Run: 2026-02-19-01KHTRMA9Y5GJ1BFAM7B1MWAHX

Run Details

Duration:
33.0s
Cost:
$0.001671
Provider:
Novita

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 hammered down on the slick pavement, turning the neon reflections into liquid smears of color. Detective Harlow Quinn sprinted after the figure disappearing around the corner, her breath sharp in her chest. The suspect—hooded, fast—had been tailing her for blocks before she’d made him. Now he was running, and that was all the confirmation she needed. She skidded around the corner, her boots splashing through a puddle. The street was narrow, lined with shuttered shops and the occasional flickering streetlamp. The hooded figure darted into an alley, and Quinn followed without hesitation. Her wristwatch, the worn leather strap damp against her skin, read 2:17 AM. Too late for witnesses, too early for the morning shift. Perfect for someone who didn’t want to be seen. The alley dead-ended at a rusted metal door. The suspect was already through it, the door swinging shut behind him. Quinn didn’t slow. She slammed her shoulder into it, bursting into a dimly lit stairwell that reeked of mildew and something sharper—ozone, maybe, or old magic. The steps descended into darkness. She hesitated, just for a second. No backup. No idea what was down there. But the case had been cold for too long, and this was the first real lead in months. She took the stairs two at a time. The air grew thicker, warmer, the deeper she went. The sound of dripping water echoed off the curved brick walls—old Tube tunnels, maybe. Abandoned, but not empty. At the bottom, a flickering lantern cast jagged shadows across a heavy wooden door. A single bone token hung from a nail beside it. Quinn’s fingers hovered over it. She’d heard whispers about the Veil Market, but she’d never seen it. Never had reason to. A muffled voice carried through the door—low, urgent. The suspect was close. She grabbed the token. The door swung open on silent hinges. The market sprawled before her, a labyrinth of stalls and makeshift tents under the vaulted ceiling of the disused station. Lanterns hung from rusted pipes, their light wavering like candle flames. The crowd was a shifting mass of shadows and silhouettes—some human, some not. A vendor with too-long fingers haggled over a jar of something that pulsed faintly blue. A woman with a crow perched on her shoulder counted out coins that glinted like teeth. Quinn’s hand drifted to her sidearm, but she didn’t draw. Not yet. The hooded figure was moving fast, weaving through the crowd. She followed, keeping her strides measured, her posture loose. Military precision, even here. A hand caught her elbow. “You’re not supposed to be here, detective.” She turned. Tomás Herrera stood beside her, his olive skin washed gold in the lantern light. His Saint Christopher medallion glinted at his throat. The scar on his forearm stood pale against his skin. She pulled her arm free. “You know him?” Tomás’s gaze flicked toward the retreating figure. “I know this isn’t your place.” “He’s involved.” “In what?” Quinn’s jaw tightened. “Morris.” Tomás exhaled sharply. “Christ.” He glanced around, then leaned in. “You follow him deeper in, you don’t come back out. Not without help.” “Then help me.” He studied her face, then nodded once. “Stay close.” They moved through the market, the crowd parting subtly around Tomás. The air smelled of incense and iron. Up ahead, the hooded figure ducked behind a curtain into a smaller alcove. Quinn reached for her gun. Tomás caught her wrist. “Not here. You pull that, you start a war.” She met his eyes. “Then what do you suggest?” He reached into his jacket and pulled out a small vial filled with dark liquid. “Distraction.” He threw it against the far wall. The glass shattered, and the liquid burst into thick, swirling smoke. The market erupted into shouts and scrambling bodies. Quinn didn’t wait. She lunged for the alcove, shoving the curtain aside. The hooded figure stood in the center of the cramped space, his back to her. Slowly, he turned. The hood fell back. Quinn’s breath caught. It wasn’t a suspect. It was DS Morris.
created_at"2026-02-19T10:55:14.755Z" 2/19/2026, 10:55:14 AM
model"deepseek/deepseek-chat-v3"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2134
moderation_latency(null)
generation_time32932
tokens_prompt1140
tokens_completion1123
native_tokens_prompt1002
native_tokens_completion977
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"
usage0.0016709
router(null)
provider_responses
0
endpoint_id"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
id"b3bad65bf92b724acbe039eb8776403e"
is_byokfalse
latency2134
model_permaslug"deepseek/deepseek-chat-v3"
provider_name"Novita"
status200
api_type"completions"
id"gen-1771498514-Lssg1JOxtcjV37yx8K8x"
upstream_id"b3bad65bf92b724acbe039eb8776403e"
total_cost0.0016709
cache_discount(null)
upstream_inference_cost0
provider_name"Novita"

