Run: 2026-09-24-01M39VGWHT0DMEMVNFR1BAR4XD

Run Details

Duration:
1m 50s
Cost:
$0.006926
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 had been falling over Soho for six hours, and the city wore it badly. The Raven's Nest's green sign bled into the flooded gutter outside, and Detective Harlow Quinn had watched that smear of light from a doorway opposite for three hours, cold working through her coat while her thumb traced the cracked leather strap of her watch. Eleven forty. The bar's front door hadn't opened all night. Which was why, when a man slipped out of the rear alley with his hood up and a canvas duffel hugged to his chest, she was already crossing the street. "Tomás Herrera. Metropolitan Police." He ran. She gave chase up Wardour Street, boots hammering through puddles deep enough to soak her to the knee. He vaulted a skip, and something swung free of his neck and snapped — a white charm on a leather cord, hitting the pavement, bouncing once. She stamped her palm over it, shoved it in her pocket, and kept running. Great Chapel Street. Tottenham Court Road. Buses hissed past, throwing up sheets of gray water. He was younger, faster, but he kept checking over his shoulder, and every check cost him a half step. "You've got the wrong man, officer!" "Then stop running and tell me that with a lawyer present." He cut left, through a gap in the hoarding around a construction site, and she followed him down scaffolding poles slick as soap. Her shoulder screamed where it hit a crossbeam. He came out onto the pavement near Warren Street with a lead of maybe twenty meters, and she ate into it block by block, breath tearing, the rain freezing on her face. Camden High Street was shuttered and empty, stall frames folded down for the night, chip-shop steam rising from a vent like breath from a wound. He cut off the main drag, took a side road at a sprint, and it dead-ended at a boarded-up frontage she recognized from the file — the old South Kentish Town station, closed before her father was born, its tiled name still visible under a century of grime. Herrera wrenched at a sheet of plywood. It swung on a hinge she couldn't see. "The station is closed, detective." He was panting, the duffel still clutched to his chest. "Has been for a hundred years." "Then you've got nowhere left to go." "Take the collar here. On the street. Whatever you think we are, whatever you think you saw tonight — the street is as far as you can follow it." "Give me one reason to believe you." His eyes dropped to her coat pocket, where the white charm sat, and something in his face went flat and cold. "You're carrying my token. That's reason enough. They'll know it isn't yours." "Who's they?" He looked up, then. The clouds had torn open, and the full moon spilled down over the dead station's facade, over his rain-dark curls, over the black mouth of the stairwell behind him. "Dawn," he said. "The market moves at dawn. If you're coming, come now. If you're not — let me go and go home, and forget the token, and forget the Nest, and live a long life, Detective Quinn." "Is that what you told my colleague? Three years ago? DS Morris, working a case that ended at this station. His file doesn't say where he went that night. It just stops." Herrera's grip tightened on the duffel. For a moment she thought he'd answer. Then he stepped backward into the dark, and the plywood swung shut behind him with a sound like a coffin lid. Quinn stood at the sealed frontage, rain running off her chin, her radio crackling against her shoulder. "Control, this is Quinn. Suspect entered the disused South Kentish Town station, north side entrance. I need backup at—" "Copy, Quinn. Nearest armed response is nineteen minutes out. Do not enter the structure alone. Confirm." She looked at the plywood. Nineteen minutes. The market moved at dawn. By morning those stairs would open onto brick and dust, and whatever Herrera carried in that duffel would be somewhere she couldn't follow, and Morris's file would keep stopping where it stopped. Her thumb found the worn strap of the watch. Morris had put it on her wrist the day she made detective, both hands shaking from the champagne, and said, *Time's the only thing they can't take off you, Harlow.* They'd taken everything else. "Quinn, confirm you are holding position." She clicked the radio twice and left it crackling on the pavement. The plywood opened easier the second time. Beyond it, a service stairwell dropped into dark, the air rising up warm and wet and wrong — tallow and river mud and something sweet underneath, like fruit going off. Her torch beam found old tile, then newer wood, then a turnstile that had no business standing upright in a station that had been stripped to the studs in 1924. An old man sat beside it on a folding chair, lantern balanced on his knee. His eyes were the color of boiled milk, and they found her without light. "Token." She set the white charm on his palm. It still carried a smear of blood where Herrera's hand had torn on the scaffolding. "Fresh." The old man turned it over with a fingernail. "Whose blood?" "Mine now." "Moon's full tonight. We fold at first light, and we don't fold for stragglers." "Noted." He bit the charm, nodded, and waved her through the turnstile. The passage beyond breathed heat at her, and the sound reached her next — a crowd, hundreds strong, murmuring under the earth. Her torch showed the tunnel opening ahead into lantern light, stalls and awnings and the glint of things on sale that had no price tags. Twenty meters in, past a stall hung with jars of teeth, a man in a bloodstained apron was stitching a wound in a boy's shoulder by candlelight — olive skin, curly dark hair, a Saint Christopher medallion swinging with each pass of the needle. He glanced up, and his hands never stopped moving. "You kept the token," Herrera called across the aisle. "Stubborn woman." "You owe me a name, doctor. And a file number." "Then keep up." He shouldered the duffel and plunged into the crowd, and Quinn went in after him.
