Run: 2026-02-25-01KJ94JW9FVZJQPXHBPFY3YBEP

Run Details

Duration:
16.4s
Cost:
$0.001360
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
Rain lashed down, turning the London streets into slick, obsidian mirrors reflecting the garish neon glow of a thousand signs. Detective Harlow Quinn’s breath hitched, a ragged sound swallowed by the downpour and the thrum of her own exertion. Her salt-and-pepper hair clung to her scalp, plastered where it wasn't already lashed by the wind. Her worn leather watch, a familiar weight on her left wrist, kept time with the pounding in her chest. The figure ahead, a hunched shape in dark, cheap fabric, darted between overflowing bins and slick pavements, a whisper of movement in the deluge. Quinn pumped her legs, metres eating into the distance. Eighteen years on the force, and this was the familiar, brutal rhythm: the guttural chase, the hunter’s instinct, the desperate scramble of prey. The suspect was good, showing a runner’s agility born of necessity, not sport. They swung around a corner, splashing through a puddle that sent a geyser of dirty water into the air. Quinn followed, her military precision guiding her feet over the treacherous, uneven ground. The initial pursuit began near a dimly lit bar in Soho, its distinctive green neon sign a smear in the distance. The figure Bolt-down an alley, and Quinn was on their heels. This narrow passage reeked of damp brick and stale beer. Old maps, faded and peeling, would have adorned the walls if they hadn't been obscured by years of grime and hasty graffiti. The air grew heavy, charged with the scent of something foul. The suspect’s shoes skidded on loose gravel, a frantic scramble that echoed off the brickwork. "Stop!" The command ripped from Quinn’s throat, raw and hoarse, lost in the storm's roar. The figure didn't falter. They vaulted a low wall, landing hard on the other side. Quinn scrambled over it, the rough brick scraping her hands through her coat. She landed clumsily, but her training kicked in, righting her in an instant. The streets now opened into a wider, grayer district. The air grew colder, carrying the damp chill of the Thames. Warehouses loomed, skeletal shapes against the bruised sky, laced with rusting fire escapes and boarded-up windows. The chase veered sharply north, a relentless urban obstacle course. The suspect seemed to know these back routes, slipping through gaps in fences, under dripping awnings, their movements becoming more desperate, more erratic the further they fled. Quinn’s lungs burned, each breath a searing intake of rain-tinged air. Her sharp jaw clenched. She saw her partner, Morris, his laugh silenced three years ago, the inexplicable circumstances of his end a gnawing ache she pushed down, deep. This quarry, whoever they were, was leading her through increasingly desolate territory, far from the usual beat. They plunged under a dripping railway arch, the roaring of trains overhead a momentary deafening assault. The ground here was a mess of broken concrete and discarded detritus. The suspect stumbled, a cry of pain choked back. Quinn surged forward, the gap closing. Then, the figure veered towards a dark, cavernous opening beneath the archway, a place that looked less like an entrance and more like a wound in the city's side. Discarded scaffolding and rusting metal formed a chaotic fence. As the suspect neared the opening, they fumbled with something small, dark, and strangely shaped, tossing it towards a figure silhouetted against the gloom within. A faint clinking sound, like bone against stone, carried on the wind before the suspect plunged into the darkness itself. Quinn reached the entrance moments later. The storm seemed to recoil from the maw, leaving a pocket of unnerving quiet, broken only by the drip, drip, drip of water. The air here was thick with a miasma of unfamiliar scents – petrichor mixed with something metallic, something earthy, and a faint, sickly sweet undertone she couldn't place. The figure she had pursued had vanished into this subterranean abyss. Lights flickered deep within, casting shifting, unsettling shadows. What Anya had once called a black market, a place for the veiled and the banished, now lay before her: The Veil Market. She pulled up, boots crunching on broken glass. The sheer drop into the darkness was disorienting. This was no standard police raid scenario. This was the deep end, a place whispered about in hushed tones by informants who suddenly got very quiet when she pressed them. The entry, the bone token – it screamed of a world she only dimly grasped, a world that had swallowed her partner. Her hand tightened on the cold metal of her service weapon, the familiar weight a small comfort against the unknown pressing in. Her gaze swept the street, then returned to the gaping hole. The decision hung in the air, heavy as the London fog. Follow the ghost, or retreat to the known?
