Run: 2026-09-23-01M37PAG9N2C6T068AYF5WCZDT

Run Details

Duration:
43.0s
Cost:
$0.013726
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 came down like it had a grudge against London. Harlow Quinn stood beneath the sagging awning of a closed kebab shop across from The Raven's Nest, watching the green neon sign buzz and flicker against the downpour. Three hours. Three hours of watching that door, her feet going numb in her boots, the worn leather watch on her wrist reading quarter past midnight. Then the door opened, and Tomás Herrera stepped out. She knew him from the file. Twenty-nine, olive-skinned, curly dark hair plastered flat by the rain within seconds. Former paramedic, struck off the register two years ago. The kind of man who patched people up in back rooms and never filed a single report. The kind of man who knew where the bodies were, because he'd probably stitched half of them closed. He turned north. Quinn gave him half a block. Herrera walked like a man who knew he was being followed. Head up, glancing at reflections in darkened shopfronts, doubling back once at a newsagent's before cutting down a side street. Quinn kept her distance, staying in doorways, letting a pair of drunks stumble between them for cover. The rain worked in her favour. Nobody looked at anybody in this weather. They crossed out of Soho, Herrera picking up pace, weaving past the stragglers spilling out of a pub. Somewhere behind her, a siren wailed and faded. Herrera glanced over his shoulder. Brown eyes found hers through the rain. He ran. "Herrera!" Quinn's voice cracked across the street. "Police! Stop!" He didn't stop. He vaulted a sandwich board, sending it clattering, and tore down the pavement with the loose-limbed speed of a man who'd done this before. Quinn put her head down and drove after him, her radio bouncing against her hip. "Control, this is Quinn. I've got eyes on Herrera, Tomás, heading north from Soho toward Camden. On foot. Requesting units." Static hissed back at her. She yanked the radio up. "Control, say again, I'm in pursuit—" The static swallowed her voice. She swore and clipped the radio back on. Herrera cut down an alley, boots slapping through puddles that threw up orange light from a security lamp. Quinn followed, lungs burning, the cold rain needling her face. Bins. A chained bicycle. A man in a doorway who swore at them both. Herrera grabbed a drainpipe and swung himself over a low brick wall in one motion, and Quinn took the wall at a run, scraping her palms on the wet brick as she hauled herself over. She landed hard on the other side and kept moving. "Tomás!" she shouted. "I just want to talk!" "Nobody ever just wants to talk!" His voice bounced off the brickwork. He was ahead of her, cutting through a gap between terraced houses, the Saint Christopher medallion at his neck catching a streetlight. "You've been sitting outside the Nest for three hours. I counted." "You should've come over. I'd have bought you a coffee." "I don't take coffee from cops!" He burst out of the gap onto a wider street and she nearly lost him — a bus groaned past, its windows lit up and blind, and when it cleared, Herrera was a block gone, sprinting past the shuttered stalls of Camden Market. Quinn's breath tore at her chest. Eighteen years on the job, and the young ones still ran faster. But she ran smarter. He was heading somewhere. Nobody ran blind in this rain. He had a destination, and destinations could be staked out, watched, torn open. She just had to keep him in sight long enough to see where. Herrera ducked left down a service road and Quinn followed, and the city changed. The noise fell away. The streetlights thinned. This was the old stretch near the Underground, the part of Camden the developers hadn't reached — boarded shopfronts, graffiti gone grey with age, weeds pushing up through the cracked pavement. The rain hammered on the rusted awnings like fingers on a drum. And Herrera stopped running. Quinn slowed. Her hand drifted to her holster. Twenty yards ahead, the man stood at the mouth of a fenced-off construction site, bent double, catching his breath. Behind him, half-swallowed by scaffolding and hoardings, yawned the bricked-up entrance of an abandoned Tube station. She'd seen the type before. Sealed since the sixties. Razor wire along the top of the fence. A council notice plastered to the hoarding, the paper pulped to mush by the rain. "End of the road, Herrera." She walked toward him, unhurried now, her boots loud on the wet concrete. "There's nothing back there but a dead station." He straightened up. He wasn't even looking at her. He was looking past her, the way people look when they're working out how much time they've got. "You shouldn't have followed me tonight, Detective." "Quinn. And I've heard that before, usually right before somebody does something stupid." She closed the distance to fifteen yards. "You're off the register, you're running with people who light fires the Met can't put out, and last month a man turned up in A&E with a wound that sealed itself shut before the sutures went in. Your name's on the admission slip. So you can stand there catching pneumonia, or you can come in from the rain and we'll talk somewhere warm." Something flickered across his face. Not fear. Pity. That was worse. "You have no idea what you're standing on top of." He