Evaluation details

Result Evaluator Details Meta Data
46.15% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags1
adverbTagCount1
adverbTags
0"He glanced around [around]"
dialogueSentences13
tagDensity0.077
leniency0.154
rawRatio1
effectiveRatio0.154
85.40% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount685
totalAiIsmAdverbs2
found
0
adverb"sharply"
count1
1
adverb"slowly"
count1
highlights
0"sharply"
1"slowly"
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)
48.91% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount685
totalAiIsms7
found
0
word"perfect"
count1
1
word"echoed"
count1
2
word"wavering"
count1
3
word"pulsed"
count1
4
word"measured"
count1
5
word"flicked"
count1
6
word"shattered"
count1
highlights
0"perfect"
1"echoed"
2"wavering"
3"pulsed"
4"measured"
5"flicked"
6"shattered"
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
narrationSentences71
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences71
filterMatches(empty)
hedgeMatches(empty)
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
maxSentenceWordsSeen24
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords677
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions2
unquotedAttributions0
matches(empty)
77.65% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions22
wordCount622
uniqueNames10
maxNameDensity1.45
worstName"Quinn"
maxWindowNameDensity2.5
worstWindowName"Tomás"
discoveredNames
Harlow1
Quinn9
Tube1
Veil1
Market1
Herrera1
Saint1
Christopher1
Tomás5
Morris1
persons
0"Harlow"
1"Quinn"
2"Market"
3"Herrera"
4"Saint"
5"Christopher"
6"Tomás"
7"Morris"
places(empty)
globalScore0.777
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences47
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount677
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences83
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs36
mean18.81
std17.41
cv0.926
sampleLengths
058
136
232
346
437
58
651
721
812
911
1075
1112
1223
135
147
1534
168
1713
182
192
204
2123
223
239
2431
255
2613
279
2816
2926
3012
3118
324
333
344
354
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences71
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount1
totalVerbs112
matches
0"was running"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount6
semicolonCount0
flaggedSentences5
totalSentences83
ratio0.06
matches
0"The suspect—hooded, fast—had been tailing her for blocks before she’d made him."
1"She slammed her shoulder into it, bursting into a dimly lit stairwell that reeked of mildew and something sharper—ozone, maybe, or old magic."
2"The sound of dripping water echoed off the curved brick walls—old Tube tunnels, maybe."
3"A muffled voice carried through the door—low, urgent."
4"The crowd was a shifting mass of shadows and silhouettes—some human, some not."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount630
adjectiveStacks0
stackExamples(empty)
adverbCount24
adverbRatio0.0380952380952381
lyAdverbCount6
lyAdverbRatio0.009523809523809525
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
mean8.16
std4.86
cv0.596
sampleLengths
017
117
212
312
411
513
612
713
810
99
108
1112
123
1323
145
156
162
176
1818
198
209
2114
224
2314
2410
255
2612
274
288
294
304
317
3220
3311
3413
3515
3616
3710
382
3910
409
414
425
437
442
4514
468
4710
485
493
54.62% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats8
diversityRatio0.3855421686746988
totalSentences83
uniqueOpeners32
98.04% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences68
matches
0"Too late for witnesses, too"
1"Slowly, he turned."
ratio0.029
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount19
totalSentences68
matches
0"She skidded around the corner,"
1"Her wristwatch, the worn leather"
2"She slammed her shoulder into"
3"She hesitated, just for a"
4"She took the stairs two"
5"She’d heard whispers about the"
6"She grabbed the token."
7"She followed, keeping her strides"
8"His Saint Christopher medallion glinted"
9"She pulled her arm free."
10"He glanced around, then leaned"
11"He studied her face, then"
12"They moved through the market,"
13"She met his eyes."
14"He reached into his jacket"
15"He threw it against the"
16"She lunged for the alcove,"
17"It wasn’t a suspect."
18"It was DS Morris."
ratio0.279
33.53% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount58
totalSentences68
matches
0"The rain hammered down on"
1"Detective Harlow Quinn sprinted after"
2"The suspect—hooded, fast—had been tailing"
3"She skidded around the corner,"
4"The street was narrow, lined"
5"The hooded figure darted into"
6"Her wristwatch, the worn leather"
7"The alley dead-ended at a"
8"The suspect was already through"
9"Quinn didn’t slow."
10"She slammed her shoulder into"
11"The steps descended into darkness."
12"She hesitated, just for a"
13"She took the stairs two"
14"The air grew thicker, warmer,"
15"The sound of dripping water"
16"A single bone token hung"
17"Quinn’s fingers hovered over it."
18"She’d heard whispers about the"
19"A muffled voice carried through"
ratio0.853
73.53% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences68
matches
0"Now he was running, and"
ratio0.015
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences30
technicalSentenceCount1
matches
0"She slammed her shoulder into it, bursting into a dimly lit stairwell that reeked of mildew and something sharper—ozone, maybe, or old magic."
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
87.2610%