Run: 2026-07-07-01KWZ5RR9QA16RADXNP7CTX83J

Run Details

Duration:
37.7s
Cost:
$0.003091
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 London's cobblestones, turning the streets into rivers of reflected amber light. Detective Harlow Quinn's boots slapped wet pavement as she cleared a stack of cardboard boxes, her lungs burning with the familiar taste of a chase gone too long. The suspect was fast. Too fast. Quinn caught a glimpse of him—black coat, pale skin, no discernible features in the downpour—as he vaulted a railing and disappeared into the maw of an alley near Mornington Crescent. She followed without hesitation, her right hand pressed against the SIG Sauer riding her hip. "Stop! Met Police!" The words dissolved in the rain. The alley opened into a courtyard choked with dumpsters and dead potted plants. Quinn scanned left, right. A metal grate rattled somewhere beneath her feet. She ran toward the sound. A maintenance hatch lay torn from its hinges in the corner of the yard, rainwater cascading into darkness below. Quinn knelt, shining her torch into the hole. Iron rungs descended into black water. The suspect's footprints vanished into the murk. She should call this in. Wait for backup. She pulled out her phone. No signal. Dead zone. Quinn holstered her weapon, gripped the rungs, and descended. The ladder dropped her into a Victorian sewer tunnel, the brickwork slick with moisture and age. The smell hit her—rank water, rot, copper. She stood still, listening. Dripping water echoed off curved walls. Somewhere ahead, footsteps splashed. She moved. The tunnel forked three ways. Quinn chose the middle path, relying on instinct honed over eighteen years. The ceiling lowered. The walls narrowed. She pressed forward until the sewer opened into something else entirely. An abandoned Tube station. The old Northern Line platform sprawled before her, tiled walls daubed with graffiti, benches rusted into skeletons. Fluorescent lights flickered overhead—impossible, since the station had been decommissioned in the seventies. Quinn's hand drifted back to her weapon. Voices. She killed her torch and pressed herself against a pillar. The voices came from beyond the platform, echoing off curved ceilings. Low murmurs in a language she didn't recognize. Guttural. Old. She crept forward. Suspects didn't lead detectives into abandoned Tube stations by accident. This was either an ambush or a destination. Either way, Quinn was out of her depth and she knew it. But she also knew the suspect held answers. Answers about the clique. About what killed Morris. Morris had been chasing the same people. The same shadows. He'd walked into a warehouse in Deptford and never walked out. The coroner called it cardiac arrest. Quinn called it bullshit. She stepped onto the platform. The air changed. It grew thick, heavy with incense and something metallic. The walls shimmered where the light touched them, as if the tiles were breathing. Quinn blinked hard. Her vision cleared. A doorway stood at the end of the platform, framed in rusted iron. Beyond it, stairs led down. The stairs hummed with a low vibration she felt in her teeth. The suspect was gone. She approached the doorway, her footsteps loud in the sudden silence. The humming grew stronger. The stairs descended into a darkness that didn't quite look like darkness—more like a thick, purple-brown absence of light that seemed to shift when she wasn't directly looking at it. A voice spoke from behind her. "You won't find him in there." Quinn spun, drawing her weapon in one fluid motion. A man stood at the edge of the platform, hands raised. Olive skin. Dark curls plastered to his forehead. A Saint Christopher medallion glinted at his throat. "The fuck are you?" Quinn kept the SIG trained on his chest. "Someone who knows you don't have a bone token." He stepped closer. Rainwater dripped from his jacket. "And the Market guards won't let you pass without one." "Market." "The Veil Market. Under Camden. Moves every full moon." He gestured at the doorway. "That's tonight's entrance. You follow him down there without the proper offering, they'll gut you before you hit the bottom step." Quinn's finger rested against the trigger guard. "And you know this how?" "Because I used to work for them. Patch people up when the deals went bad." He pulled back his sleeve, revealing a jagged scar running the length of his left forearm. "I'm Tomás Herrera. Former paramedic. Current liability." "You're telling me the supernatural bullshit is real." "I'm telling you it's real enough to kill you." Quinn stared at him. The rain. The humming stairs. Morris's face flashing behind her eyes. She had a choice. Turn around, call for backup, file a report that would end up buried in some cold case drawer. Or step through that doorway and find the truth, whatever it cost her. She lowered the weapon. "Then get me a token."
created_at"2026-07-07T20:54:29.447Z" 7/7/2026, 8:54:29 PM
model"aion-labs/aion-3.0-mini-20260707"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency651
moderation_latency(null)
generation_time37531
tokens_prompt1140
tokens_completion2234
native_tokens_prompt1002
native_tokens_completion1826
native_tokens_completion_images(null)
native_tokens_reasoning968
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)
usage0.00309088
router(null)
provider_responses
0
endpoint_id"0ad7ab68-a351-4a96-b2ef-fa8fe13adae3"
id"b1dce213fe324ec392904b572d3a8d1a"
is_byokfalse
latency650
model_permaslug"aion-labs/aion-3.0-mini-20260707"
provider_name"AionLabs"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer(null)
request_id"req-1783457669-n1WlNUQr8sbjR2Fh9FFp"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1783457669-cVFieVZjc5F5eI9oRKm8"
upstream_id"b1dce213fe324ec392904b572d3a8d1a"
total_cost0.00309088
cache_discount0.00016692
upstream_inference_cost0
provider_name"AionLabs"
response_cache_source_id(null)
data_region"global"

