Run: 2026-02-20-01KHY8ES23QN863NBK4EZH454N

Run Details

Duration:
47.5s
Cost:
$0.000458
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="4414" name="Eva Kowalski" aliases="Eva, Evie" pronouns="she/her" species="Human" storyRole="Best Friend"> <eyeColor>green</eyeColor> <hair>curly red</hair> <height>5'4"</height> <age>26</age> <glasses>round glasses</glasses> <satchel>worn leather satchel full of books</satchel> <freckles>freckled complexion</freckles> <nervousHabit>tucking hair behind her left ear</nervousHabit> <description>Aurora's childhood friend and an occult researcher.</description> <backstory>Moved to London two years before Aurora and works as a research assistant at the British Museum's restricted archives. She holds a master's degree in Ancient History from Oxford.</backstory> </character> <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> <item id="2004" name="Veil Compass" aliases="the Compass, shadow compass" type="Tool" origin="The Veil Market"> <casingMaterial>small brass compass</casingMaterial> <faceMarkings>face etched with protective sigils</faceMarkings> <needle>points toward the nearest supernatural rift or portal</needle> <patina>casing has a patina of verdigris</patina> <creator>crafted by a Shade artisan</creator> <description>A compass attuned to supernatural energy.</description> </item> </codex> Continue the story using the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the mystery genre. A detective arrives at a crime scene in an unusual location. Something is wrong — the evidence doesn't add up. A colleague is present, offering a different interpretation. Through careful observation and deduction, the detective begins to see what others have missed. 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 air tasted of iron and damp concrete. Not the usual London grime, but something older, heavier. Detective Harlow Quinn adjusted the collar of her coat, the abrasive wool doing little against the chill seeping from the walls. Camden Town’s abandoned tube station wasn’t known for brisk drafts. It was known for being sealed off, forgotten. Now, it pulsed with a grim, unwelcome energy. Fluorescent lights, jury-rigged from something scavenged, buzzed overhead, illuminating a circle of chalk dust on the platform. Inside it, a man lay sprawled, limbs at awkward angles. Expensive suit, polished shoes. Looked like someone who usually frequented the Mayfair, not a ghost station. “Clean,” she observed, voice raspy from years of unfiltered cigarettes. “Too clean.” DS Davies, younger, by at least a decade, and perpetually eager, hovered beside the body. He bounced on the balls of his feet, trying to stay warm. His face, pale under the harsh light, registered concern. “Heart attack, maybe? Looks natural enough.” Quinn crouched, ignoring the protest in her knees. She ran a gloved hand along the platform’s edge, collecting grit. Her eyes swept the scene, cataloging. No signs of a struggle. No disturbed dust. Just… emptiness. “Natural doesn’t usually come with a bone token clutched in the hand, Davies.” Davies shuffled his feet. “Right. The token. Forensics are bagging it now. Bit odd, though, innit? Like something out of a film.” She picked up the bagged token with a pair of tweezers, turning it over. Carved bone, intricate swirling patterns. The kind you’d find… down here. “Odd doesn’t cover it. This isn't a random heart attack. This is someone who knew where they were going, and why.” She glanced around, noting the subtle scent of ozone. “And whoever he was meeting wasn’t offering tea and biscuits.” “We got a name, sir?” “Julian Devereux. City banker. Made a fortune on… well, something complicated involving derivatives. Wife reported him missing this morning. Said he mentioned a ‘late night meeting’. Couldn't specify where.” Davies recited the information with practiced efficiency. Quinn stood, her gaze fixed on a barely perceptible discoloration on the tunnel wall. A smear, almost invisible against the soot. She touched it with a gloved finger. It felt… cold. Not just temperature, but a bone-deep chill. “Devereux wasn’t here for a deal gone wrong, Davies. He was hunted.” “Hunted? By what, sir?” “That’s what we need to find out. Forensics. I want everything dusted. Every surface. I want to know if anyone else was down here, recent or not. And get me a list of everything Devereux was working on. Every account, every transaction. I want it all.” She adjusted her worn leather watch, a habit she’d picked up from DS Morris. Still felt wrong without its weight on her wrist. “Right away, sir.” Davies hurried off to relay her orders, his shoes echoing in the cavernous space. Quinn returned to the body. The medical examiner, a weary-looking woman named Patel, was already examining Devereux. “Anything?” Quinn asked. Patel looked up, her expression grim. “No obvious trauma. Heart gave out, like Davies said. But… there's something off. His skin. It’s… cold. Not post-mortem cold. *Frozen* cold. Like he was exposed to extreme temperatures, but there’s no indication of that here.” “And the eyes?” Patel gently