Run: 2026-02-19-01KHTXECGMFB8VPHWV5JP7VKZS

Run Details

Duration:
36.9s
Cost:
$0.033833
Provider:
Google AI Studio

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 fell in sheets, blurring the neon signs of Soho into watercolour streaks across the slick tarmac. Detective Harlow Quinn’s boots slapped a punishing rhythm against the pavement, each stride measured, each breath a controlled plume of white in the cold night air. Ahead, a fleeting shadow vaulted a stack of overflowing bins. Tomás Herrera. He was fast, a desperate, fluid motion against the city's static backdrop. Quinn rounded the corner, her trench coat a heavy, sodden weight on her shoulders. She ignored the burn in her lungs, the stitch threatening her side. Her focus narrowed to the man’s dark, curly hair, plastered to his head, and the glint of metal at his neck—a small medallion catching the jaundiced glow of a streetlamp. He glanced back, his face a pale oval of alarm, and pushed himself harder, weaving through a throng of late-night revellers spilling from a pub. He moved with the frantic energy of cornered prey. Quinn maintained her pace, a predator’s economy of motion. She had been on his tail since he bolted from a back table at The Raven's Nest, instinct screaming that he was more than just a witness. They tore through the warren of streets, a frantic ballet of hunter and hunted. Herrera sent a newspaper stand crashing in his wake; Quinn sidestepped the cascade of glossy magazines without breaking her stride. He risked a blind dash across Shaftesbury Avenue, a horn blaring in protest as a taxi screeched to a halt inches from him. Quinn flowed through the traffic behind him, her hand instinctively hovering near the small of her back. She saw the white flash of a scar on his forearm as he used a lamppost to swing into a narrow alley. She followed. The passage stank of stale beer and decay. It was a gut of brick and grimy metal, a shortcut she knew led towards Camden. The sounds of the city muted, replaced by the frantic echo of their footfalls and the steady drum of rain on corrugated iron overhangs. Herrera was losing steam. His movements grew ragged, his breathing a harsh, tearing sound that reached her even over her own. Quinn closed the distance. Ten metres. Five. He burst from the alley onto a quieter street, a row of shuttered market stalls lining the pavement. He risked another look over his shoulder, his warm brown eyes wide with a terror that seemed too large for a simple off-the-books medic. He skidded on the wet tiles, catching himself against the graffiti-covered shutter of a shop, then ducked behind it. Quinn drew her service weapon, the cool metal a familiar comfort in her hand. She approached the corner, body low, using the reflection in a puddle to track his position. He wasn’t waiting in ambush. He was fumbling with something on the wall. A rusted maintenance hatch, barely visible in the gloom. It squealed open. He scrambled through the dark opening and vanished. Quinn reached the hatch a moment later. A wave of cool, subterranean air, thick with the scent of damp earth and ozone, washed over her. Below, a set of iron rungs descended into blackness. She holstered her weapon, the click echoing in the sudden quiet, and began her descent. The iron was cold and slick beneath her gloves. The world above disappeared, the sound of the rain fading to a distant whisper. Her feet found solid ground on the tiled platform of a derelict Tube station. Ghostly advertisements from a forgotten era peeled from the curved walls. The air was heavy, stagnant. Water dripped from the ceiling in a maddeningly irregular rhythm, each drop a percussive note in the oppressive silence. Her footfalls were loud on the grimy platform. She followed the tunnel, her senses on high alert. The only light came from strange sources ahead—not the steady, sterile light of electricity, but the flickering, erratic glow of open flames and something else, something that pulsed with shades of violet and veridian. The air grew thick with a bazaar of alien smells: cinnamon and sulphur, night-blooming flowers and something metallic, like hot copper. And voices. A low, continuous hum of bartering and conversation, but the languages were a discordant symphony she couldn't parse. Quinn slowed her approach, hugging the damp, curved wall. She peered around a broad support pillar. Before her lay an impossible scene. The station platform opened into a vast cavern teeming with life. Stalls cobbled together from scrap wood and glowing crystal were piled high with goods she couldn't identify. Jars containing swirling nebulae of light. Plants with writhing, sentient-looking vines. Weapons that seemed to drink the very light from the air. The crowd was a menagerie of beings that scrambled her perception; people with skin like polished obsidian, others with eyes that held entire constellations, and some shrouded in shadows that shifted and coiled with a life of their own. The Veil Market. The name surfaced from a whisper on an informant's lips, a place she had dismissed as urban legend. She saw Herrera. He was near the entrance, speaking to a hulking figure whose form seemed to ripple at the edges. Herrera held up his hand. In his palm rested a small, intricately