Run: 2026-02-24-01KJ8V9S0CWW9Q4PTPAGPXG2RV

Run Details

Model:
Aion 2.0
Duration:
1m 3s
Cost:
$0.004950
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 a relentless, icy curtain, turning the neon signs of Soho into smeared watercolor streaks. Detective Harlow Quinn shifted her weight against the damp brick wall, the collar of her trench coat turned up against the wet. Across the street, the distinctive green neon sign of The Raven’s Nest buzzed and flickered, casting a sickly glow on the wet pavement. She’d been here for two hours, watching the door. Her left wrist ached where the worn leather of her watch strap dug into her skin. Eighteen years on the force, the last three spent chasing ghosts since Morris vanished. The memory was a cold stone in her gut. She focused on the bar’s entrance. The door opened, spilling a wedge of amber light and the low murmur of jazz into the rain. A figure stepped out, a man in a long, dark coat, the hood pulled up against the weather. He paused, glanced left and right with a quick, furtive movement that set Harlow’s instincts humming. Military precision had been drilled into her; she recognized the posture of someone who didn’t want to be seen. He moved off down the street, footsteps quick and light on the slick cobbles. Harlow pushed off the wall and followed, keeping to the shadows, her own movements economical and silent. The rain masked the sound of her pursuit. He led her on a winding route through back alleys, past overflowing bins and the occasional huddled form in a doorway. The smell of wet garbage and old beer hung in the air. He never looked back, but his pace was urgent, purposeful. He was heading north, towards Camden. Harlow’s mind raced. This was it—a direct link from the Nest to something else. Morris had been investigating whispers of a hidden network, a market for things that shouldn’t exist. He’d called it ‘the Veil’ in his last, garbled message. Then he was gone, his body found in the Thames with no marks, no cause the coroner could name. The suspect ducked into a narrow passage between two condemned buildings. Harlow sped up, her shoes slipping on the greasy pavement. She rounded the corner and saw him fifty yards ahead, disappearing down a set of concrete stairs that led to a boarded-up Tube station entrance. The familiar roundel was still visible, though rusted and graffitied. ‘Camden Town’ it read, but this entrance had been sealed for years. She reached the top of the stairs and peered down. The metal gate that should have been chained shut stood ajar. A faint, phosphorescent glow emanated from the darkness below. The suspect was gone. Harlow descended, each step echoing in the confined space. The rain lessened to a drip-drip from the ceiling. At the bottom, the gate was secured by a heavy padlock, but it hung open. Next to it, set into the grimy wall, was a small, tarnished brass plate with a single, shallow indentation shaped like a slender bone. A token slot. She’d heard the rumors. Entry required a bone token. The market moved with the moon. This was the place. A sound from the tunnel beyond the gate—a scrape of foot on gravel. Harlow froze, her hand going to the service pistol holstered under her arm. She didn’t draw it. The rules changed down here. Morris had learned that the hard way. She could turn back. Call it in, get a team, come back with a warrant for a place that officially didn’t exist. The rational choice. The procedure. Procedure hadn’t found Morris’s killer. Procedure had closed the case as ‘death by misadventure’ and moved on. Her fingers brushed the cool metal of her watch. Morris had given her a hard time about that old thing. *‘Quinn, you need a digital. One that tells the time in Dubai.’* She’d told him to piss off. Now the worn leather was all she had left of their partnership. Another sound, closer this time. A low, guttural whisper that didn’t sound human. The hair on the back of her neck stood up. She looked at the gate, at the dark maw of the tunnel. The suspect was in there. Answers were in there. Maybe the thing that took Morris was in there. Harlow took a deep breath, the air cold and tasting of ozone and damp earth. She reached into her coat pocket and pulled out her phone. No signal, of course. She typed a quick text to her sergeant, knowing it wouldn’t send until she surfaced. *‘At abandoned Camden Tube entrance. Pursuing suspect into suspected Veil Market. Location unstable.’* She hit send, shoved the phone back into her pocket. Her heart hammered against her ribs. This was the decision point. Cross the threshold into a world her training didn’t cover, alone and unprepared. A memory surfaced, unbidden. Morris’s face, pale under the fluorescent lights of the morgue. His eyes had been open, staring at nothing. The pathologist had found traces of a substance in his blood she couldn’t identify. ‘Uncatalogued particulate matter,’ the report said. Like fairy dust, Harlow had thought bitterly. She stepped through the gate. The tunnel beyond was wider than she expected, the walls curved and lined with cracked Victorian tiles. The phosphorescent glow came from clusters of bioluminescent fungi growing in patches, casting everything in an eerie blue-green light. The air grew warmer, thick with the scent of incense, ozone, and something metallic. The tunnel opened into a vast, cavernous space—the abandoned station platform. But it was transformed. Stalls made of scrap wood and moth-eaten velvet lined the walls, their wares glowing, whispering, shifting in the strange light. Figures moved through the shadows, some hunched and cloaked, others tall and impossibly slender. The murmur of conversation was a low, alien hum. Harlow stood at the edge of the platform, her sharp jaw set, her brown eyes scanning the scene. The suspect was nowhere in sight. She was in.
