Run: 2026-07-07-01KWZ5HBQM5VEVDDRM78PKFDT4

Run Details

Model:
Aion 3.0
Duration:
37.1s
Cost:
$0.014968
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
Rain hammered the pavement in sheets, turning Soho's neon into bleeding watercolors across wet asphalt. Detective Harlow Quinn kept her pace steady behind the figure thirty meters ahead, her worn leather watch face slick with water, its second hand ticking through the downpour. Eighteen years on the force had taught her when to sprint and when to hold back. Tonight called for patience. The man she followed moved with purpose. Dark curly hair plastered to his skull, jacket collar turned up, he navigated the narrow streets with the confidence of someone who knew exactly where he was going. She had spotted him outside The Raven's Nest, that bar with the green neon sign she'd been surveilling for three weeks. He'd emerged from a side door she hadn't known existed, checked his surroundings once, and set off southward into the rain. Quinn had memorized his face from the photographs. Tomás Herrera. Twenty-nine, olive-skinned, a scar along his left forearm she'd seen in beach photos pulled from social media. Former paramedic, lost his NHS license under circumstances that remained murky in the file. Now he ran medical care for the people she was building a case against. He turned left onto Old Compton Street. She matched his pace, staying close enough to keep visual contact but far enough to avoid detection. A group of drunk tourists spilled from a pub and she weaved through them, never losing sight of Herrera's dark jacket. The Saint Christopher medallion around his neck caught a streetlight's glow for a moment before the rain swallowed it. "You're leading me somewhere specific," she muttered to herself, wiping water from her eyes. He wasn't wandering. Wasn't behaving like a man caught in the rain seeking shelter. Each turn was deliberate, each glance over his shoulder timed and casual. He suspected he was being followed. Or he was cautious by nature. They pushed north through Soho's maze, past restaurants emptying their bins and taxis hunting fares. The rain intensified, hammering against awnings and turning gutters into rivers. Quinn's boots squelched with each step, but she kept her breathing measured, her gait controlled. Herrera crossed Charing Cross Road and cut through the crowds waiting for night buses. She followed, dodging an umbrella swung carelessly by a woman on her phone. The gap between them widened to forty meters, then fifty. She quickened her stride. The streets grew quieter as they moved away from Soho's glow. Herrera turned down a service alley behind a row of shops, and Quinn hesitated at the corner. An ambush would be stupid, but Herrera had connections to people who operated outside the law. She checked her watch. 11:47 PM. Backup was a phone call away, but a phone call would end this pursuit. She entered the alley. It dead-ended at a chain-link fence. Herrera was already over it, dropping to the other side with practiced ease. Quinn climbed after him, her jacket catching on a loose wire, tearing at the shoulder. She hit the ground on the other side and kept moving. They emerged onto a main road where traffic had thinned to nothing. North of Soho now, heading toward Camden. Herrera hailed a taxi that was passing and climbed in. Quinn sprinted. The taxi pulled away from the curb. She memorized the license plate, but the vehicle merged into sparse traffic and she lost it within two blocks. "Damn it." She stood on the pavement, rain streaming down her face, watching taillights blur and disappear. Three weeks of surveillance. Three weeks of building a case against a network she still didn't fully understand. And now her best lead was driving away into the London night. Then she saw it. The taxi had stopped three blocks ahead, outside a building she recognized from the file. An abandoned Tube station, one of the many that dotted London's underground network. Herrera climbed out, paid the driver, and disappeared through a gate that should have been locked. Quinn moved fast. Her training kept her silent as she approached the gate. A padlock lay in the mud, freshly cut. Beyond it, concrete stairs descended into darkness. The air rising from below carried a smell she couldn't place. Something metallic, something old. She pulled out her phone and opened the camera. Photographed the cut padlock, the gate, the stairs. Evidence that might matter later, if later ever came. Quinn descended. The stairs spiraled down, the walls slick with moisture and covered in graffiti that had been painted over multiple times. Her footsteps echoed despite her efforts to move quietly. Below, she heard a door open and close. Then silence. She reached a landing where the stairs ended at a heavy metal door. It stood slightly ajar. Beyond it, she heard voices. Many voices. Conversation, laughter, the clink of glasses. The sound of a crowd gathered in a place that shouldn't exist. Quinn pushed the door open with her fingertips. The tunnel stretched before her, wider than she expected. Originally a platform, now transformed into something else entirely. Stalls lined both sides, their tables draped in dark cloth and lit by candles that burned with unusual colors. Blues and purples and greens that no normal flame should produce. People moved between the