Evaluation details

Result Evaluator Details Meta Data
57.14% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags4
adverbTagCount1
adverbTags
0"He pulled back [back]"
dialogueSentences14
tagDensity0.286
leniency0.571
rawRatio0.25
effectiveRatio0.143
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount793
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)
30.64% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount793
totalAiIsms11
found
0
word"familiar"
count1
1
word"maw"
count1
2
word"scanned"
count1
3
word"cascading"
count1
4
word"echoed"
count1
5
word"footsteps"
count2
6
word"flickered"
count1
7
word"echoing"
count1
8
word"shimmered"
count1
9
word"silence"
count1
highlights
0"familiar"
1"maw"
2"scanned"
3"cascading"
4"echoed"
5"footsteps"
6"flickered"
7"echoing"
8"shimmered"
9"silence"
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
narrationSentences87
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount1
narrationSentences87
filterMatches(empty)
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences97
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
totalWords788
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions3
unquotedAttributions0
matches(empty)
46.45% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions31
wordCount676
uniqueNames15
maxNameDensity2.07
worstName"Quinn"
maxWindowNameDensity2.5
worstWindowName"Quinn"
discoveredNames
London1
Harlow1
Quinn14
Mornington1
Crescent1
Sauer1
Victorian1
Tube2
Northern1
Line1
Morris3
Deptford1
Saint1
Christopher1
Rainwater1
persons
0"Harlow"
1"Quinn"
2"Sauer"
3"Morris"
4"Saint"
5"Christopher"
6"Rainwater"
places
0"London"
1"Mornington"
2"Crescent"
3"Victorian"
4"Deptford"
globalScore0.464
windowScore0.833
96.81% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences47
glossingSentenceCount1
matches
0"light that seemed to shift when she wasn't directly looking at it"
1"quite look like darkness—more like a thick, purple-brown absence of light that seemed to shift when she wasn't directly looking at it"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount788
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences97
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs39
mean20.21
std16.28
cv0.806
sampleLengths
041
16
245
33
431
55
640
78
89
99
1037
112
1234
134
1437
151
1631
173
1846
1931
205
2132
2230
234
2445
256
266
2736
2812
2927
301
3135
3212
3338
348
359
3650
374
385
97.20% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences87
matches
0"been decommissioned"
1"was gone"
98.99% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs132
matches
0"were breathing"
1"wasn't directly looking"
25.04% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount5
semicolonCount0
flaggedSentences4
totalSentences97
ratio0.041
matches
0"Quinn caught a glimpse of him—black coat, pale skin, no discernible features in the downpour—as he vaulted a railing and disappeared into the maw of an alley near Mornington Crescent."
1"The smell hit her—rank water, rot, copper."
2"Fluorescent lights flickered overhead—impossible, since the station had been decommissioned in the seventies."
3"The stairs descended into a darkness that didn't quite look like darkness—more like a thick, purple-brown absence of light that seemed to shift when she wasn't directly looking at it."
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount682
adjectiveStacks1
stackExamples
0"thick, purple-brown absence"
adverbCount14
adverbRatio0.020527859237536656
lyAdverbCount2
lyAdverbRatio0.002932551319648094
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences97
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences97
mean8.12
std6.26
cv0.771
sampleLengths
013
128
24
32
430
515
63
76
813
94
108
115
1219
138
146
157
165
173
185
192
202
219
2216
237
244
256
264
272
285
2912
303
313
3211
334
3417
3513
367
371
3810
3911
408
411
421
433
4410
458
4612
478
484
494
69.42% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats6
diversityRatio0.4536082474226804
totalSentences97
uniqueOpeners44
42.74% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences78
matches
0"Somewhere ahead, footsteps splashed."
ratio0.013
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount18
totalSentences78
matches
0"She followed without hesitation, her"
1"She ran toward the sound."
2"She should call this in."
3"She pulled out her phone."
4"She stood still, listening."
5"She pressed forward until the"
6"She killed her torch and"
7"She crept forward."
8"He'd walked into a warehouse"
9"She stepped onto the platform."
10"It grew thick, heavy with"
11"Her vision cleared."
12"She approached the doorway, her"
13"He stepped closer"
14"He gestured at the doorway"
15"He pulled back his sleeve,"
16"She had a choice."
17"She lowered the weapon."
ratio0.231
49.74% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount64
totalSentences78
matches
0"Detective Harlow Quinn's boots slapped"
1"The suspect was fast."
2"Quinn caught a glimpse of"
3"She followed without hesitation, her"
4"The words dissolved in the"
5"The alley opened into a"
6"Quinn scanned left, right."
7"A metal grate rattled somewhere"
8"She ran toward the sound."
9"A maintenance hatch lay torn"
10"Quinn knelt, shining her torch"
11"Iron rungs descended into black"
12"The suspect's footprints vanished into"
13"She should call this in."
14"She pulled out her phone."
15"Quinn holstered her weapon, gripped"
16"The ladder dropped her into"
17"The smell hit her—rank water,"
18"She stood still, listening."
19"The tunnel forked three ways."
ratio0.821
64.10% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences78
matches
0"Either way, Quinn was out"
ratio0.013
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences24
technicalSentenceCount1
matches
0"The stairs descended into a darkness that didn't quite look like darkness—more like a thick, purple-brown absence of light that seemed to shift when she wasn't …"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags4
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
85.7422%