Run: 2026-02-17-01KHMQE6P0D3S0S27V13GZ2Y8F

Run Details

Duration:
6.9s
Cost:
$0.003481
Provider:
Google AI Studio

Model input

System
You are an expert novelist with a gift for vivid, immersive prose. You write in tight third-person limited point of view with a strong narrative voice. Your prose is clean, precise, and engaging — you favor strong verbs, concrete details, and natural-sounding dialogue. You will be given a story bible (codex) containing canonical details about characters, locations, items, and lore. Use these details to ground your writing in the established world. Stay consistent with the codex. Write only the prose of the scene. Do not include titles, chapter headings, markdown formatting, or any commentary before or after the scene.
User/Human
<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> 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.

Model response

AI
The downpour had turned Great Windmill Street into a slick black mirror, reflecting the stuttering neon of *The Raven’s Nest*. Harlow Quinn squinted, the rain lashing against her face with a brutal, cold efficiency. She pushed a damp strand of closely cropped salt-and-pepper hair from her eyes, the sharp jaw of her face set in a grim line. Her worn leather watch on her left wrist read 2:17 AM. Too late for anything good. She’d been watching *The Raven’s Nest* for three hours, the distinctive green neon sign a beacon of suspicion in the Soho night. Tomás Herrera had slipped out barely a minute ago, a silhouette against the garish light, disappearing east down the street. Quinn took off after him, her thirty-one years of military precision in every stride. Tomás was quick, his short curly dark brown hair plastered to his head, his olive skin gleaming under the streetlights. He moved with a practiced ease through the narrow, twisting lanes of Soho, each turn taking him deeper into the labyrinthine heart of London. Quinn kept pace, her gaze locked on the Saint Christopher medallion that bounced against his back, a small, silver target in the oppressive night. He was going somewhere in a hurry, not just home. He cut down Rupert Street, then veered sharply into Greek Street, the rhythmic slap of their shoes on the wet pavement the only sound save for the drumming rain. Quinn’s breath hitched, a stitch forming in her side, but she pressed on, the memory of DS Morris a cold, hard knot in her gut. She’d lost Morris, lost him in a way she still couldn’t explain, three years ago. This clique, these people hovering in the shadowed edges of the city, they were connected. She knew it. Tomás glanced over his shoulder, his warm brown eyes wide with surprise and a flicker of something close to recognition. He sped up, a renewed urgency in his stride. He must have known she was there, had been running her. The realization tightened Quinn’s jaw, a fresh burst of adrenaline flooding her system. She accelerated, closing the distance. They burst out onto Charing Cross Road, the traffic a blurry stream of red and white lights. Tomás risked a direct path, darting between two taxis, a blare of horns in his wake. Quinn didn’t hesitate, slipping through the same gap with an almost surgical precision. He was heading for Tottenham Court Road, towards Camden. And Quinn knew what that meant. Camden… the Veil Market. She'd been hearing rumors, whispers among informants about a black market that moved with the full moon, a place hidden, selling things that shouldn't exist. She’d never had concrete proof, never had a lead. Until now. Tomás ducked into an alleyway, a gaping maw between two derelict buildings. Quinn followed, her hand instinctively going to the Glock at her hip. The air grew heavy, thick with the smell of damp brick and something else, something metallic and faintly sweet. This wasn’t just an alley. It felt… older, deeper. The alley opened into a small, grimy courtyard, overlooked by blackened windows. At the far end, a set of crumbling concrete steps descended into darkness. Tomás was already halfway down, his figure swallowed by the inky black. Quinn paused, her heart thumping against her ribs. This was territory she knew nothing about, a place the official records wouldn’t touch. Every instinct screamed at her to stop, to call for backup, to wait. But then she pictured Morris’s face, etched in her memory, and the cold logic of her mission reasserted itself. She had to know. She descended the steps, one hand on the cold, damp wall. The air grew colder, the sound of the rain fading to a distant murmur. A faint, greenish light pulsed from below, casting strange, elongated shadows. The steps ended at