closed Devereux’s eyelids. “Dilated. Unfocused. Like he saw something terrifying just before he died.” “Terrifying enough to induce cardiac arrest,” Quinn muttered. She crouched again, carefully examining the chalk circle. The lines weren’t clean, weren’t precise. They wavered, as if drawn by a shaky hand. Almost… defensively. “Look at this.” She gestured to a tiny, almost invisible scratch inside the circle. “Too small to be made by a shoe. Too deliberate to be accidental.” Patel leaned in, squinting. “Looks like… a sigil. Old. Very old.” Quinn’s jaw tightened. “Eva will know.” She pulled out her phone, scrolling through her contacts until she found Eva Kowalski. “Eva, it's Quinn. I need you down to Camden tube station. Now.” A pause. “Camden? What’s happened?” Eva’s voice was laced with a familiar anxiety. “Body. Looks… complicated. Sigils, bone tokens. I need your eyes on it.” “On my way.” Eva hung up, her urgency palpable even through the phone line. Fifteen minutes later, Eva arrived, a whirlwind of curly red hair and frantic energy. She clutched her worn leather satchel to her chest, round glasses sliding down her nose as she took in the scene. “Good Lord,” she breathed, pushing her glasses back up. “This is… intense.” “You recognize the sigil?” Quinn asked, nodding towards the almost invisible scratch. Eva knelt, carefully photographing it with her phone. “Partial. Very partial. Looks like a fragment of a warding symbol. Used to… contain something. Or someone.” Her fingers flew across her phone screen, pulling up images, cross-referencing. “Contain?” “Yeah. Ancient stuff. Pre-Roman Britain. Believed to be effective against… entities. Spirits. Things that aren’t supposed to be here.” “Entities?” Davies interjected, hovering nearby. “You mean ghosts?” Eva gave him a withering look. “Not ghosts, DS. Something… more substantial. More *hungry*. The Veil is thin in places, you know. And this station…” “The Veil?” Davies’ confusion was evident. Quinn cut him off. “Save the explanations for later, Eva. What can you tell me about the token?” Eva pointed to the bagged bone token on a nearby table. “Those are used to gain access to the Veil Market. It’s an… underground market. Sells enchanted objects, alchemical ingredients, information. Generally stuff you can't get anywhere else.” “And Devereux was a customer?” “Possibly. Or a supplier. Or both. People go to the Market for all sorts of reasons. Some seek power, some seek knowledge, some seek things best left alone.” Quinn walked to the tunnel wall, tracing the discoloration with her finger. “This feels… wrong. It’s not just the sigil, not just the token. It’s like something *leaked* into this place.” “Leaked?” Eva followed her, examining the wall. “You mean a rift? A thinning of the Veil?” She pulled a small brass compass from her satchel, its face etched with protective sigils. The needle spun wildly, then settled, pointing directly at the discoloration. “Definitely something here,” Eva said, her voice barely a whisper. "And it’s not happy." The casing had a patina of verdigris, evidence of age and countless journeys. “What does the Compass tell you?” Quinn asked, her gaze unwavering. “It's radiating interference. Strong. Like a localized energy surge. Whatever happened here wasn’t natural, Quinn. It was… intentional.” Eva’s nervous habit surfaced, her hand flying to tuck a strand of red hair behind her left ear. “Someone *opened* something they shouldn’t have.”
created_at"2026-02-20T19:29:33.772Z" 2/20/2026, 7:29:33 PM
model"google/gemma-3-27b-it"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency681
moderation_latency(null)
generation_time47369
tokens_prompt1173
tokens_completion1904
native_tokens_prompt1084
native_tokens_completion1644
native_tokens_completion_images(null)
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"
usage0.000457796
router(null)
provider_responses
0
endpoint_id"cf530f36-7cb8-4eb9-8953-880eef952af3"
id"bbd8ec10-7cbe-4b57-8ad4-475cf09ab5e7"
is_byokfalse
latency584
model_permaslug"google/gemma-3-27b-it"
provider_name"Novita"
status200
api_type"completions"
id"gen-1771615773-BPjfxDBviqH2baJ7OyqW"
upstream_id"bbd8ec10-7cbe-4b57-8ad4-475cf09ab5e7"
total_cost0.000457796
cache_discount(null)
upstream_inference_cost0
provider_name"Novita"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags18
adverbTagCount1
adverbTags
0"She glanced around [around]"
dialogueSentences48
tagDensity0.375
leniency0.75
rawRatio0.056
effectiveRatio0.042
77.29% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1101
totalAiIsmAdverbs5
found
0
adverb"gently"
count1
1
adverb"carefully"
count2
2
adverb"very"
count2
highlights
0"gently"
1"carefully"
2"very"
80.00% AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions(empty)
found
0"Patel"
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
40.96% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1101
totalAiIsms13
found
0
word"chill"
count2
1
word"pulsed"
count1
2
word"intricate"
count1
3
word"weight"
count1
4
word"echoing"
count1
5
word"wavered"
count1
6
word"familiar"
count1
7
word"palpable"
count1
8
word"tracing"
count1
