Run: 2026-05-27-01KSMF0F5Y15NXJC02JR62JVF9

Run Details

Duration:
11.1s
Cost:
$0.000904
Provider:
Parasail

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="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> 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.

Model response

AI
Detective Harlow Quinn scanned the abandoned Tube station with a critical gaze, her sharp brown eyes taking in the Cairo Street. She hated being woken from a fitful sleep after only four hours, but this was the sort of call you just couldn't ignore. According to dispatch, a body had been found in the underground tunnel system beneath Camden - an area technically off limits to the public since its closure over 20 years ago. The acrid stench of supernatural hung heavy in the stale air, making the hairs on the back of the detective's neck prick. Catnip and burnt juniper - the early warning signs of arcane activity she'd gotten all too familiar with since partnering with Dunn after the incident in St Albans. Her colleague peered around the corner, his doughy face twisted into a rictus. Discarded takeaway wrappers covered in gang graffiti crunched underfoot as she approached the scene. "Another overdose then?" Dunn asked, wryly. "The body's over here," Quinn replied, ignoring his flippant tone. She held her hand out for a flashlight. A slender young woman - perhaps a student - lay face down in a heap, crumpled papers scattered around her like graveside flowers. "Damage to the upper respiratory tract," she muttered, "She drowned on her own vomit." Dunn. Played havoc with 30 pages decomposing matter, only made it clear that prominent bone fragments and a blood-soaked backpack. The victim's pale green rain mac shimmered like snake skin under the lights. On closer inspection, the lacerations on the girl's wrists looked almost ritualistic, as if whoever had killed her had also attempted to bleed her dry. Two knots - an occult symbol. A tightness cinched Quinn's throat. But alongside these grisly wounds were what looked like...dog bite marks? Careful not to disturb any potential evidence, Quinn slowly circled the body, scanning the dingy brick walls for clues. And that's when she saw it - a tiny disc screwed under an Ivy covered poster advertising the latest hosts of Got Talent...a bone token. Her stomach lurching. Quinn knew exactly what that meant. "Shite," she hissed under her breath. When she'd last encountered one, it had been proof that a crop of so called 'psychic healers' inside Holloway Belmarsh had been selling more than just spiritual cleansing to their clients. She flashed her torch back over the corpse - this was no ordinary murder. Quinn straightened up, digging through her leather jacket for her phone. She hesitated a moment, considering her options, before pulling up a number and hitting dial. "Evie?" She pressed the device to her ear, "It's me, Harlow. I need your help."
created_at"2026-05-27T10:17:15.212Z" 5/27/2026, 10:17:15 AM
model"thedrummer/skyfall-36b-v2"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency252
moderation_latency(null)
generation_time10989
tokens_prompt923
tokens_completion672
native_tokens_prompt875
native_tokens_completion577
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached128
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
service_tier(null)
usage0.00090445
router(null)
provider_responses
0
endpoint_id"1eb01ded-ae11-49e6-8aa6-3067584070bd"
id"chatcmpl-9545a0b8ae35e8e8"
is_byokfalse
latency252
model_permaslug"thedrummer/skyfall-36b-v2"
provider_name"Parasail"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.15.0; linux; x64))"
http_referer(null)
request_id"req-1779877035-4ii6ENNh1TIxHyDZ3uUv"
session_id(null)
api_type"completions"
id"gen-1779877035-KmaWklZetZdnaxiDSuX4"
upstream_id"chatcmpl-9545a0b8ae35e8e8"
total_cost0.00090445
cache_discount0.0000384
upstream_inference_cost0
provider_name"Parasail"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags6
adverbTagCount0
adverbTags(empty)
dialogueSentences5
tagDensity1
leniency1
rawRatio0
effectiveRatio0
88.40% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount431
totalAiIsmAdverbs1
found
0
adverb"slowly"
count1
highlights
0"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)
18.79% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount431
totalAiIsms7
found
0
word"scanned"
count1
1
word"familiar"
count1
2
word"shimmered"
count1
3
word"potential"
count1
4
word"scanning"
count1
5
word"stomach"
count1
6
word"lurching"
count1
highlights
0"scanned"
1"familiar"
2"shimmered"
3"potential"
4"scanning"
5"stomach"
6"lurching"
