Run: 2026-03-03-01KJTZ8M4VM130ZQG3BQ70KND1

Run Details

Duration:
7.8s
Cost:
$0.002723
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 rain in Soho did not wash the city clean; it only turned the grit into a slick, obsidian lacquer that clung to the soles of Harlow Quinn’s boots. She moved with the silent, coiled efficiency of a predator, her salt-and-pepper hair plastered to her skull. She kept her eyes fixed on the man fleeing ahead of her. He was quick, weaving through the late-night foot traffic like a ghost, his olive skin pale beneath the stuttering hum of streetlights. Tomás Herrera. She remembered his face from the files she had scrubbed clean of official badges three years ago, back when the brass had tried to bury the truth about DS Morris. He darted across the wet asphalt of a narrow alley, his foot catching on a piece of debris before he recovered with an agility that spoke of long nights spent running toward disaster. He wasn’t just a medic; he was a gatekeeper, and he was heading toward something that didn't appear on any of the Metropolitan Police’s city maps. Quinn picked up her pace, her sharp jaw set against the bite of the wind. She checked her leather watch; it was past midnight. The air grew heavy, smelling of ozone and something sharper, like spoiled milk and burnt copper. Herrera skidded to a halt in front of a rusted iron gate tucked behind a derelict warehouse near the Camden sprawl, a place where the city’s pulse seemed to skip a beat. He looked back, his warm brown eyes wide, flicking toward the Saint Christopher medallion that caught the streetlamp’s sickly yellow glow. He reached into his coat, producing a small, jagged object—a sliver of bone, bleached white and unnaturally heavy—and pressed it into a seamless indent in the rusted metal. The gate didn't creak. It groaned, a low-frequency vibration that rattled Quinn’s teeth, and folded inward like a closing eye. Quinn broke cover, her lungs burning, boots splashing through a stagnant puddle. "Herrera! Stop where you are!" He didn't run away. He stepped backward into the gaping darkness of the disused Tube station entrance, watching her with a mixture of terror and pity. Quinn reached the threshold, her hand resting on the weight of her service weapon. Below, the air was different. The damp chill of the London rain vanished, replaced by a humid, cloying heat that smelled of wet earth and ancient, moldering paper. She descended the stairs, each step heavy with the intent of a woman who had spent months chasing shadows. As she reached the bottom, the world opened up. The abandoned platform had been transformed. It was no longer a tomb of concrete and rats; it was the Veil Market. Lanterns fueled by an unknown, violet flame hung from the arched ceilings, casting distorted silhouettes against the tunnels. Strange, shimmering stalls were packed into the hollowed-out subway cars, overflowing with jars of shifting liquid, bundles of dried herbs that pulsed with a rhythmic light, and artifacts that looked as if they had been unearthed from the bottom of a midnight sea. Creatures she couldn't name—hunched, spindly things draped in heavy furs and cloaks—haggled in a language that sounded like grinding glass and clicking insects. Quinn froze, her hand hovering near her holster. She was a detective of the Metropolitan Police, a woman of science and law, and yet, the sheer scale of the impossibility before her threatened to unravel her composure. She had seen the aftermath of the case that killed Morris—the shredded metal, the cauterized wounds that no standard weapon could inflict—but she had never seen the source. She spotted Herrera near an old ticket kiosk, his arm scarred from a knife attack she had seen in previous surveillance reports. He was talking to a vendor who held a collection of floating glass spheres. Caution, deep and ingrained, fought with the investigator’s need for the truth. If she crossed this threshold, she stepped out of the world of forensic reports and court testimony into something far older and more dangerous. If she were seen here, she couldn't call for backup. The streets above were the only jurisdiction she knew. Down here, she was an intruder, a foreign object in a delicate, shifting ecosystem. Her mind traced the path back to the exit. She could turn around, leave the bone token behind, and pretend the entrance was nothing more than an architectural anomaly. But then, she thought of Morris. She thought of the way the case files had been sanitized, the way the sergeant’s body had been returned to her with reports that defied the autopsy’s physical reality. She took a step forward into the crowd. The atmosphere intensified. The eyes of the vendors—some too wide, some vertically slit, some merely reflecting the violet light—turned toward her. She felt like an unlit match in a room filled with gas. Herrera had vanished into a tangle of merchants hawking vials of what looked like captured starlight, but his trajectory was clear. He was moving deeper into the tunnel, toward the belly of the station where the shadows were densest. She pushed past a stall display offering leering, carved masks that seemed to follow her with their wooden eyes. Her progress was slow. The crowd here didn't move like people; they flowed like ink in water, obstructing her path without ever touching her. "Detective," a voice hissed from the dark, cold and resonant. Quinn turned, her hand tightening on her weapon. A figure stood in the alcove of a brick pillar, its face hidden under the deep hood of a tattered coat. The stench of deep, stagnant water clung to it. "You’re wandering in a place that has no use for your badge," the figure continued. Quinn didn't retreat. She stood her ground, her military