Run: 2026-05-27-01KSMF31T3N49AMZ71S55RXCPQ

Run Details

Duration:
23.4s
Cost:
$0.001255
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 tilted her camera to capture the bloody handprint on the crumbling brick wall. Another flick, and the flash illuminated the upturned stool and cracked floor tiles scattered with manila envelopes and yellowing paper. The abandoned Tube station was a graveyard of subway trestles and rusted tracks, the corrupt air thick with the scent of mildew. Dusting his hands, SOCO forensics tech Richtung looked at her from beneath his lowered goggles. "What do you make of it then, guv?" Quinn scanned the trashed office. This crime scene was...unexpected. Like finding cancer hiding in an arterial ultrasound. She popped the lid on her espresso and took a sip, printing off her images to tuck in her elbow crooks. Glancing at the yellow tape blocking the looted dossier drawer by her sneaker, she considered what it meant. When she'd pulled back the tears of the station manager in the bluish light of his security footage, he'd confirmed her worst fears. Just before closing yesterday, a couple tables had been tucked out of sight, and a who's-who of local criminal element poured in. Pink pints flowing, eyebrows raised and voices low, they swapped sacks and chips, business conducted in plain sight. But then at 10:00 sharp, the camera had glitched, white noise fuzzing the picture. By 11, the station emptied, the tables scraped back, and only the crushed goblets left the wild rumpus; as if they'd been guests to nothing more than a raucous pub night. Except for this new crime center here under the Eston Place escalator, splattered with black-candled wax and reeking of money. Quinn's money was on an occult black market operating under her nose, and that seat covered with talcum was the cardman's chair. But more than that, she breathed in, there was something seriously supernatural swirling in the ether. Their not-dconsult dismissed, Quinn let her captain, jabbed thumbprints across his phone, wait for Clingmans as he hunched there over the éclat's tablet at the crime tape. Warren was a developer and a gamester, late 30s with a poor man's Porshe. Put him in the same room with an otaku and his madra, he'd wiggle in and still play 'em for cecks. Warren jogged up and bumped hands with Richt, wrapped his tweed tie around his fist while Quinn massaged her eyes. "So what is this, then, Quinn? Who are you calling in, our resident psychic medium?" He rubbed his temples and sighed, drawing an 'X' in his forehead from a stacks of greasy fry wrappers. "Look, I'll let you run out this lead, yeah? But we got both law and customs gunning for this. You'll need to partner for this one, probably Roberti. And day report and proceed accordingly. No freakshows, hear?" She narrowed her eyes and tightened her fists, staring at Warren who was explaining. "Yeah, well you explain why this crime scene shows evidence of an occult ritual, but no sign of an actual body or bloodstains. And who's Roberti?" "Ah, so you're taking that track then, huh?" Warren rolled his eyes and flicked his crape hat brim. "Roberti's a new blood period on sifting through the occult in art for the museum." DJed thumbprint, he pocketed and uploaded the prints, gave Quinn a reproving look and stuffed his clipboard. "Right, so let me get this straight. We've got a crime scene that all but screams black magic, and you're telling me I need to partner with some occult consult from the art department?" Quinn shook her head, disbelief seeping in. "I don't know, captain. This feels like an episode of Scooby Doo more than an actual police investigation." But Quinn knew the game was changing. The game was watching back. She looked at her watch - 14:00, she'd best limp on in to the ME and see what Kip had cooked up, phone in hand, already on course for the morgue, the mess he'd made of the file and the shoddy fresh instagram photos locked in her father's camera. Warren had spoken. Quinn knew what she needed to do. This weighed like a lasso 'round her neck, though. The magics and mysteries crowd. A panted hesitation, caught in her throat. Her mind raced, turning in scrutiny like a fingerprint. The bloodstains. The wax and the glasses. She stared at the game board. Quiet news break, though, dog and pony show. Bolstering the case. Could it have been a part of an occult ritual? If so, what kind of ritual? Who were these people and what did they want? Quinn swallowed and braced, thinking harder. He looked up from his phone and smirked. "Either way, you're gonna have to play nice with the experts, Quinn. They're the big dogs on the supernatural food chain, remember? Oh, and don't forget to send me a post-mortem, yeah? Wouldn't want no skeletons in the closet, now would we?" Quinn's shoulders slacked, defeated. Christ almighty, why did it have to be Eva, her colleague from art history? Of course she'd be hauled in. Fucking figures. Eva, with her penchant for all things witchy and woo-woo. Always talking about her esoteric books and Magic the Gathering. Quinn's jaw tightened. If she had to hear about her guide on toldra ornijo or lintomas threadskra one more goddamn time, she'd... She'd what? Swear on the fucking raz? Pin the talcman's hands on Leary's card and crush it? No, that wouldn't help. Eva was the driven expert, she supposed. She sighed, resigning herself to the task at hand.
