Run: 2026-03-11-01KKFFAQR492DVH495T871M9HR

Run Details

Duration:
32.6s
Cost:
$0.000000
Provider:
Stealth

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 in sheets, turning the neon signs of Soho into blurry watercolour smears. Harlow Quinn’s lungs burned, each breath a ragged pull of damp, cold air. Ahead, the suspect—a wiry figure in a dark hoodie—darted through the throng of late-night revellers, shoving past umbrellas and brollies. Quinn’s worn leather watch strap was slick against her wrist. Eighteen years on the force, and the chase still got her blood up. This one was different, though. This wasn’t some pickpocket. The files on her desk, the whispers about DS Morris three years ago, they all pointed to threads she couldn’t quite see. Threads this runner, Herrera, might help her pull. He’d bolted the second she’d shown her warrant card near the green neon glow of The Raven’s Nest. A mistake on his part. Now she was just another shape in the downpour, her salt-and-pepper hair plastered to her skull, her sharp jaw set. He cut left down an alley reeking of bins and stale beer. A dead end? No. He vaulted a rusted fence with a grunt of effort. Quinn followed, the metal biting into her palms. He was heading for the Camden border, abandoning the bright chaos of the West End for quieter, darker streets. She lost sight of him for a block. Then she caught the flash of his medallion under a streetlamp. Saint Christopher. The file said Tomás Herrera. Former paramedic. Now a ghost who patched up people who didn’t go to hospitals. He was fast, but she was relentless. The rain drummed a frantic rhythm on the pavement. He rounded a corner near the looming arches of an old viaduct. Quinn rounded it a second later. He was gone. The street was empty, a canyon of wet brick and closed shopfronts. No flicker of movement in doorways. Just the hiss of the rain and the distant growl of a late-night bus. Quinn slowed, her hand resting on the butt of her holstered sidearm. Her breath plumed in the frigid air. She scanned the shadows. A drop of water fell from her eyebrow onto her cheek. A sound. A scrape, metallic and hollow. Coming from below. Her eyes dropped to the street level. A large, grated maintenance hatch, set flush with the pavement, sat ajar. Steam, or mist, curled from the gap. Herrera’s escape route. The Underground. But not the Tube. She knew the maps of the city’s transit system by heart, and this wasn’t on them. She knelt, ignoring the cold water soaking through her trousers. The hatch was heavy. Below, a rusted iron ladder descended into a dim, orange-lit gloom. The air that wafted up smelled of ozone, wet earth, and something else. Incense and old coins. It was a smell that didn’t belong in a London sewer. It was the smell from the cold case files, the ones with Morris’s name on them. Quinn’s fingers tightened on the ladder. Following a suspect into a known drug den was one thing. This was a hole in the map. Unsanctioned. Unknowable. Her training screamed about tactical disadvantages, about potential traps. But the image of her partner’s face in the morgue photo, the one they’d never properly explained, flashed behind her eyes. Morris had chased a thread, too. He’d followed it somewhere. And he hadn’t come back. She pulled her flashlight, its beam cutting a sharp white cone through the darkness below. She went down. The ladder ended in a vast, vaulted space. An abandoned Tube station, by the look of it. The tiled walls were grimy, the old station nameplate obliterated by grime. But it wasn’t abandoned. Stalls and carts lined the disused platforms, lit by strings of bare bulbs and flickering lanterns. The air buzzed with a low murmur of voices, a language that wasn’t quite English, or any other single tongue she recognised. People—some looking perfectly normal, others… less so—moved between the stalls. One vendor was selling what looked like bottled lightning in mason jars. Another had a table of books that rustled their own pages. The Veil Market. The name surfaced from a half-remembered briefing, a rumour whispered in the corridors of the Met’s odder departments. A supernatural black market. The bone token requirement. Herrera had vanished into this. Quinn stepped off the ladder, her boots crunching on something that might have been gravel or might have been old teeth. She pulled her warrant card from her pocket, holding it up. It felt flimsy here, a paper shield in a place that operated on older laws. The murmur around her dipped. Eyes turned her way. Not all of them were human. A stallkeeper with scales instead of skin watched her, unblinking. A tall, gaunt figure in a moth-eaten coat sniffed the air in her direction. She spotted him. Herrera was at a stall twenty yards down the platform, talking urgently to a hunched figure behind a cart of shimmering liquids. He hadn’t seen her yet. Quinn moved, keeping her gait steady, projecting a confidence she didn’t feel. She pushed past a man whose shadow moved independently on the wall. “Herrera!” Her voice cut through the low din. He snapped his head around. Warm brown eyes wide with panic. He wasn’t a hardened criminal; he was a scared man who knew things. He shoved the stallkeeper’s cart, sending vials shattering on the platform in a burst of coloured light and acrid smoke. People shouted. The market crowd, initially curious, now erupted into chaos. Herrera bolted, scrambling over a fallen cart and disappearing down a darkened service tunnel at the far end of the platform. Quinn pursued, but the gap was closing. The crowd was a barrier of bodies and strange merchandise. She shouldered through, her focus narrowed to the tunnel entrance. The sounds of the market faded behind her, replaced by the drip of water and her own pounding heart. The tunnel was pitch black beyond the spill of light from the platform. She skidded to a halt at the threshold. Her flashlight beam stabbed into the void, showing only damp concrete and rusted rails vanishing into a curve. He could be waiting around that bend. Or he could be miles away in a labyrinth only he knew. This was the line. The point of no return. Back there was rain-soaked London, a world she understood. Down this tunnel was the answer to Morris’s death, maybe. Or it was just a quicker way to join him. Quinn took a breath, the strange, charged air of the market filling her lungs. She checked her weapon, the action a familiar, grounding ritual. Then she stepped into the darkness, the light from the Veil Market shrinking behind her until it was just a single, distant green spark, like the neon sign of a bar she’d never be able to find again.
