Run: 2026-09-23-01M37PAKGE4XCJN3VWTQ6FQ7WK

Run Details

Duration:
43.4s
Cost:
$0.015682
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
Detective Harlow Quinn had been watching the green neon sign for three hours when Tomás Herrera finally walked out of the Raven's Nest. The rain had started as a drizzle around ten and turned serious by midnight, hammering the Soho pavement in sheets that turned the streetlights into smears of orange. Quinn stood beneath a dead awning across from the bar, collar up, hands in her pockets, the worn leather watch on her left wrist reading 12:47. Herrera stepped into the downpour and pulled his jacket over his head, and she gave him half a block before she moved. She knew him from the file. Former paramedic, lost his license two years back, and since then every lowlife in central London with a wound they couldn't take to A&E apparently ended up on his table. What she didn't have was a single witness willing to say so out loud. Tonight that was going to change. "Herrera." His shoulders locked. He turned just enough for the streetlight to catch the Saint Christopher medallion at his throat, and for one second they looked at each other across the rain. "Detective." He said it like a diagnosis. "Rough night to be standing outside." "Rough night to be doing whatever you were doing in there for two hours." She stepped off the kerb. "Walk with me. We'll do it somewhere dry." "I don't think so." "Tommy." She let the name land the way a hand lands on a shoulder. "I know about the supplies. I know about the payments. The only question left is whether you talk to me tonight or to the CPS next month." He ran. He went left through the gap between a shuttered kebab shop and a sex shop's blinking sign, and Quinn followed without a moment's hesitation, her boots hitting wet concrete, water exploding off puddles as she cut the angle hard. He was fast. He was also predictable — three years of chasing people through this city had taught her that everyone runs the way they live, and Herrera ran like a man who fixed things: straight lines, no waste. "Quinn!" he shouted over his shoulder, vaulting a stack of beer crates. "I don't have time for this tonight!" "Make time." He tore down the alley and hooked right onto the back street, and she lost sight of him for four seconds — four seconds that felt like a held breath — before she caught the flash of his medallion again under a sodium lamp. He wasn't running like a cornered man. That was the thing that put a cold finger on the back of her neck. He was running like a man with somewhere to be, and he was letting her keep up. The streets blurred. Chinatown's gates. A construction site, chain-link and mud. He squeezed through a gap in the hoarding and she went through after him, tearing her sleeve on the wire, landing hard on the other side and rolling back to her feet the way her instructor had drilled into her twenty years ago. Her knee screamed. She ignored it. "Whatever you're chasing," Herrera called from somewhere ahead, his voice bouncing off brick, "it's not what you think it is." "Everyone says that." "Because it's true more often than you'd believe." She burst out onto the canal towpath and there he was, fifty metres ahead, running north with the black water sliding past on her right. Rain pocked the surface of the canal like a million tiny mouths talking at once. Her breath burned. Her heartbeat filled her ears. And underneath it, underneath all of it, Morris's face floated up the way it always did when her body hit its limit — the last photograph of him, laughing outside the station, three weeks before the night nobody could explain to her satisfaction. She ran faster. Herrera cut off the towpath at Camden, through a scrap of wasteland, over a wall that she scaled with her forearms and a grunt of fury, and then he dropped down into the mouth of a service road she'd never noticed in fifteen years of working this city. Chain-link. Graffiti. A padlocked gate hanging open on one hinge. And then he was gone. Quinn slowed at the top of a stairwell cut into the earth. A maintenance entrance, half-swallowed by ivy, an old Transport for London sign bolted to the brick above it, rusted to the point of illegibility. Below, a corridor of brick arched away into the dark, lit at intervals by caged bulbs that had no business working in an abandoned station. She could hear him — boots on wet stone, fading. She put her hand on her radio and got static. Of course she did. Down here the world above simply stopped applying. She descended anyway, one hand on the damp brick, and the corridor opened out onto a platform that hadn't seen a train since before she was born. Weeds grew through the track ballast. Rainwater wept through the ceiling in long silver threads. And at the far end, where the tunnel mouth gaped, Herrera stood talking to a shape. The shape was a woman, broad as a wardrobe, holding a lantern that burned with a light Quinn's eyes kept insisting was the wrong colour. Not orange. Not white. Something that made her teeth ache. Herrera held something up between his fingers — small, pale, carved — and the woman turned it in the lantern light. A token. Bone, by the look of it, worn smooth as a river stone. The woman nodded and stepped aside, and Herrera vanished past her into the tunnel. Before he did, he looked back — Quinn would swear to it, he looked straight at her across the dead platform — and shook his head once. "Go home, Detective," he