stalls, examining wares she couldn't identify from this distance. The Veil Market. The name surfaced from a case file she'd read two months ago, dismissed as urban legend. An underground supernatural black market that moved locations every full moon. She'd laughed when she first read the report. She wasn't laughing now. Quinn stepped back behind the door and pressed her back against the damp wall. Her heart hammered against her ribs. In all her years on the force, she'd seen things that defied explanation. The case that killed her partner, DS Morris, three years ago. The way he'd died, the impossible wounds, the way the scene didn't make forensic sense no matter how many times they reexamined it. She'd buried those questions because answering them meant accepting something she wasn't ready to accept. She unbuttoned her jacket and checked her holster. Her service weapon sat where it always did, reassuring weight against her hip. She had no idea what she was walking into. No backup. No knowledge of what the people in that market were capable of. Herrera was down there somewhere. Moving through the crowd, meeting whoever he'd come to meet. Whatever transaction he was making, whatever information he was exchanging, it was happening right now. Quinn looked at her watch. 11:53 PM. She could call for backup. Wait for uniforms to arrive. But by then, Herrera would be gone. The market would close. Whatever evidence existed in that tunnel would vanish until the next full moon. She looked back through the gap in the door. A woman at the nearest stall examined a glass vial that seemed to glow from within. The vendor, a man with burn scars covering half his face, watched her with eyes that caught the candlelight strangely. Quinn's jaw tightened. Three years since Morris died. Three years of questions that no one could answer. Three years of feeling like she was missing something fundamental about the world, something everyone else could see but her. She could turn around. Go back up the stairs. Report what she'd found and let someone else handle it. That would be the smart play. The safe play. But safe hadn't solved Morris's case. Safe hadn't given her answers. Safe had left her standing at his graveside with nothing but hollow condolences and a file stamped unsolved. The market hummed with activity ahead of her. Somewhere in that crowd, Herrera was conducting business that connected to the network she'd been investigating. And somewhere in that network were answers she'd been seeking for three years. Quinn pushed off the wall. Straightened her jacket. Touched the worn leather of her watch, a habit she'd developed when making decisions that scared her. She stepped through the door and into the tunnel. The candle flames flickered as she passed them, their colors shifting in ways that made her eyes ache. The crowd ahead moved like a living organism, bodies flowing between stalls, voices murmuring in languages she didn't recognize. She kept her hand near her weapon and walked forward, leaving behind the world she understood and entering one she didn't.
created_at"2026-07-07T20:50:27.204Z" 7/7/2026, 8:50:27 PM
model"aion-labs/aion-3.0-20260707"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency735
moderation_latency(null)
generation_time36901
tokens_prompt1140
tokens_completion2630
native_tokens_prompt992
native_tokens_completion2119
native_tokens_completion_images(null)
native_tokens_reasoning488
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)
usage0.01496775
router(null)
provider_responses
0
endpoint_id"8c8f827d-2bef-468a-8f9e-8e27b470de5e"
id"93b04174d8854c7d9023ceaa9da9945c"
is_byokfalse
latency735
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-1783457427-TIbQihvdGtKUThJfMa5W"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1783457427-dxnn2dP7rp3FXmY8sb5c"
upstream_id"93b04174d8854c7d9023ceaa9da9945c"
total_cost0.01496775
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
totalTags2
adverbTagCount0
adverbTags(empty)
dialogueSentences2
tagDensity1
leniency1
rawRatio0
effectiveRatio0
96.39% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1386
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)
63.92% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1386
totalAiIsms10
found
0
word"navigated"
count1
1
word"measured"
count1
2
word"quickened"
count1
3
word"practiced ease"
count1
4
word"streaming"
count1
5
word"footsteps"
count1
6
word"echoed"
count1
7
word"silence"
count1
8
word"weight"
count1
9
word"flickered"
count1
highlights
0"navigated"
1"measured"
2"quickened"
3"practiced ease"
4"streaming"
5"footsteps"
6"echoed"
7"silence"
8"weight"
9"flickered"
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
narrationSentences132
matches(empty)
88.74% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount4
hedgeCount1
narrationSentences132
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)
analyzedSentences132
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen28
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1386
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions5
unquotedAttributions0
matches(empty)
83.33% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions53
wordCount1379
uniqueNames21
maxNameDensity0.94
worstName"Quinn"
maxWindowNameDensity2.5
worstWindowName"Herrera"
discoveredNames
Soho4
Harlow1
Quinn13
Raven1
Nest1
Herrera11
Old1
Compton1
Street1
Saint1