created_at"2026-02-25T00:53:32.596Z" 2/25/2026, 12:53:32 AM
model"google/gemini-2.5-flash-lite"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1103
moderation_latency(null)
generation_time16340
tokens_prompt1140
tokens_completion4408
native_tokens_prompt1042
native_tokens_completion3139
native_tokens_completion_images0
native_tokens_reasoning2125
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"
usage0.0013598
router(null)
provider_responses
0
endpoint_id"ce839073-aa24-4f29-8358-15b319bd05ec"
is_byokfalse
latency1103
model_permaslug"google/gemini-2.5-flash-lite"
provider_name"Google AI Studio"
status200
api_type"completions"
id"gen-1771980812-tOk6u4RDzhRvTHDDDDy9"
upstream_id(null)
total_cost0.0013598
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)
dialogueSentences1
tagDensity1
leniency1
rawRatio0
effectiveRatio0
81.08% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount793
totalAiIsmAdverbs3
found
0
adverb"sharply"
count1
1
adverb"suddenly"
count1
2
adverb"very"
count1
highlights
0"sharply"
1"suddenly"
2"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)
0.00% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount793
totalAiIsms21
found
0
word"familiar"
count3
1
word"weight"
count2
2
word"pounding"
count1
3
word"whisper"
count1
4
word"treacherous"
count1
5
word"charged"
count1
6
word"echoed"
count1
7
word"chill"
count1
8
word"loomed"
count1
9
word"searing"
count1
10
word"tinged"
count1
11
word"jaw clenched"
count1
12
word"roaring"
count1
13
word"chaotic"
count1
14
word"gloom"
count1
15
word"maw"
count1
16
word"flickered"
count1
17
word"standard"
count1
highlights
0"familiar"
1"weight"
2"pounding"
3"whisper"
4"treacherous"
5"charged"
6"echoed"
7"chill"
8"loomed"
9"searing"
10"tinged"
11"jaw clenched"
12"roaring"
13"chaotic"
14"gloom"
15"maw"
16"flickered"
17"standard"
66.67% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches2
maxInWindow2
found
0
label"jaw/fists clenched"
count1
1
label"hung in the air"
count1
highlights
0"jaw clenched"
1"hung in the air"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences53
matches(empty)
61.99% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount2
narrationSentences53
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)
analyzedSentences53
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen29
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords795
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions1
unquotedAttributions0
matches(empty)
83.33% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions19
wordCount794
uniqueNames10
maxNameDensity1.13
worstName"Quinn"
maxWindowNameDensity2.5
worstWindowName"Quinn"
discoveredNames
London2
Harlow1
Quinn9
Soho1
Bolt-down1
Thames1
Morris1
Anya1
Veil1
Market1
persons
0"Harlow"
1"Quinn"
2"Morris"
3"Anya"
places
0"London"
1"Soho"
2"Thames"
globalScore0.933
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences51
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount795
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences53
matches(empty)
19.15% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs9
mean88.33
std19.17
cv0.217
sampleLengths
098
177
290
392
493
581
645
799
8120
98.64% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences53
matches
0"been obscured"
93.33% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs125
matches
0"was leading"
1"was disorienting"
35.04% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount2
semicolonCount0
flaggedSentences2
totalSentences53
ratio0.038
matches
0"The air here was thick with a miasma of unfamiliar scents – petrichor mixed with something metallic, something earthy, and a faint, sickly sweet undertone she couldn't place."
1"The entry, the bone token – it screamed of a world she only dimly grasped, a world that had swallowed her partner."
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount797
adjectiveStacks1
stackExamples
0"faint, sickly sweet undertone"
adverbCount23
adverbRatio0.028858218318695106
lyAdverbCount10
lyAdverbRatio0.012547051442910916
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences53
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences53
mean15
std6.62
cv0.442
sampleLengths
020
119
216
319
424
59
623
713
819
913
1021
1111
1210
1322
1411
1515
1615
174
1811
1913
2013
219
2211
2316
2410
2527
2611
274
2824
2917
3016
3112
329
336
3429
359
3625
3720
386
3923
4028
4111
428
4323
448
458
467
4723
4822
4922
40.88% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats10
diversityRatio0.3584905660377358
totalSentences53
uniqueOpeners19
62.89% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences53
matches
0"Then, the figure veered towards"
ratio0.019
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount11
totalSentences53
matches
0"Her salt-and-pepper hair clung to"
1"Her worn leather watch, a"
2"They swung around a corner,"
3"They vaulted a low wall,"
4"She landed clumsily, but her"
5"Her sharp jaw clenched."
6"She saw her partner, Morris,"
7"They plunged under a dripping"
8"She pulled up, boots crunching"
9"Her hand tightened on the"
10"Her gaze swept the street,"
ratio0.208
35.47% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount45
totalSentences53
matches
0"Rain lashed down, turning the"
1"Detective Harlow Quinn’s breath hitched,"
2"Her salt-and-pepper hair clung to"
3"Her worn leather watch, a"
4"The figure ahead, a hunched"
5"Quinn pumped her legs, metres"
6"The suspect was good, showing"
7"They swung around a corner,"
8"Quinn followed, her military precision"
9"The initial pursuit began near"
10"The figure Bolt-down an alley,"
11"This narrow passage reeked of"
12"The air grew heavy, charged"
13"The suspect’s shoes skidded on"
14"The command ripped from Quinn’s"
15"The figure didn't falter."
16"They vaulted a low wall,"
17"Quinn scrambled over it, the"
18"She landed clumsily, but her"
19"The streets now opened into"
ratio0.849
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences53
matches(empty)
ratio0
87.91% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences39
technicalSentenceCount3
matches
0"The suspect’s shoes skidded on loose gravel, a frantic scramble that echoed off the brickwork."
1"The suspect seemed to know these back routes, slipping through gaps in fences, under dripping awnings, their movements becoming more desperate, more erratic the…"
2"The entry, the bone token – it screamed of a world she only dimly grasped, a world that had swallowed her partner."
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
78.6802%