carved piece of bone, pale and yellowed. It pulsed with a soft inner light. The guard nodded, its massive form stepping aside. Herrera slipped into the throng and was immediately swallowed by it. Quinn flattened herself back against the pillar, her heart a heavy, thudding drum against her ribs. This was it. This was the same brand of wrongness that had clung to the scene of DS Morris’s death. The same inexplicable chill, the same sense of a world operating on rules she had never been taught. The official report read 'gas leak explosion'. A neat, tidy lie. She remembered the symbol scrawled on the floor, a symbol that warped the light around it. She remembered the way Morris’s shadow had stretched and torn away from him an instant before the blast. Her every instinct, eighteen years of decorated service, screamed at her to retreat. Call for backup. Set up a perimeter. Wait. But backup wouldn't understand. They would see an empty Tube station, just as they had seen a simple explosion three years ago. She was alone with this. The answer to what happened to Morris was in there. She felt it with a bone-deep certainty. Her partner’s face swam in her memory—a wry smile, a weary sigh. She had to know. She checked her weapon. Slipped a spare magazine into her coat pocket. The worn leather of the watch on her wrist felt tight and grounding. She was a detective. This was a crime scene. Herrera was her suspect. The rest was just background noise. She took a deep, steadying breath, the strange, spiced air a shock to her lungs, and pushed off from the pillar. She walked towards the light.
created_at"2026-02-19T12:19:23.29Z" 2/19/2026, 12:19:23 PM
model"google/gemini-2.5-pro"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency3007
moderation_latency(null)
generation_time36904
tokens_prompt1140
tokens_completion2770
native_tokens_prompt1042
native_tokens_completion3253
native_tokens_completion_images0
native_tokens_reasoning1806
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"
usage0.0338325
router(null)
provider_responses
0
endpoint_id"b261d15b-95ce-4c8c-8bce-00eb0dc1ff77"
is_byokfalse
latency3007
model_permaslug"google/gemini-2.5-pro"
provider_name"Google AI Studio"
status200
api_type"completions"
id"gen-1771503563-JZokhqxqOvZEvgcgZolE"
upstream_id(null)
total_cost0.0338325
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
totalTags1
adverbTagCount0
adverbTags(empty)
dialogueSentences0
tagDensity1
leniency1
rawRatio0
effectiveRatio0
95.70% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1163
totalAiIsmAdverbs1
found
0
adverb"very"
count1
highlights
0"very"
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)
14.02% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1163
totalAiIsms20
found
0
word"measured"
count1
1
word"fleeting"
count1
2
word"weight"
count1
3
word"glint"
count1
4
word"predator"
count1
5
word"echo"
count1
6
word"familiar"
count1
7
word"gloom"
count1
8
word"echoing"
count1
9
word"whisper"
count2
10
word"oppressive"
count1
11
word"silence"
count1
12
word"pulsed"
count2
13
word"symphony"
count1
14
word"crystal"
count1
15
word"hulking"
count1
16
word"chill"
count1
17
word"sense of"
count1
highlights
0"measured"
1"fleeting"
2"weight"
3"glint"
4"predator"
5"echo"
6"familiar"
7"gloom"
8"echoing"
9"whisper"
10"oppressive"
11"silence"
12"pulsed"
13"symphony"
14"crystal"
15"hulking"
16"chill"
17"sense of"
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
narrationSentences98
matches(empty)
84.55% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount4
narrationSentences98
filterMatches(empty)
hedgeMatches
0"seemed to"
1"happened to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences98
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen39
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1153
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
totalMentions31
wordCount1150
uniqueNames13
maxNameDensity0.87
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Soho1
Harlow1
Quinn10
Herrera7
Raven1
Nest1
Shaftesbury1
Avenue1
Camden1
Tube2
Veil1
Market1
Morris3
persons
0"Harlow"
1"Quinn"
2"Herrera"
3"Morris"
places
0"Soho"
1"Raven"
2"Shaftesbury"
3"Avenue"
4"Camden"
globalScore1
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences70
glossingSentenceCount1
matches
0"Weapons that seemed to drink the very light from the air"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords0.867
wordCount1153
matches
0"not the steady, sterile light of electricity, but the flickering, erratic glow of open flames"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences98
matches
0"screaming that he"
36.52% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs13
mean88.69
std24.64
cv0.278
sampleLengths
068
1126
298
376
4124
549
680
784
8132
966
1099
1181
1270
98.10% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences98
matches
0"were piled"
1"been taught"
82.35% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs170
matches
0"was losing"
1"wasn’t waiting"
2"was fumbling"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount3
semicolonCount2
flaggedSentences5
totalSentences98
ratio0.051
matches
0"Her focus narrowed to the man’s dark, curly hair, plastered to his head, and the glint of metal at his neck—a small medallion catching the jaundiced glow of a streetlamp."