carriage rigid. "I’m looking for a man. Herrera." "The medic?" The creature let out a dry, rattling laugh. "He is one of us, however much he tries to pretend he isn't. He trades in flesh. You trade in paper. Why come to the Market to settle a grudge that belongs to the dead?" Quinn felt a cold prickle of realization. They knew about Morris. They knew why she was here. "I don't leave investigations unfinished," she said, her voice steady despite the hammer of her heart. "Some things are not investigations, Detective. They are warnings." The figure stepped closer, the purple light glinting off a jagged, obsidian blade at its hip. Quinn looked past the creature. Herrera had reached the far end of the platform, where a series of iron doors led into the deeper, uncharted tunnels of the London Underground. He paused, looking back one last time—not at her, but at the tunnel behind her. He seemed to be measuring whether his own escape was worth the cost of the disruption she had brought with her. The moral weight of her decision sat heavily in her chest. If she followed him, she was walking into a trap set by forces she didn't understand. If she stayed, she might learn the secrets of this place, even if it meant risking everything that remained of her life above. She looked at her worn leather watch. Time had stopped entirely. The silence of the station felt expectant, waiting to see if she would commit to the chase or turn back and flee into the safety of the rain. Quinn took another step forward, her boot echoing on the platform like a gunshot. The creature in the alcove stepped back into the gloom, a gesture that felt less like a retreat and more like an opening. She kept her eyes on Herrera, her focus narrowing until the entire world of the Veil Market dissolved into a blur of violet light and static. She wasn't a detective anymore; she was a witness. And the deeper she went, the less certain she was that she would ever return to the surface the same woman who had descended the stairs.
created_at"2026-03-03T23:06:53.48Z" 3/3/2026, 11:06:53 PM
model"google/gemini-3.1-flash-lite-preview-20260303"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency500
moderation_latency(null)
generation_time7723
tokens_prompt914
tokens_completion1987
native_tokens_prompt852
native_tokens_completion1673
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"
usage0.0027225
router(null)
provider_responses
0
endpoint_id"e004ce39-eb0c-4474-93d5-55072e725970"
is_byokfalse
latency500
model_permaslug"google/gemini-3.1-flash-lite-preview-20260303"
provider_name"Google AI Studio"
status200
api_type"completions"
id"gen-1772579213-WfGnJMyTGsCclyvBTI0S"
upstream_id(null)
total_cost0.0027225
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
totalTags5
adverbTagCount0
adverbTags(empty)
dialogueSentences8
tagDensity0.625
leniency1
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1332
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)
43.69% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1332
totalAiIsms15
found
0
word"predator"
count1
1
word"pulse"
count1
2
word"weight"
count2
3
word"chill"
count1
4
word"pulsed"
count1
5
word"rhythmic"
count1
6
word"unravel"
count1
7
word"aftermath"
count1
8
word"standard"
count1
9
word"traced"
count1
10
word"glinting"
count1
11
word"silence"
count1
12
word"echoing"
count1
13
word"gloom"
count1
highlights
0"predator"
1"pulse"
2"weight"
3"chill"
4"pulsed"
5"rhythmic"
6"unravel"
7"aftermath"
8"standard"
9"traced"
10"glinting"
11"silence"
12"echoing"
13"gloom"
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
narrationSentences80
matches(empty)
35.71% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount2
hedgeCount4
narrationSentences80
filterMatches
0"watch"
hedgeMatches
0"tried to"
1"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences83
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen44
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1323
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions5
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions38
wordCount1248
uniqueNames15
maxNameDensity0.88
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Soho1
Harlow1
Quinn11
Herrera6
Morris4
Metropolitan2
Police2
Camden1
Saint1
Christopher1
Tube1
London2
Veil2
Market2
Underground1
persons
0"Harlow"
1"Quinn"
2"Herrera"
3"Morris"
4"Police"
5"Saint"
6"Christopher"
7"Market"
places
0"Soho"
1"London"
globalScore1
windowScore1
5.07% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences69
glossingSentenceCount4
matches
0"sounded like grinding glass and clicking i"
1"felt like an unlit match in a room fill"
2"looked like captured starlight, but his t"
3"masks that seemed to follow her with their wooden eyes"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords0.756
wordCount1323
matches
0"not at her, but at the tunnel behind her"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences83
matches
0"was that she"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs31
mean42.68
std22.19
cv0.52
sampleLengths
080
132
259
372
449
520
617
726
861
930
1084
1165
1236
1369
1464
158
1672
1743
1810
1938
2015
2117
2245
2317
2416
2525
2666
2750
2839
2937
3061
87.72% Passive voice overuse
Target: ≤2% passive sentences
passiveCount4
totalSentences80
matches
0"been transformed"
1"were packed"
2"been unearthed"
3"were seen"
4"been sanitized"
5"been returned"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs206
matches
0"was heading"
1"was talking"
2"was walking"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount9
semicolonCount6
flaggedSentences11
totalSentences83
ratio0.133
matches
0"The rain in Soho did not wash the city clean; it only turned the grit into a slick, obsidian lacquer that clung to the soles of Harlow Quinn’s boots."
