a crowd, the clink of glass, a low, melodic chant that raised the hairs on her arms."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags4
uselessAdditionCount0
matches(empty)
38.89% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags1
fancyCount1
fancyTags
0"she yelled (yell)"
dialogueSentences9
tagDensity0.111
leniency0.222
rawRatio1
effectiveRatio0.222
78.8725%