1"Herrera sent a newspaper stand crashing in his wake; Quinn sidestepped the cascade of glossy magazines without breaking her stride."
2"The only light came from strange sources ahead—not the steady, sterile light of electricity, but the flickering, erratic glow of open flames and something else, something that pulsed with shades of violet and veridian."
3"The crowd was a menagerie of beings that scrambled her perception; people with skin like polished obsidian, others with eyes that held entire constellations, and some shrouded in shadows that shifted and coiled with a life of their own."
4"Her partner’s face swam in her memory—a wry smile, a weary sigh."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount969
adjectiveStacks0
stackExamples(empty)
adverbCount16
adverbRatio0.016511867905056758
lyAdverbCount8
lyAdverbRatio0.008255933952528379
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences98
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences98
mean11.77
std7.72
cv0.657
sampleLengths
018
126
210
32
412
514
612
730
825
99
109
1127
1214
1320
1423
1517
1622
172
188
1916
2024
214
2217
234
242
251
2618
2724
2819
2914
3016
315
328
339
343
358
367
3718
389
3915
409
4114
4214
4311
445
4519
468
479
4834
4921
38.44% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats14
diversityRatio0.3163265306122449
totalSentences98
uniqueOpeners31
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences92
matches(empty)
ratio0
50.43% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount39
totalSentences92
matches
0"He was fast, a desperate,"
1"She ignored the burn in"
2"Her focus narrowed to the"
3"He glanced back, his face"
4"He moved with the frantic"
5"She had been on his"
6"They tore through the warren"
7"He risked a blind dash"
8"She saw the white flash"
9"It was a gut of"
10"His movements grew ragged, his"
11"He burst from the alley"
12"He risked another look over"
13"He skidded on the wet"
14"She approached the corner, body"
15"He wasn’t waiting in ambush."
16"He was fumbling with something"
17"It squealed open."
18"He scrambled through the dark"
19"She holstered her weapon, the"
ratio0.424
14.35% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount82
totalSentences92
matches
0"The rain fell in sheets,"
1"Detective Harlow Quinn’s boots slapped"
2"He was fast, a desperate,"
3"Quinn rounded the corner, her"
4"She ignored the burn in"
5"Her focus narrowed to the"
6"He glanced back, his face"
7"He moved with the frantic"
8"Quinn maintained her pace, a"
9"She had been on his"
10"They tore through the warren"
11"Herrera sent a newspaper stand"
12"He risked a blind dash"
13"Quinn flowed through the traffic"
14"She saw the white flash"
15"The passage stank of stale"
16"It was a gut of"
17"The sounds of the city"
18"Herrera was losing steam."
19"His movements grew ragged, his"
ratio0.891
54.35% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences92
matches
0"Before her lay an impossible"
ratio0.011
85.71% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences50
technicalSentenceCount4
matches
0"His movements grew ragged, his breathing a harsh, tearing sound that reached her even over her own."
1"He risked another look over his shoulder, his warm brown eyes wide with a terror that seemed too large for a simple off-the-books medic."
2"The crowd was a menagerie of beings that scrambled her perception; people with skin like polished obsidian, others with eyes that held entire constellations, an…"
3"This was the same brand of wrongness that had clung to the scene of DS Morris’s death."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags1
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
78.4840%