a rusted metal door, slightly ajar. Pushing it open, Quinn found herself in a narrow, decaying tunnel. The air was thick with dust and the metallic tang she’d noticed earlier, but now it was sharper, laced with something else, something earthy and ancient. The greenish light source was clearer now, emanating from around a bend in the tunnel. She moved cautiously, her hand never leaving the Glock. Her military bearing, honed over 18 years of decorated service, held her rigid, her senses on high alert. The tunnel opened into a vast space, a cavernous chamber where the greenish light was stronger, pulsing from bioluminescent fungi clinging to the walls and ceiling. Below her, a scene unfolded that defied explanation. It was a market, but unlike any she had ever seen. Stalls fashioned from salvaged materials were overflowing with strange, glowing objects, vials of shimmering liquids, and intricate carvings that seemed to shift and writhe in the dim light. Figures moved among the stalls, some clearly human, others… less so. She saw things that looked like shadows given form, creatures with too many limbs, and others whose eyes glowed with an unsettling inner light. This was the Veil Market. This was what Morris had been getting close to. Tomás was already down there, weaving through the throng, his Saint Christopher medallion a familiar anchor in a sea of the unknown. He was making for a stall at the far end, manned by a gaunt figure whose face was obscured by a wide-brimmed hat. Quinn hesitated at the edge of the opening, the noise of the market washing over her – a low hum of chatter, the clink of strange coins, the occasional unearthly cry. Every fiber of her being screamed caution. This was not her world, not something she was equipped for. But years of detective work, of chasing down the inexplicable, had taught her that sometimes, you had to step into the darkness to find the light. She had to go. She had to know what Tomás was doing here, what her instincts had been telling her all along. Steeling herself, she took the first step down into the market, her gaze fixed on Tomás, her hand firm on her weapon.
created_at"2026-02-17T02:39:06.451047+00:00" 2/17/2026, 2:39:06 AM
model"google/gemini-2.5-flash"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency366
moderation_latency(null)
generation_time6533
tokens_prompt914
tokens_completion1525
native_tokens_prompt852
native_tokens_completion1290
native_tokens_completion_images0
native_tokens_reasoning0
native_tokens_cached0
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"
usage0.0034806
router(null)
provider_responses
0
status200
is_byokfalse
latency366
endpoint_id"16c01e26-9b91-4d22-b487-ed35634b017d"
provider_name"Google AI Studio"
model_permaslug"google/gemini-2.5-flash"
api_type"completions"
id"gen-1771295939-mHcUOAA3mlcuJfd6CWae"
upstream_id(null)
total_cost0.0034806
cache_discount(null)
upstream_inference_cost0
provider_name"Google AI Studio"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags0
85.16% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1011
totalAiIsmAdverbs3
found
0
adverb"sharply"
count1
1
adverb"slightly"
count1
2
adverb"cautiously"
count1
highlights
0"sharply"
1"slightly"
2"cautiously"
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)
45.60% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1011
totalAiIsms11
found
0
word"beacon"
count1
1
word"gleaming"
count1
2
word"practiced ease"
count1
3
word"oppressive"
count1
4
word"rhythmic"
count1
5
word"flicker"
count1
6
word"maw"
count1
7
word"etched"
count1
8
word"pulsed"
count1
9
word"intricate"
count1
10
word"familiar"
count1
highlights
0"beacon"
1"gleaming"
2"practiced ease"
3"oppressive"
4"rhythmic"
5"flicker"
6"maw"
7"etched"
8"pulsed"
9"intricate"
10"familiar"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"air was thick with"
count1
highlights
0"The air was thick with"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells1
narrationSentences73
matches
0"e with surprise"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences73
filterMatches
0"watch"
hedgeMatches
0"seemed to"
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
maxSentenceWordsSeen30
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans2
markdownWords6
totalWords1012
ratio0.006
matches
0"The Raven’s Nest"
1"The Raven’s Nest"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions2
unquotedAttributions0
matches(empty)
95.65% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions55
wordCount1012
uniqueNames23
maxNameDensity1.09
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Great1
Windmill1
Street3
Raven2
Quinn11
Soho2
Herrera1
London1