created_at"2026-03-11T22:12:28.561Z" 3/11/2026, 10:12:28 PM
model"openrouter/hunter-alpha"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency867
moderation_latency(null)
generation_time32525
tokens_prompt1140
tokens_completion2005
native_tokens_prompt1005
native_tokens_completion1725
native_tokens_completion_images(null)
native_tokens_reasoning318
native_tokens_cached960
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0
router(null)
provider_responses(null)
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer(null)
api_type"completions"
id"gen-1773267148-Lo5MhUcLRq2GDmuU6oj0"
upstream_id"gen-1773267148-Lo5MhUcLRq2GDmuU6oj0"
total_cost0
cache_discount(null)
upstream_inference_cost0
provider_name"Stealth"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags0
95.61% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1139
totalAiIsmAdverbs1
found
0
adverb"perfectly"
count1
highlights
0"perfectly"
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)
60.49% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1139
totalAiIsms9
found
0
word"looming"
count1
1
word"flicker"
count1
2
word"scanned"
count1
3
word"eyebrow"
count1
4
word"gloom"
count1
5
word"potential"
count1
6
word"pounding"
count1
7
word"charged"
count1
8
word"familiar"
count1
highlights
0"looming"
1"flicker"
2"scanned"
3"eyebrow"
4"gloom"
5"potential"
6"pounding"
7"charged"
8"familiar"
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
emotionTells1
narrationSentences118
matches
0"e with panic"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences118
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences119
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen38
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1135
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions2
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions39
wordCount1134
uniqueNames18
maxNameDensity0.88
worstName"Quinn"
maxWindowNameDensity1.5
worstWindowName"Quinn"
discoveredNames
Soho1
Quinn10
Morris4
Herrera6
Raven1
Nest1
Camden1
West1
End1
Christopher1
Tomás1
Underground1
Tube2
London2
English1
Veil2
Market2
Met1
persons
0"Quinn"
1"Morris"
2"Herrera"
3"Raven"
4"Christopher"
5"Tomás"
6"Market"
7"Met"
places
0"Soho"
1"West"
2"End"
3"London"
4"Veil"
globalScore1
windowScore1
56.25% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences80
glossingSentenceCount3
matches
0"quite see"
1"quite English, or any other single tongue she recognised"
2"looked like bottled lightning in mason ja"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1135
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences119
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs19
mean59.74
std30.39
cv0.509
sampleLengths
0111
196
274
33
466
561
669
771
818
9104
1034
1186
1254
131
1451
1532
1659
1783
1862
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences118
matches
0"was gone"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs172
matches
0"was heading"
1"was selling"
46.82% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount4
semicolonCount1
flaggedSentences4
totalSentences119
ratio0.034
matches
0"Ahead, the suspect—a wiry figure in a dark hoodie—darted through the throng of late-night revellers, shoving past umbrellas and brollies."
1"People—some looking perfectly normal, others…"
2"less so—moved between the stalls."
3"He wasn’t a hardened criminal; he was a scared man who knew things."
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1146
adjectiveStacks1
stackExamples
0"single, distant green spark,"
adverbCount28
adverbRatio0.02443280977312391
lyAdverbCount7
lyAdverbRatio0.006108202443280977
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences119
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences119
mean9.54
std6.1
cv0.639
sampleLengths
016
113
220
310
413
55
64
722
88
918
105
1120
1212
133
141
1510
168
1719
188
1911
202
215
222
2312
247
259
2612
276
283
2912
306
3114
3212
337
344
3511
362
375
383
397
4012
417
423
432
444
4516
4610
474
4811
4913
49.02% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats10
diversityRatio0.3445378151260504
totalSentences119
uniqueOpeners41
90.91% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences110
matches
0"Then she caught the flash"
1"Just the hiss of the"
2"Then she stepped into the"
ratio0.027
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount33
totalSentences110
matches
0"He’d bolted the second she’d"
1"He cut left down an"
2"He vaulted a rusted fence"
3"He was heading for the"
4"She lost sight of him"
5"He was fast, but she"
6"He rounded a corner near"
7"He was gone."
8"Her breath plumed in the"
9"She scanned the shadows."
10"Her eyes dropped to the"
11"She knew the maps of"
12"She knelt, ignoring the cold"
13"It was a smell that"
14"It was the smell from"
15"Her training screamed about tactical"
16"He’d followed it somewhere."
17"She pulled her flashlight, its"
18"She went down."
19"She pulled her warrant card"
ratio0.3
64.55% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount87
totalSentences110
matches
0"The rain came down in"
1"Harlow Quinn’s lungs burned, each"
2"Quinn’s worn leather watch strap"
3"This one was different, though."
4"This wasn’t some pickpocket."
5"The files on her desk,"
6"He’d bolted the second she’d"
7"A mistake on his part."
8"He cut left down an"
9"A dead end?"
10"He vaulted a rusted fence"
11"Quinn followed, the metal biting"
12"He was heading for the"
13"She lost sight of him"
14"The file said Tomás Herrera."
15"He was fast, but she"
16"The rain drummed a frantic"
17"He rounded a corner near"
18"Quinn rounded it a second"
19"He was gone."
ratio0.791
90.91% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount2
totalSentences110
matches
0"Now she was just another"
1"Now a ghost who patched"
ratio0.018
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences57
technicalSentenceCount3
matches
0"The air buzzed with a low murmur of voices, a language that wasn’t quite English, or any other single tongue she recognised."
1"Quinn stepped off the ladder, her boots crunching on something that might have been gravel or might have been old teeth."
2"He shoved the stallkeeper’s cart, sending vials shattering on the platform in a burst of coloured light and acrid smoke."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags0
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
91.6185%