9
word"etched"
count1
10
word"whisper"
count1
11
word"unwavering"
count1
highlights
0"chill"
1"pulsed"
2"intricate"
3"weight"
4"echoing"
5"wavered"
6"familiar"
7"palpable"
8"tracing"
9"etched"
10"whisper"
11"unwavering"
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
narrationSentences73
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences73
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences102
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen60
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans4
markdownWords4
totalWords1096
ratio0.004
matches
0"Frozen"
1"hungry"
2"leaked"
3"opened"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions10
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions39
wordCount598
uniqueNames12
maxNameDensity1.84
worstName"Quinn"
maxWindowNameDensity5
worstWindowName"Eva"
discoveredNames
London1
Harlow1
Quinn11
Town1
Mayfair1
Davies5
Morris1
Patel4
Devereux2
Eva10
Kowalski1
Fifteen1
persons
0"Harlow"
1"Quinn"
2"Davies"
3"Morris"
4"Patel"
5"Devereux"
6"Eva"
7"Kowalski"
places
0"London"
1"Town"
globalScore0.58
windowScore0
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences50
glossingSentenceCount1
matches
0"Looked like someone who usually frequente"
17.52% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches2
per1kWords1.825
wordCount1096
matches
0"Not the usual London grime, but something older, heavier"
1"Not just temperature, but a bone-deep chill"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences102
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs50
mean21.92
std15.54
cv0.709
sampleLengths
064
143
212
336
46
535
613
722
825
940
105
1136
1238
1312
144
1569
1617
1717
183
1942
203
2116
2233
2327
2411
256
2614
2712
2813
2912
3014
3135
3212
3312
3436
351
3619
378
3825
396
4018
4138
425
4328
4431
4542
4614
4713
4811
4942
95.65% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences73
matches
0"was known"
1"was laced"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs116
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences102
ratio0
matches(empty)
95.29% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount617
adjectiveStacks0
stackExamples(empty)
adverbCount28
adverbRatio0.04538087520259319
lyAdverbCount9
lyAdverbRatio0.014586709886547812
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences102
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences102
mean10.75
std9.16
cv0.852
sampleLengths
08
19
221
310
48
58
617
710
84
912
1010
112
1215
1312
149
156
168
1711
186
195
203
211
221
2313
244
2518
2614
275
284
292
3030
3110
325
3336
3414
357
367
372
381
397
4012
414
4260
439
4417
455
4612
473
486
4936
99.02% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.6274509803921569
totalSentences102
uniqueOpeners64
52.91% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences63
matches
0"Still felt wrong without its"
ratio0.016
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount18
totalSentences63
matches
0"It was known for being"
1"she observed, voice raspy from"
2"He bounced on the balls"
3"His face, pale under the"
4"She ran a gloved hand"
5"Her eyes swept the scene,"
6"She picked up the bagged"
7"She glanced around, noting the"
8"She touched it with a"
9"She adjusted her worn leather"
10"She crouched again, carefully examining"
11"They wavered, as if drawn"
12"She gestured to a tiny,"
13"She pulled out her phone,"
14"She clutched her worn leather"
15"she breathed, pushing her glasses"
16"Her fingers flew across her"
17"She pulled a small brass"
ratio0.286
55.24% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount51
totalSentences63
matches
0"The air tasted of iron"
1"Detective Harlow Quinn adjusted the"
2"Camden Town’s abandoned tube station"
3"It was known for being"
4"she observed, voice raspy from"
5"DS Davies, younger, by at"
6"He bounced on the balls"
7"His face, pale under the"
8"Quinn crouched, ignoring the protest"
9"She ran a gloved hand"
10"Her eyes swept the scene,"
11"Davies shuffled his feet."
12"She picked up the bagged"
13"The kind you’d find…"
14"She glanced around, noting the"
15"Davies recited the information with"
16"Quinn stood, her gaze fixed"
17"A smear, almost invisible against"
18"She touched it with a"
19"She adjusted her worn leather"
ratio0.81
79.37% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences63
matches
0"Now, it pulsed with a"
ratio0.016
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences18
technicalSentenceCount0
matches(empty)
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags18
uselessAdditionCount5
matches
0"she observed, voice raspy from years of unfiltered cigarettes"
1"Davies hurried, his shoes echoing in the cavernous space"
2"Eva hung up, her urgency palpable even through the phone line"
3"Eva said, her voice barely a whisper"
4"Quinn asked, her gaze unwavering"
66.67% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags8
fancyCount4
fancyTags
0"she observed (observe)"
1"Quinn muttered (mutter)"
2"she breathed (breathe)"
3"Davies interjected (interject)"
dialogueSentences48
tagDensity0.167
leniency0.333
rawRatio0.5
effectiveRatio0.167
81.9972%