took a step backward, toward the hoarding. "Don't." She drew her sidearm, the weight of it steady in her hand. "Whatever hole you're about to crawl down, don't." "You want to know what happened to your partner?" Herrera said. "Morris. Three years ago. The case they closed without an answer." The rain seemed to get louder. Quinn's finger rested along the trigger guard. Her jaw tightened. "You don't know a damn thing about Morris." "I know things got explained away. I know you've spent three years chasing people like me because you can't chase what actually took him." He reached behind him and pulled at a section of the hoarding — a section that swung, because it wasn't fixed to anything, because it was a door dressed up as a wall. "Down there, they know. Down there, they trade in answers. But it's not your world, Detective. It's not your streets anymore." He stepped through into the dark. Quinn ran. She hit the hoarding four seconds after it swung shut, shoulder first, and found the gap — a rusted iron gate, and behind it a stairwell descending into the earth, the old station steps slick with rainwater running down like a stream. The smell rose up out of the ground: candle smoke, wet stone, and something else underneath it, something faintly metallic and wrong. She stood at the top of the stairs with her weapon raised and her radio dead and rain running off the end of her nose. No backup. No signal. No jurisdiction she could name. Every instinct hammered out the same word — wait, wait, call it in, wait for daylight, wait for uniformed bodies and proper warrants and a world that made sense. Then her watch, the old leather one, the one Morris had given her a week before the end, began to tick backwards. Quinn looked at it. Looked down the stairwell, where far below, something flickered — a warm, amber light, and the murmur of a crowd that had no business existing beneath a condemned station. She breathed out. She started down the stairs.
created_at"2026-09-23T17:51:54.696Z" 9/23/2026, 5:51:54 PM
model"aion-labs/aion-3.5-20260923"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency628
moderation_latency(null)
generation_time42903
tokens_prompt1104
tokens_completion2454
native_tokens_prompt989
native_tokens_completion2164
native_tokens_completion_images(null)
native_tokens_reasoning610
native_tokens_cached989
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)
usage0.01372575
router(null)
user_agent"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer(null)
request_id"req-1790185914-fQ9YgBcQVgcbHRzC546R"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1790185914-fSaCnw0OtFaYjh9d0F7O"
upstream_id"478a71e4118b43c390d11750005ae068"
provider_responses
0
endpoint_id"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id"478a71e4118b43c390d11750005ae068"
is_byokfalse
latency628
model_permaslug"aion-labs/aion-3.5-20260923"
provider_name"AionLabs"
status200
total_cost0.01372575
cache_discount0.00222525
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
totalTags9
adverbTagCount0
adverbTags(empty)
dialogueSentences23
tagDensity0.391
leniency0.783
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1255
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)
84.06% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1255
totalAiIsms4
found
0
word"flicker"
count1
1
word"flickered"
count2
2
word"weight"
count1
highlights
0"flicker"
1"flickered"
2"weight"
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
narrationSentences92
matches(empty)
49.69% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount4
hedgeCount2
narrationSentences92
filterMatches
0"watch"
1"notice"
2"look"
hedgeMatches
0"seemed to"
1"began to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences106
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen63
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1261
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
totalMentions36
wordCount1005
uniqueNames14
maxNameDensity1.29
worstName"Quinn"
maxWindowNameDensity2.5
worstWindowName"Quinn"
discoveredNames
London1
Quinn13
Raven1
Nest1
Tomás1
Herrera10
Soho1
Saint1
Christopher1
Camden2
Market1
Underground1
Tube1
Morris1
persons
0"Quinn"
1"Nest"
2"Tomás"
3"Herrera"
4"Saint"
5"Christopher"
6"Morris"
places
0"London"
1"Raven"
2"Soho"
3"Underground"
globalScore0.853
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences59
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1261
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences106
matches
0"watching that door"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs44
mean28.66
std24.8
cv0.865
sampleLengths
011
154
29
362
49
561
631
77
82
99
1042
1120
1216
1313
1477
1510
168
1745
1810
196
2088
2113
2214
2350
244
2575
2626
2727
287
2983
3011
3118
3221
3322
346
3518
3678
376
3866
3925
4038
4122
4233
438
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences92
matches
0"being followed"
90.11% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs182
matches
0"was heading"
1"wasn't even looking"
2"was looking"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount6
semicolonCount0
flaggedSentences6
totalSentences106
ratio0.057
matches
0"He burst out of the gap onto a wider street and she nearly lost him — a bus groaned past, its windows lit up and blind, and when it cleared, Herrera was a block gone, sprinting past the shuttered stalls of Camden Market."