created_at"2026-09-24T14:01:15.594Z" 9/24/2026, 2:01:15 PM
model"aion-labs/aion-3.5-mini-20260923"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2576
moderation_latency(null)
generation_time110130
tokens_prompt1104
tokens_completion5068
native_tokens_prompt989
native_tokens_completion4548
native_tokens_completion_images(null)
native_tokens_reasoning3548
native_tokens_cached256
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)
usage0.00692638
router(null)
user_agent"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer(null)
request_id"req-1790258475-PKpxkOHAolyggByx7tsE"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1790258475-ldTky2crwoq4ybhUE3sM"
upstream_id"dace6202a7794b339acebe75f8d80d69"
provider_responses
0
endpoint_id"60ac3bdc-90ec-4769-9193-2c00b4d79562"
id"dace6202a7794b339acebe75f8d80d69"
is_byokfalse
latency2576
model_permaslug"aion-labs/aion-3.5-mini-20260923"
provider_name"AionLabs"
status200
total_cost0.00692638
cache_discount0.00013312
upstream_inference_cost0
provider_name"AionLabs"
response_cache_source_id(null)
data_region"global"
workspace_id"97e315e5-d303-487d-83c1-83180e8a13d4"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags4
adverbTagCount0
adverbTags(empty)
dialogueSentences26
tagDensity0.154
leniency0.308
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1050
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)
61.90% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1050
totalAiIsms8
found
0
word"traced"
count1
1
word"charm"
count4
2
word"facade"
count1
3
word"structure"
count1
4
word"glint"
count1
highlights
0"traced"
1"charm"
2"facade"
3"structure"
4"glint"
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
narrationSentences51
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences51
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences73
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen49
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans1
markdownWords10
totalWords1057
ratio0.009
matches
0"Time's the only thing they can't take off you, Harlow."
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions9
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions31
wordCount819
uniqueNames20
maxNameDensity0.61
worstName"Herrera"
maxWindowNameDensity2
worstWindowName"Street"
discoveredNames
Soho1
Raven1
Nest1
Detective1
Harlow2
Quinn3
Wardour1
Street4
Chapel1
Court1
Road1
Warren1
High1
South1
Kentish1
Town1
Herrera5
Morris2
Saint1
Christopher1
persons
0"Raven"
1"Nest"
2"Harlow"
3"Quinn"
4"Herrera"
5"Morris"
6"Saint"
7"Christopher"
places
0"Soho"
1"Wardour"
2"Street"
3"Chapel"
4"Court"
5"Road"
6"Warren"
7"High"
8"South"
9"Kentish"
10"Town"
globalScore1
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences41
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1057
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences73
matches
0"watched that smear"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs43
mean24.58
std20.29
cv0.825
sampleLengths
059
140
24
32
458
534
66
711
863
973
1015
1121
127
1329
147
1521
1612
172
1833
1938
2032
2134
2217
2319
2416
2544
2643
276
2812
2967
3029
311
3223
3312
342
3514
361
3758
3853
3911
4010
413
4215
91.50% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences51
matches
0"was shuttered"
1"been stripped"
40.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs125
matches
0"was already crossing"
1"was panting"
2"was stitching"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount5
semicolonCount0
flaggedSentences5
totalSentences73
ratio0.068
matches
0"He vaulted a skip, and something swung free of his neck and snapped — a white charm on a leather cord, hitting the pavement, bouncing once."