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
narrationSentences28
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences28
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences28
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen31
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords438
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions4
unquotedAttributions0
matches(empty)
73.86% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions19
wordCount394
uniqueNames12
maxNameDensity1.52
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Harlow1
Quinn6
Tube1
Cairo1
Street1
Camden1
Dunn3
St1
Albans1
Played1
Ivy1
Got1
persons
0"Harlow"
1"Quinn"
2"Dunn"
3"Ivy"
places
0"Cairo"
1"Street"
2"St"
3"Albans"
globalScore0.739
windowScore1
41.30% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences23
glossingSentenceCount1
matches
0"looked like...dog bite marks"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount438
matches(empty)
47.62% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences28
matches
0"proof that a"
76.35% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs10
mean43.8
std18.27
cv0.417
sampleLengths
075
150
233
318
470
547
644
746
840
915
80.20% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences28
matches
0"being woken"
1"been found"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs70
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount7
semicolonCount0
flaggedSentences6
totalSentences28
ratio0.214
matches
0"According to dispatch, a body had been found in the underground tunnel system beneath Camden - an area technically off limits to the public since its closure over 20 years ago."
1"Catnip and burnt juniper - the early warning signs of arcane activity she'd gotten all too familiar with since partnering with Dunn after the incident in St Albans."
2"A slender young woman - perhaps a student - lay face down in a heap, crumpled papers scattered around her like graveside flowers."
3"Two knots - an occult symbol."
4"And that's when she saw it - a tiny disc screwed under an Ivy covered poster advertising the latest hosts of Got Talent...a bone token."
5"She flashed her torch back over the corpse - this was no ordinary murder."
87.07% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount347
adjectiveStacks0
stackExamples(empty)
adverbCount18
adverbRatio0.05187319884726225
lyAdverbCount8
lyAdverbRatio0.023054755043227664
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences28
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences28
mean15.64
std8.01
cv0.512
sampleLengths
021
123
231
322
428
513
614
76
810
98
1023
1115
1219
1313
1425
156
165
1711
1819
1925
203
216
226
2331
2414
2511
2615
2715
100.00% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats0
diversityRatio0.7142857142857143
totalSentences28
uniqueOpeners20
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences28
matches(empty)
ratio0
91.43% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount9
totalSentences28
matches
0"She hated being woken from"
1"Her colleague peered around the"
2"She held her hand out"
3"she muttered, Dunn"
4"Her stomach lurching."
5"she hissed under her breath"
6"She flashed her torch back"
7"She hesitated a moment, considering"
8"She pressed the device to"
ratio0.321
100.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount19
totalSentences28
matches
0"Detective Harlow Quinn scanned the"
1"She hated being woken from"
2"The acrid stench of supernatural"
3"Catnip and burnt juniper -"
4"Her colleague peered around the"
5"Dunn asked, wryly"
6"Quinn replied, ignoring his flippant"
7"She held her hand out"
8"A slender young woman -"
9"she muttered, Dunn"
10"The victim's pale green rain"
11"A tightness cinched Quinn's throat."
12"Her stomach lurching."
13"Quinn knew exactly what that"
14"she hissed under her breath"
15"She flashed her torch back"
16"Quinn straightened up, digging through"
17"She hesitated a moment, considering"
18"She pressed the device to"
ratio0.679
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences28
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences17
technicalSentenceCount1
matches
0"On closer inspection, the lacerations on the girl's wrists looked almost ritualistic, as if whoever had killed her had also attempted to bleed her dry."
41.67% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount1
matches
0"Dunn asked, wryly"
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags5
fancyCount3
fancyTags
0"she muttered (mutter)"
1"she hissed (hiss)"
2"She pressed (press)"
dialogueSentences5
tagDensity1
leniency1
rawRatio0.6
effectiveRatio0.6
74.8895%