Saint2
Christopher2
Rupert1
Greek1
Morris4
Charing1
Cross1
Road2
Tottenham1
Court1
Camden2
Veil2
Market2
Glock2
Tomás9
persons
0"Raven"
1"Quinn"
2"Herrera"
3"Saint"
4"Christopher"
5"Morris"
6"Tomás"
places
0"Windmill"
1"Street"
2"Soho"
3"London"
4"Rupert"
5"Greek"
6"Charing"
7"Cross"
8"Road"
9"Tottenham"
10"Court"
11"Camden"
12"Market"
13"Glock"
globalScore0.957
windowScore1
25.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences60
glossingSentenceCount3
matches
0"something close to recognition"
1"carvings that seemed to shift and writhe in the dim light"
2"looked like shadows given form, creatures"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1012
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences73
matches(empty)
61.97% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs19
mean53.26
std19.54
cv0.367
sampleLengths
074
156
278
387
458
546
655
752
837
958
1046
1152
1253
138
1474
1514
1645
1775
1844
86.04% Passive voice overuse
Target: ≤2% passive sentences
passiveCount4
totalSentences73
matches
0"were connected"
1"was obscured"
2"being screamed"
3"was equipped"
0.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount5
totalVerbs153
matches
0"was going"
1"was heading"
2"were overflowing"
3"was making"
4"was doing"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount1
semicolonCount0
flaggedSentences1
totalSentences73
ratio0.014
matches
0"Quinn hesitated at the edge of the opening, the noise of the market washing over her – a low hum of chatter, the clink of strange coins, the occasional unearthly cry."
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1015
adjectiveStacks1
stackExamples
0"faint, greenish light pulsed"
adverbCount25
adverbRatio0.024630541871921183
lyAdverbCount11
lyAdverbRatio0.01083743842364532
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
mean13.86
std7.64
cv0.551
sampleLengths
020
114
224
311
45
522
620
714
820
924
1024
1110
1229
1325
1415
1515
163
1720
189
1911
2013
215
2217
2316
2413
259
266
271
283
2925
309
312
3212
3312
3419
355
362
372
3812
3913
4012
418
4214
4313
4419
454
4611
4714
4811
4910
47.49% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats7
diversityRatio0.3424657534246575
totalSentences73
uniqueOpeners25
49.02% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences68
matches
0"Too late for anything good."
ratio0.015
78.82% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount24
totalSentences68
matches
0"She pushed a damp strand"
1"Her worn leather watch on"
2"She’d been watching *The Raven’s"
3"He moved with a practiced"
4"He was going somewhere in"
5"He cut down Rupert Street,"
6"She’d lost Morris, lost him"
7"She knew it."
8"He sped up, a renewed"
9"He must have known she"
10"She accelerated, closing the distance."
11"They burst out onto Charing"
12"He was heading for Tottenham"
13"She'd been hearing rumors, whispers"
14"She’d never had concrete proof,"
15"She had to know."
16"She descended the steps, one"
17"She moved cautiously, her hand"
18"Her military bearing, honed over"
19"It was a market, but"
ratio0.353
18.82% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount60
totalSentences68
matches
0"The downpour had turned Great"
1"Harlow Quinn squinted, the rain"
2"She pushed a damp strand"
3"Her worn leather watch on"
4"She’d been watching *The Raven’s"
5"Tomás Herrera had slipped out"
6"Quinn took off after him,"
7"Tomás was quick, his short"
8"He moved with a practiced"
9"Quinn kept pace, her gaze"
10"He was going somewhere in"
11"He cut down Rupert Street,"
12"Quinn’s breath hitched, a stitch"
13"She’d lost Morris, lost him"
14"This clique, these people hovering"
15"She knew it."
16"Tomás glanced over his shoulder,"
17"He sped up, a renewed"
18"He must have known she"
19"The realization tightened Quinn’s jaw,"
ratio0.882
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences68
matches(empty)
ratio0
85.71% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences50
technicalSentenceCount4
matches
0"Quinn kept pace, her gaze locked on the Saint Christopher medallion that bounced against his back, a small, silver target in the oppressive night."
1"She'd been hearing rumors, whispers among informants about a black market that moved with the full moon, a place hidden, selling things that shouldn't exist."
2"Stalls fashioned from salvaged materials were overflowing with strange, glowing objects, vials of shimmering liquids, and intricate carvings that seemed to shif…"
3"She saw things that looked like shadows given form, creatures with too many limbs, and others whose eyes glowed with an unsettling inner light."
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
79.1096%