1"He cut off the main drag, took a side road at a sprint, and it dead-ended at a boarded-up frontage she recognized from the file — the old South Kentish Town station, closed before her father was born, its tiled name still visible under a century of grime."
2"Beyond it, a service stairwell dropped into dark, the air rising up warm and wet and wrong — tallow and river mud and something sweet underneath, like fruit going off."
3"The passage beyond breathed heat at her, and the sound reached her next — a crowd, hundreds strong, murmuring under the earth."
4"Twenty meters in, past a stall hung with jars of teeth, a man in a bloodstained apron was stitching a wound in a boy's shoulder by candlelight — olive skin, curly dark hair, a Saint Christopher medallion swinging with each pass of the needle."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount818
adjectiveStacks0
stackExamples(empty)
adverbCount19
adverbRatio0.023227383863080684
lyAdverbCount3
lyAdverbRatio0.003667481662591687
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences73
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences73
mean14.48
std11.51
cv0.795
sampleLengths
015
144
22
38
430
54
62
718
826
914
103
113
129
1319
146
1511
1623
178
1832
1925
2048
217
228
2315
246
257
2629
277
2821
2912
302
314
3229
333
3435
3532
366
377
3821
3917
4019
4116
425
432
445
4532
469
4734
486
4912
91.32% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats0
diversityRatio0.547945205479452
totalSentences73
uniqueOpeners40
70.92% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences47
matches
0"Then he stepped backward into"
ratio0.021
24.26% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount23
totalSentences47
matches
0"She gave chase up Wardour"
1"He vaulted a skip, and"
2"She stamped her palm over"
3"He was younger, faster, but"
4"He cut left, through a"
5"Her shoulder screamed where it"
6"He came out onto the"
7"He cut off the main"
8"It swung on a hinge"
9"He was panting, the duffel"
10"His eyes dropped to her"
11"He looked up, then."
12"She looked at the plywood."
13"Her thumb found the worn"
14"She clicked the radio twice"
15"Her torch beam found old"
16"His eyes were the color"
17"She set the white charm"
18"It still carried a smear"
19"He bit the charm, nodded,"
ratio0.489
34.47% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount40
totalSentences47
matches
0"Rain had been falling over"
1"The Raven's Nest's green sign"
2"The bar's front door hadn't"
3"She gave chase up Wardour"
4"He vaulted a skip, and"
5"She stamped her palm over"
6"Tottenham Court Road."
7"Buses hissed past, throwing up"
8"He was younger, faster, but"
9"He cut left, through a"
10"Her shoulder screamed where it"
11"He came out onto the"
12"Camden High Street was shuttered"
13"He cut off the main"
14"Herrera wrenched at a sheet"
15"It swung on a hinge"
16"He was panting, the duffel"
17"His eyes dropped to her"
18"He looked up, then."
19"The clouds had torn open,"
ratio0.851
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences47
matches(empty)
ratio0
66.33% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences28
technicalSentenceCount3
matches
0"Quinn stood at the sealed frontage, rain running off her chin, her radio crackling against her shoulder."
1"Her torch beam found old tile, then newer wood, then a turnstile that had no business standing upright in a station that had been stripped to the studs in 1924."
2"Her torch showed the tunnel opening ahead into lantern light, stalls and awnings and the glint of things on sale that had no price tags."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags4
uselessAdditionCount1
matches
0"He was panting, the duffel still clutched to his chest"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags3
fancyCount1
fancyTags
0"He was panting (be pant)"
dialogueSentences26
tagDensity0.115
leniency0.231
rawRatio0.333
effectiveRatio0.077
79.3568%