called, his voice strange and flat in the vaulted dark. "You can't follow me where I'm going. Not without one of these." And then the tunnel swallowed him. Quinn walked to the woman with the lantern. The light washed over Quinn's face and the woman studied her the way a butcher studies a cut of meat — unhurried, professional. "No token." The woman didn't ask it. "I'm police." "Down here?" The woman's laugh was a low rumble. "Down here, that word's just noise. You want in, you need a token. You want to stand on the platform all night getting rained on through the ceiling, that's free." Quinn stood at the threshold of the tunnel. Cold air breathed out of it, carrying smells she couldn't name — smoke, incense, something metallic and alive. From somewhere deep below, past the curve of the tunnel, she caught voices. Dozens of them. The murmur of a crowd, and beneath it music, and beneath that a sound like a bell rung underwater. Every instinct from eighteen years of service told her the same thing: this was a crime scene waiting to be catalogued, a network waiting to be mapped, and the man who could connect it all to the Nest had just walked into the middle of it. Every other instinct — the older kind, the kind that had started whispering the night Morris died and never stopped — told her that the rules she lived by ended at this tunnel mouth, and that the people who'd gone looking for answers past this line before her hadn't all come back. Her thumb traced the cracked face of her watch. Three years since Morris. Three years of files that contradicted themselves, of witnesses who changed their stories overnight, of a partner's death wrapped in a silence no warrant had ever broken. She thought: he's getting away. She thought: he wanted me to follow him. And that scared her more than the dark did. Quinn took out her warrant card, looked at it for a long moment, then put it away. She turned her collar down, cracked her neck, and walked into the tunnel. "Bad idea," the lantern woman said behind her. "Probably." The dark took her, and the sound of the rain faded to nothing.
created_at"2026-09-23T17:51:57.982Z" 9/23/2026, 5:51:57 PM
model"aion-labs/aion-3.5-20260923"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency459
moderation_latency(null)
generation_time43350
tokens_prompt1104
tokens_completion2853
native_tokens_prompt989
native_tokens_completion2490
native_tokens_completion_images(null)
native_tokens_reasoning945
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)
usage0.01568175
router(null)
user_agent"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer(null)
request_id"req-1790185917-YuNw9QNFbC2fxy6lA4GB"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1790185917-gzmuYLl2yk8wGGLeES6k"
upstream_id"1d6a69b4739347cb93cd10d5f13971c5"
provider_responses
0
endpoint_id"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id"1d6a69b4739347cb93cd10d5f13971c5"
is_byokfalse
latency459
model_permaslug"aion-labs/aion-3.5-20260923"
provider_name"AionLabs"
status200
total_cost0.01568175
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
totalTags8
adverbTagCount0
adverbTags(empty)
dialogueSentences22
tagDensity0.364
leniency0.727
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1337
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)
88.78% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1337
totalAiIsms3
found
0
word"predictable"
count1
1
word"traced"
count1
2
word"silence"
count1
highlights
0"predictable"
1"traced"
2"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
narrationSentences83
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount2
hedgeCount0
narrationSentences83
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences96
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen50
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1350
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions11
unquotedAttributions0
matches(empty)
83.33% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions33
wordCount1203
uniqueNames13
maxNameDensity0.83
worstName"Quinn"
maxWindowNameDensity2.5
worstWindowName"Quinn"
discoveredNames
Harlow1
Quinn10
Tomás1
Herrera8
Raven1
Nest2
Soho1
London2
Saint1
Christopher1
Morris3
Camden1
Transport1
persons
0"Harlow"
1"Quinn"
2"Tomás"
3"Herrera"
4"Raven"
5"Saint"
6"Christopher"
7"Morris"
places
0"Soho"
1"London"
2"Camden"
globalScore1
windowScore0.833
68.03% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences61
glossingSentenceCount2
matches
0"'t take to A&E apparently ended up on his tab"
1"felt like a held breath — before she ca"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1350
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences96
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs42
mean32.14
std28.36
cv0.882
sampleLengths
023
176
256
31
431
513
627
74
841
92
1078
1119
122
1383
1460
1520
163
178
1891
193
2058
215
2271
2322
2458
2570
2641
2726
286
2931
307
312
3239
3361
3498
3540
365
3717
3830
398
401
4113
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences83
matches
0"was gone"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs190
matches
0"was running"
1"was letting"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount13
semicolonCount0
flaggedSentences9
totalSentences96
ratio0.094
matches
0"He was also predictable — three years of chasing people through this city had taught her that everyone runs the way they live, and Herrera ran like a man who fixed things: straight lines, no waste."