created_at"2026-05-27T10:18:39.825Z" 5/27/2026, 10:18:39 AM
model"thedrummer/skyfall-36b-v2"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency203
moderation_latency(null)
generation_time23274
tokens_prompt923
tokens_completion1357
native_tokens_prompt875
native_tokens_completion1291
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached864
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)
usage0.00125485
router(null)
provider_responses
0
endpoint_id"1eb01ded-ae11-49e6-8aa6-3067584070bd"
id"chatcmpl-870110f9d01f5658"
is_byokfalse
latency203
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-1779877119-MQ4QQLSS7V6Aoxw10x56"
session_id(null)
api_type"completions"
id"gen-1779877119-40AtnPlW1KHSoQX59FTD"
upstream_id"chatcmpl-870110f9d01f5658"
total_cost0.00125485
cache_discount0.0002592
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
totalTags5
adverbTagCount0
adverbTags(empty)
dialogueSentences9
tagDensity0.556
leniency1
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount915
totalAiIsmAdverbs0
found(empty)
highlights(empty)
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)
83.61% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount915
totalAiIsms3
found
0
word"scanned"
count1
1
word"flicked"
count1
2
word"raced"
count1
highlights
0"scanned"
1"flicked"
2"raced"
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
narrationSentences59
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences59
filterMatches
0"watch "
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences64
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen48
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords916
ratio0
matches(empty)
75.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions5
unquotedAttributions1
matches
0"But more than that, she breathed in, there was something seriously supernatural swirling in the ether."
63.67% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions32
wordCount695
uniqueNames15
maxNameDensity1.73
worstName"Quinn"
maxWindowNameDensity3
worstWindowName"Quinn"
discoveredNames
Harlow1
Quinn12
Tube1
Richtung1
Eston1
Place1
Clingmans1
Porshe1
Warren5
Richt1
Kip1
Eva3
Magic1
Gathering1
Leary1
persons
0"Harlow"
1"Quinn"
2"Richtung"
3"Warren"
4"Richt"
5"Kip"
6"Eva"
7"Leary"
places
0"Eston"
1"Place"
globalScore0.637
windowScore0.667
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences44
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount916
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences64
matches(empty)
33.49% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs17
mean53.88
std14.4
cv0.267
sampleLengths
058
123
256
363
445
558
682
771
840
950
1059
1171
1243
1342
1450
1568
1637
99.32% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences59
matches
0"been tucked"
99.75% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs133
matches
0"was explaining"
1"was watching"
53.57% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount1
semicolonCount1
flaggedSentences2
totalSentences64
ratio0.031
matches
0"By 11, the station emptied, the tables scraped back, and only the crushed goblets left the wild rumpus; as if they'd been guests to nothing more than a raucous pub night."
1"She looked at her watch - 14:00, she'd best limp on in to the ME and see what Kip had cooked up, phone in hand, already on course for the morgue, the mess he'd made of the file and the shoddy fresh instagram photos locked in her father's camera."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount537
adjectiveStacks0
stackExamples(empty)
adverbCount17
adverbRatio0.03165735567970205
lyAdverbCount4
lyAdverbRatio0.0074487895716946
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences64
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences64
mean14.31
std10.77
cv0.752
sampleLengths
016
120
222
315
48
55
64
78
821
918
1023
1122
1218
1314
1431
1520
1622
1716
1827
1914
2021
2120
2234
2337
2414
2526
2618
2732
2841
2918
307
315
3249
333
347
359
365
377
389
392
405
416
428
433
4410
456
469
476
488
4942
98.44% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.671875
totalSentences64
uniqueOpeners43
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences56
matches
0"Just before closing yesterday, a"
1"Of course she'd be hauled"
2"Always talking about her esoteric"
ratio0.054
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount9
totalSentences56
matches
0"She popped the lid on"
1"Their not-dconsult dismissed, Quinn let"
2"He rubbed his temples and"
3"She narrowed her eyes and"
4"She looked at her watch"
5"Her mind raced, turning in"
6"She stared at the game"
7"He looked up from his"
8"She sighed, resigning herself to"
ratio0.161
100.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount33
totalSentences56
matches
0"Detective Harlow Quinn tilted her"
1"Another flick, and the flash"
2"The abandoned Tube station was"
3"Quinn scanned the trashed office."
4"This crime scene was...unexpected."
5"She popped the lid on"
6"Quinn's money was on an"
7"Their not-dconsult dismissed, Quinn let"
8"Warren was a developer and"
9"Warren jogged up and bumped"
10"He rubbed his temples and"
11"She narrowed her eyes and"
12"Warren rolled his eyes and"
13"DJed thumbprint, he pocketed and"
14"Quinn shook her head, disbelief"
15"The game was watching back."
16"She looked at her watch"
17"Warren had spoken."
18"Quinn knew what she needed"
19"This weighed like a lasso"
ratio0.589
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount2
totalSentences56
matches
0"If so, what kind of"
1"If she had to hear"
ratio0.036
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences25
technicalSentenceCount1
matches
0"She narrowed her eyes and tightened her fists, staring at Warren who was explaining."
25.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags5
uselessAdditionCount1
matches
0"Quinn shook, disbelief seeping in"
38.89% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags1
fancyCount1
fancyTags
0"He rubbed (rub)"
dialogueSentences9
tagDensity0.111
leniency0.222
rawRatio1
effectiveRatio0.222
89.0241%