Christopher1
Charing1
Cross1
Road1
Camden1
Three5
London2
Tube1
Veil1
Market1
Morris3
persons
0"Harlow"
1"Quinn"
2"Herrera"
3"Saint"
4"Christopher"
5"Market"
6"Morris"
places
0"Soho"
1"Raven"
2"Old"
3"Compton"
4"Street"
5"Charing"
6"Cross"
7"Road"
8"Camden"
9"London"
globalScore1
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences98
glossingSentenceCount1
matches
0"vial that seemed to glow from within"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1386
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences132
matches(empty)
88.41% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs35
mean39.6
std18.19
cv0.459
sampleLengths
063
177
255
364
414
538
641
741
864
94
1045
1129
1228
1347
1448
1543
1626
172
1839
1942
208
2161
2242
2382
2444
2530
2641
2745
2837
2928
3029
3137
3225
3346
3421
97.29% Passive voice overuse
Target: ≤2% passive sentences
passiveCount3
totalSentences132
matches
0"being followed"
1"been locked"
2"been painted"
0.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount12
totalVerbs254
matches
0"was going"
1"was building"
2"wasn't wandering"
3"Wasn't behaving"
4"was passing"
5"was driving"
6"wasn't laughing"
7"was walking"
8"was making"
9"was exchanging"
10"was happening"
11"was conducting"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences132
ratio0
matches(empty)
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1383
adjectiveStacks1
stackExamples
0"underground supernatural black market"
adverbCount35
adverbRatio0.025307302964569775
lyAdverbCount10
lyAdverbRatio0.0072306579898770785
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences132
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences132
mean10.5
std5.85
cv0.557
sampleLengths
015
128
216
34
47
528
621
721
88
92
1017
1114
1214
137
1417
1521
1619
1714
183
1911
2012
216
226
2315
2411
2515
2614
2713
2810
294
3011
3117
3216
334
342
3514
364
376
3813
3915
4011
4112
427
4310
442
457
4619
4717
484
4914
60.61% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats10
diversityRatio0.4090909090909091
totalSentences132
uniqueOpeners54
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount4
totalSentences124
matches
0"Dark curly hair plastered to"
1"Then she saw it."
2"Originally a platform, now transformed"
3"Somewhere in that crowd, Herrera"
ratio0.032
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount34
totalSentences124
matches
0"She had spotted him outside"
1"He'd emerged from a side"
2"He turned left onto Old"
3"She matched his pace, staying"
4"she muttered to herself, wiping"
5"He wasn't wandering."
6"He suspected he was being"
7"They pushed north through Soho's"
8"She followed, dodging an umbrella"
9"She quickened her stride."
10"She checked her watch."
11"She entered the alley."
12"It dead-ended at a chain-link"
13"She hit the ground on"
14"They emerged onto a main"
15"She memorized the license plate,"
16"She stood on the pavement,"
17"Her training kept her silent"
18"She pulled out her phone"
19"Her footsteps echoed despite her"
ratio0.274
100.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount89
totalSentences124
matches
0"Detective Harlow Quinn kept her"
1"Tonight called for patience."
2"The man she followed moved"
3"She had spotted him outside"
4"He'd emerged from a side"
5"Quinn had memorized his face"
6"He turned left onto Old"
7"She matched his pace, staying"
8"A group of drunk tourists"
9"The Saint Christopher medallion around"
10"she muttered to herself, wiping"
11"He wasn't wandering."
12"Each turn was deliberate, each"
13"He suspected he was being"
14"They pushed north through Soho's"
15"The rain intensified, hammering against"
16"Quinn's boots squelched with each"
17"Herrera crossed Charing Cross Road"
18"She followed, dodging an umbrella"
19"The gap between them widened"
ratio0.718
40.32% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences124
matches
0"Now he ran medical care"
ratio0.008
23.81% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences66
technicalSentenceCount11
matches
0"Dark curly hair plastered to his skull, jacket collar turned up, he navigated the narrow streets with the confidence of someone who knew exactly where he was go…"
1"Former paramedic, lost his NHS license under circumstances that remained murky in the file."
2"Quinn climbed after him, her jacket catching on a loose wire, tearing at the shoulder."
3"An abandoned Tube station, one of the many that dotted London's underground network."
4"An underground supernatural black market that moved locations every full moon."
5"In all her years on the force, she'd seen things that defied explanation."
6"The case that killed her partner, DS Morris, three years ago."
7"The vendor, a man with burn scars covering half his face, watched her with eyes that caught the candlelight strangely."
8"Somewhere in that crowd, Herrera was conducting business that connected to the network she'd been investigating."
9"Touched the worn leather of her watch, a habit she'd developed when making decisions that scared her."
10"The candle flames flickered as she passed them, their colors shifting in ways that made her eyes ache."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags2
uselessAdditionCount0
matches(empty)
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags1
fancyCount1
fancyTags
0"she muttered (mutter)"
dialogueSentences2
tagDensity0.5
leniency1
rawRatio1
effectiveRatio1
84.5609%