created_at"2026-02-24T22:11:17.142Z" 2/24/2026, 10:11:17 PM
model"aion-labs/aion-2.0-20260223"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2527
moderation_latency(null)
generation_time62728
tokens_prompt1140
tokens_completion2981
native_tokens_prompt1106
native_tokens_completion2541
native_tokens_completion_images(null)
native_tokens_reasoning1488
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"
usage0.0049504
router(null)
provider_responses
0
endpoint_id"1e93b0bb-eb0f-49bc-8fda-947105413b86"
id"72babbf1-8b27-4679-b189-210cffc1e1f9"
is_byokfalse
latency123
model_permaslug"aion-labs/aion-2.0-20260223"
provider_name"AionLabs"
status200
api_type"completions"
id"gen-1771971077-Znwcy9pcbRqlg2vPi6yX"
upstream_id"72babbf1-8b27-4679-b189-210cffc1e1f9"
total_cost0.0049504
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)
dialogueSentences0
tagDensity1
leniency1
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount989
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)
49.44% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount989
totalAiIsms10
found
0
word"weight"
count1
1
word"flickered"
count1
2
word"footsteps"
count1
3
word"raced"
count1
4
word"familiar"
count1
5
word"echoing"
count1
6
word"whisper"
count1
7
word"maw"
count1
8
word"velvet"
count1
9
word"scanning"
count1
highlights
0"weight"
1"flickered"
2"footsteps"
3"raced"
4"familiar"
5"echoing"
6"whisper"
7"maw"
8"velvet"
9"scanning"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"hung in the air"
count1
highlights
0"hung in the air"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences90
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount2
hedgeCount0
narrationSentences90
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences94
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen26
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans2
markdownWords25
totalWords986
ratio0.025
matches
0"‘Quinn, you need a digital. One that tells the time in Dubai.’"
1"‘At abandoned Camden Tube entrance. Pursuing suspect into suspected Veil Market. Location unstable.’"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions4
unquotedAttributions0
matches(empty)
96.64% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions28
wordCount937
uniqueNames12
maxNameDensity1.07
worstName"Harlow"
maxWindowNameDensity2
worstWindowName"Harlow"
discoveredNames
Soho1
Harlow10
Quinn1
Raven1
Nest2
Morris7
Camden1
Thames1
Tube1
Veil1
Market1
Victorian1
persons
0"Harlow"
1"Quinn"
2"Raven"
3"Morris"
4"Market"
places
0"Soho"
1"Camden"
2"Thames"
globalScore0.966
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences67
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount986
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences94
matches
0"learned that the"
73.83% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs23
mean42.87
std17.51
cv0.408
sampleLengths
063
154
271
339
449
559
668
734
860
919
1042
1127
1217
1350
1423
1530
1658
1734
1849
195
2050
2158
2227
77.97% Passive voice overuse
Target: ≤2% passive sentences
passiveCount7
totalSentences90
matches
0"been drilled"
1"was gone"
2"been chained"
3"was gone"
4"was secured"
5"been open"
6"was transformed"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount1
totalVerbs150
matches
0"was heading"
21.28% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount3
semicolonCount1
flaggedSentences4
totalSentences94
ratio0.043
matches
0"Military precision had been drilled into her; she recognized the posture of someone who didn’t want to be seen."
1"This was it—a direct link from the Nest to something else."
2"A sound from the tunnel beyond the gate—a scrape of foot on gravel."
3"The tunnel opened into a vast, cavernous space—the abandoned station platform."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount310
adjectiveStacks0
stackExamples(empty)
adverbCount0
adverbRatio0
lyAdverbCount1
lyAdverbRatio0.0032258064516129032
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences94
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences94
mean10.49
std5.59
cv0.533
sampleLengths
018
122
223
39
416
514
69
76
818
918
1016
1119
1214
1317
148
1521
1612
1710
186
193
2011
2116
2210
2319
2411
2510
2625
2710
2812
2910
3011
319
324
339
349
3515
3624
373
384
395
406
414
4213
4313
444
455
467
474
4818
493
55.67% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats6
diversityRatio0.3723404255319149
totalSentences94
uniqueOpeners35
75.76% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences88
matches
0"Then he was gone, his"
1"Maybe the thing that took"
ratio0.023
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount23
totalSentences88
matches
0"She’d been here for two"
1"Her left wrist ached where"
2"She focused on the bar’s"
3"He paused, glanced left and"
4"He moved off down the"
5"He led her on a"
6"He never looked back, but"
7"He was heading north, towards"
8"He’d called it"
9"She rounded the corner and"
10"She reached the top of"
11"She’d heard the rumors."
12"She didn’t draw it."
13"She could turn back."
14"Her fingers brushed the cool"
15"She looked at the gate,"
16"She reached into her coat"
17"She typed a quick text"
18"She hit send, shoved the"
19"Her heart hammered against her"
ratio0.261
39.55% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount74
totalSentences88
matches
0"The rain fell in a"
1"Detective Harlow Quinn shifted her"
2"She’d been here for two"
3"Her left wrist ached where"
4"The memory was a cold"
5"She focused on the bar’s"
6"The door opened, spilling a"
7"A figure stepped out, a"
8"He paused, glanced left and"
9"Military precision had been drilled"
10"He moved off down the"
11"Harlow pushed off the wall"
12"The rain masked the sound"
13"He led her on a"
14"The smell of wet garbage"
15"He never looked back, but"
16"He was heading north, towards"
17"Harlow’s mind raced."
18"This was it—a direct link"
19"Morris had been investigating whispers"
ratio0.841
56.82% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences88
matches
0"Now the worn leather was"
ratio0.011
97.26% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences47
technicalSentenceCount3
matches
0"Morris had been investigating whispers of a hidden network, a market for things that shouldn’t exist."
1"She rounded the corner and saw him fifty yards ahead, disappearing down a set of concrete stairs that led to a boarded-up Tube station entrance."
2"Stalls made of scrap wood and moth-eaten velvet lined the walls, their wares glowing, whispering, shifting in the strange light."
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
88.1408%