1"This was the old stretch near the Underground, the part of Camden the developers hadn't reached — boarded shopfronts, graffiti gone grey with age, weeds pushing up through the cracked pavement."
2"\"I know things got explained away. I know you've spent three years chasing people like me because you can't chase what actually took him.\" He reached behind him and pulled at a section of the hoarding — a section that swung, because it wasn't fixed to anything, because it was a door dressed up as a wall."
3"She hit the hoarding four seconds after it swung shut, shoulder first, and found the gap — a rusted iron gate, and behind it a stairwell descending into the earth, the old station steps slick with rainwater running down like a stream."
4"Every instinct hammered out the same word — wait, wait, call it in, wait for daylight, wait for uniformed bodies and proper warrants and a world that made sense."
5"Looked down the stairwell, where far below, something flickered — a warm, amber light, and the murmur of a crowd that had no business existing beneath a condemned station."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1005
adjectiveStacks0
stackExamples(empty)
adverbCount18
adverbRatio0.01791044776119403
lyAdverbCount4
lyAdverbRatio0.003980099502487562
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences106
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences106
mean11.9
std11.01
cv0.925
sampleLengths
011
128
22
324
49
56
612
79
817
918
103
116
1211
1320
1417
156
167
1718
188
195
207
212
227
232
243
2524
2615
2720
285
295
306
315
328
3318
3410
351
363
3710
3835
3910
403
415
4212
4322
4411
4510
466
4743
486
4912
58.81% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats11
diversityRatio0.41509433962264153
totalSentences106
uniqueOpeners44
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences81
matches
0"Then the door opened, and"
1"Somewhere behind her, a siren"
2"Then her watch, the old"
ratio0.037
71.85% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount30
totalSentences81
matches
0"She knew him from the"
1"He turned north."
2"They crossed out of Soho,"
3"He didn't stop."
4"He vaulted a sandwich board,"
5"She yanked the radio up."
6"She swore and clipped the"
7"She landed hard on the"
8"His voice bounced off the"
9"He was ahead of her,"
10"He burst out of the"
11"He was heading somewhere."
12"He had a destination, and"
13"She just had to keep"
14"Her hand drifted to her"
15"She'd seen the type before."
16"She walked toward him, unhurried"
17"He straightened up."
18"He wasn't even looking at"
19"He was looking past her,"
ratio0.37
52.59% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount66
totalSentences81
matches
0"The rain came down like"
1"Harlow Quinn stood beneath the"
2"She knew him from the"
3"The kind of man who"
4"The kind of man who"
5"He turned north."
6"Quinn gave him half a"
7"Herrera walked like a man"
8"Quinn kept her distance, staying"
9"The rain worked in her"
10"Nobody looked at anybody in"
11"They crossed out of Soho,"
12"Herrera glanced over his shoulder."
13"Brown eyes found hers through"
14"Quinn's voice cracked across the"
15"He didn't stop."
16"He vaulted a sandwich board,"
17"Quinn put her head down"
18"Static hissed back at her."
19"She yanked the radio up."
ratio0.815
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences81
matches(empty)
ratio0
40.82% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences35
technicalSentenceCount5
matches
0"Three hours of watching that door, her feet going numb in her boots, the worn leather watch on her wrist reading quarter past midnight."
1"The kind of man who knew where the bodies were, because he'd probably stitched half of them closed."
2"Quinn kept her distance, staying in doorways, letting a pair of drunks stumble between them for cover."
3"He vaulted a sandwich board, sending it clattering, and tore down the pavement with the loose-limbed speed of a man who'd done this before."
4"Looked down the stairwell, where far below, something flickered — a warm, amber light, and the murmur of a crowd that had no business existing beneath a condemn…"
69.44% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags9
uselessAdditionCount1
matches
0"She drew, the weight of it steady in her hand"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount1
fancyTags
0"she shouted (shout)"
dialogueSentences23
tagDensity0.087
leniency0.174
rawRatio0.5
effectiveRatio0.087
83.3569%