1"He tore down the alley and hooked right onto the back street, and she lost sight of him for four seconds — four seconds that felt like a held breath — before she caught the flash of his medallion again under a sodium lamp."
2"And underneath it, underneath all of it, Morris's face floated up the way it always did when her body hit its limit — the last photograph of him, laughing outside the station, three weeks before the night nobody could explain to her satisfaction."
3"She could hear him — boots on wet stone, fading."
4"Herrera held something up between his fingers — small, pale, carved — and the woman turned it in the lantern light."
5"Before he did, he looked back — Quinn would swear to it, he looked straight at her across the dead platform — and shook his head once."
6"The light washed over Quinn's face and the woman studied her the way a butcher studies a cut of meat — unhurried, professional."
7"Cold air breathed out of it, carrying smells she couldn't name — smoke, incense, something metallic and alive."
8"Every other instinct — the older kind, the kind that had started whispering the night Morris died and never stopped — told her that the rules she lived by ended at this tunnel mouth, and that the people who'd gone looking for answers past this line before her hadn't all come back."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1193
adjectiveStacks0
stackExamples(empty)
adverbCount34
adverbRatio0.028499580888516344
lyAdverbCount3
lyAdverbRatio0.002514668901927913
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences96
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences96
mean14.06
std12.21
cv0.868
sampleLengths
023
128
226
322
46
530
614
76
81
93
1028
117
126
1319
148
154
1614
1727
182
1939
203
2136
2212
237
242
2544
267
2715
2817
293
302
316
3243
333
343
3520
363
378
3825
3915
403
415
4243
433
4448
451
461
478
485
4912
65.63% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats12
diversityRatio0.46875
totalSentences96
uniqueOpeners45
43.86% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences76
matches
0"Of course she did."
ratio0.013
72.63% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount28
totalSentences76
matches
0"She knew him from the"
1"His shoulders locked."
2"He turned just enough for"
3"He said it like a"
4"She stepped off the kerb"
5"She let the name land"
6"He went left through the"
7"He was fast."
8"He was also predictable —"
9"he shouted over his shoulder,"
10"He tore down the alley"
11"He wasn't running like a"
12"He was running like a"
13"He squeezed through a gap"
14"Her knee screamed."
15"She ignored it."
16"She burst out onto the"
17"Her breath burned."
18"Her heartbeat filled her ears."
19"She ran faster."
ratio0.368
65.26% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount60
totalSentences76
matches
0"Detective Harlow Quinn had been"
1"The rain had started as"
2"Quinn stood beneath a dead"
3"Herrera stepped into the downpour"
4"She knew him from the"
5"Tonight that was going to"
6"His shoulders locked."
7"He turned just enough for"
8"He said it like a"
9"She stepped off the kerb"
10"She let the name land"
11"He went left through the"
12"He was fast."
13"He was also predictable —"
14"he shouted over his shoulder,"
15"He tore down the alley"
16"He wasn't running like a"
17"That was the thing that"
18"He was running like a"
19"The streets blurred."
ratio0.789
65.79% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences76
matches
0"Before he did, he looked"
ratio0.013
11.28% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences38
technicalSentenceCount7
matches
0"The rain had started as a drizzle around ten and turned serious by midnight, hammering the Soho pavement in sheets that turned the streetlights into smears of o…"
1"He went left through the gap between a shuttered kebab shop and a sex shop's blinking sign, and Quinn followed without a moment's hesitation, her boots hitting …"
2"Below, a corridor of brick arched away into the dark, lit at intervals by caged bulbs that had no business working in an abandoned station."
3"The shape was a woman, broad as a wardrobe, holding a lantern that burned with a light Quinn's eyes kept insisting was the wrong colour."
4"Every instinct from eighteen years of service told her the same thing: this was a crime scene waiting to be catalogued, a network waiting to be mapped, and the …"
5"Every other instinct — the older kind, the kind that had started whispering the night Morris died and never stopped — told her that the rules she lived by ended…"
6"Three years of files that contradicted themselves, of witnesses who changed their stories overnight, of a partner's death wrapped in a silence no warrant had ev…"
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags8
uselessAdditionCount2
matches
0"Herrera called, his voice bouncing off brick,"
1"he called, his voice strange and flat in the vaulted dark"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags5
fancyCount1
fancyTags
0"he shouted (shout)"
dialogueSentences22
tagDensity0.227
leniency0.455
rawRatio0.2
effectiveRatio0.091
82.1531%