1"He wasn’t just a medic; he was a gatekeeper, and he was heading toward something that didn't appear on any of the Metropolitan Police’s city maps."
2"She checked her leather watch; it was past midnight."
3"He reached into his coat, producing a small, jagged object—a sliver of bone, bleached white and unnaturally heavy—and pressed it into a seamless indent in the rusted metal."
4"It was no longer a tomb of concrete and rats; it was the Veil Market."
5"Creatures she couldn't name—hunched, spindly things draped in heavy furs and cloaks—haggled in a language that sounded like grinding glass and clicking insects."
6"She had seen the aftermath of the case that killed Morris—the shredded metal, the cauterized wounds that no standard weapon could inflict—but she had never seen the source."
7"The eyes of the vendors—some too wide, some vertically slit, some merely reflecting the violet light—turned toward her."
8"The crowd here didn't move like people; they flowed like ink in water, obstructing her path without ever touching her."
9"He paused, looking back one last time—not at her, but at the tunnel behind her."
10"She wasn't a detective anymore; she was a witness."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1262
adjectiveStacks0
stackExamples(empty)
adverbCount29
adverbRatio0.022979397781299524
lyAdverbCount11
lyAdverbRatio0.008716323296354992
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences83
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences83
mean15.94
std8.99
cv0.564
sampleLengths
029
117
212
322
42
530
633
726
815
99
1016
1132
1221
1328
144
1516
1612
175
184
1922
2014
215
2223
2319
249
256
2615
2718
2843
2923
308
3129
3228
3322
3414
3512
3624
3710
389
3914
409
4120
426
4329
448
453
4618
4712
4821
4918
34.54% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats13
diversityRatio0.30120481927710846
totalSentences83
uniqueOpeners25
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences79
matches(empty)
ratio0
42.78% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount35
totalSentences79
matches
0"She moved with the silent,"
1"She kept her eyes fixed"
2"He was quick, weaving through"
3"She remembered his face from"
4"He darted across the wet"
5"He wasn’t just a medic;"
6"She checked her leather watch;"
7"He looked back, his warm"
8"He reached into his coat,"
9"It groaned, a low-frequency vibration"
10"He didn't run away."
11"He stepped backward into the"
12"She descended the stairs, each"
13"It was no longer a"
14"She was a detective of"
15"She had seen the aftermath"
16"She spotted Herrera near an"
17"He was talking to a"
18"Her mind traced the path"
19"She could turn around, leave"
ratio0.443
29.62% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount68
totalSentences79
matches
0"The rain in Soho did"
1"She moved with the silent,"
2"She kept her eyes fixed"
3"He was quick, weaving through"
4"She remembered his face from"
5"He darted across the wet"
6"He wasn’t just a medic;"
7"Quinn picked up her pace,"
8"She checked her leather watch;"
9"The air grew heavy, smelling"
10"Herrera skidded to a halt"
11"He looked back, his warm"
12"He reached into his coat,"
13"The gate didn't creak."
14"It groaned, a low-frequency vibration"
15"Quinn broke cover, her lungs"
16"He didn't run away."
17"He stepped backward into the"
18"Quinn reached the threshold, her"
19"The damp chill of the"
ratio0.861
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount4
totalSentences79
matches
0"If she crossed this threshold,"
1"If she were seen here,"
2"If she followed him, she"
3"If she stayed, she might"
ratio0.051
0.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences50
technicalSentenceCount10
matches
0"He darted across the wet asphalt of a narrow alley, his foot catching on a piece of debris before he recovered with an agility that spoke of long nights spent r…"
1"He wasn’t just a medic; he was a gatekeeper, and he was heading toward something that didn't appear on any of the Metropolitan Police’s city maps."
2"He looked back, his warm brown eyes wide, flicking toward the Saint Christopher medallion that caught the streetlamp’s sickly yellow glow."
3"It groaned, a low-frequency vibration that rattled Quinn’s teeth, and folded inward like a closing eye."
4"Quinn broke cover, her lungs burning, boots splashing through a stagnant puddle."
5"The damp chill of the London rain vanished, replaced by a humid, cloying heat that smelled of wet earth and ancient, moldering paper."
6"Strange, shimmering stalls were packed into the hollowed-out subway cars, overflowing with jars of shifting liquid, bundles of dried herbs that pulsed with a rh…"
7"She thought of the way the case files had been sanitized, the way the sergeant’s body had been returned to her with reports that defied the autopsy’s physical r…"
8"She pushed past a stall display offering leering, carved masks that seemed to follow her with their wooden eyes."
9"And the deeper she went, the less certain she was that she would ever return to the surface the same woman who had descended the stairs."
25.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags5
uselessAdditionCount1
matches
0"she said, her voice steady despite the hammer of her heart"
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags3
fancyCount2
fancyTags
0"a voice hissed (hiss)"
1"the figure continued (continue)"
dialogueSentences8
tagDensity0.375
leniency0.75
rawRatio0.667
effectiveRatio0.5
70.1381%