Run: 2026-05-27-01KSMET25CV9F53HWHRKNMEBC2

Run Details

Duration:
15.6s
Cost:
$0.000943
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
The flickering neon light at the entrance had already snapped off by the time I arrived, the karate-school splotch splintering across the cardboard sign made of scraps held together with duct tape. The sign informed the public that the basic 18-week program was a paltry sum of £100+VAT. I was here for something much different. My heightened sense of smell had picked up a faint fleeting scent in the air, and I'd followed it all the way to North Camden. Nuhfakh, I thought, beelining it up the creaky stairs to the second floor. And there she was. Quinn, my latest supervisor, stood to the side of the squared-off space. She ran a hand over her closely cropped hair, jaw tight as she nodded. I'd never seen her like this before. Not even after what happened with Morse. Like she was seeing something I wasn't. Quinn stepped closer to me and the light hit her glasses, casting an eerie reflection over her face. "It's them, isn't it?" I asked, acknowledging that I no longer questioned what happened in my presence. It had all shaken my reality too far, turned everything I knew on it's upside down. "No," Quinn said and wiped a bead of sweat from her forehead. "This isn't them. I've got a bad feeling about this one, Eva." That was all I needed. I rose from my duffel and let the satchel find its home against my back. Finger brushing against the compartment that held the Veil Compass. A tool that helped me navigate the underground market and stayed in place when the market shifted locations. Realize what you're seeing. Shake off the preconceived notions. Look to the edges. Like those final words of Aurora's before the darkness took her. Her twisted approach to accuracy. Always trust the eye, not the mind. I stepped to the center of the room and observed. Red and blue lights bounced against the bruises on __________'s shredded face. I played the scene in my mind, piecing together events before I even knew what had transpired.The first line of purple bruising on his left forearm. Faint and old, it had served as a distraction, a way to make you question the sequence of events. Read it like a book. He wasn't the target. The Persian rug underneath my boots had the lovely scent of spices, a bleak image against the American flag behind him. Swollen lips and contorted arms. There was a rag next to his bloodied fist. "I don't think this was a mugging." Quinn didn't offer a comeback and I felt her sidling up next to me. She moved slower, this case feeling different in her gut. "Look there." I pointed, not wanting to sully the scene in case the case ended up going to approroiate authorities. "That cherry Gamashia brand ramen. The type of glue on the car, the way it reacts with the bruises on his knuckles when the adhesive interacts with water, but keeps the material together even on impact...it's dated." I pulled out a stapled folder I had brought with me on the train. "This plays with biochemistry and genetic engineering. The manufacturer or company my colleagues here at the museum are researching has been in production for over a century. You can't buy it outside the black market. Find the company, follow the money." I held out the handout, passing the leaflet to her. Underneath the milky moon, ghosts stretched long and stark. ________ understood his twisted role, using our knowledge of herbs and natural remedies in ways meant to heal but instead hindered, controlled. We'd seen how they were recruiting from the gangs, I noted, watching Quinn reading down the thin strip of paper. From the drug users, the athlete, the influencer, they fed off their image. But this felt different. Quinn stood. Frowned. Faced the murky lake of water speckled with glittery light. "It's not him," she said, tucking the paper into the front pocket of her jacket. "It's _________, isn't it?" I watched her go, not feeling the pangs of loneliness yet after the distance I had put between myself and her.
created_at"2026-05-27T10:13:45.272Z" 5/27/2026, 10:13:45 AM
model"thedrummer/skyfall-36b-v2"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency170
moderation_latency(null)
generation_time15500
tokens_prompt923
tokens_completion1011
native_tokens_prompt875
native_tokens_completion901
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)
usage0.00094285
router(null)
provider_responses
0
endpoint_id"1eb01ded-ae11-49e6-8aa6-3067584070bd"
id"chatcmpl-9911cd751a4b6cf2"
is_byokfalse
latency170
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-1779876825-leid0oPiQ2fET0mMDhXx"
session_id(null)
api_type"completions"
id"gen-1779876825-YvSTEfG7eFBtywjjEwrf"
upstream_id"chatcmpl-9911cd751a4b6cf2"
total_cost0.00094285
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
totalTags4
adverbTagCount0
adverbTags(empty)
dialogueSentences9
tagDensity0.444
leniency0.889
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount688
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)
70.93% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount688
totalAiIsms4
found
0
word"sense of"
count1
1
word"fleeting"
count1
2
word"navigate"
count1
3
word"stark"
count1
highlights
0"sense of"
1"fleeting"
2"navigate"
3"stark"
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
narrationSentences49
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences49
filterMatches(empty)
hedgeMatches(empty)
77.91% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences54
gibberishSentences2
adjustedGibberishSentences2
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount2
maxSentenceWordsSeen41
ratio0.037
matches
0"Red and blue lights bounced against the bruises on __________'s shredded face."
1"________ understood his twisted role, using our knowledge of herbs and natural remedies in ways meant to heal but instead hindered, controlled."
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans6
markdownWords6
totalWords688
ratio0.009
matches
0"_"
1"_"
2"_"
3"_"
4"_"
5"_"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions4
unquotedAttributions0
matches(empty)
98.01% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions14
wordCount577
uniqueNames9
maxNameDensity1.04
worstName"Quinn"
maxWindowNameDensity1.5
worstWindowName"Quinn"
discoveredNames
North1
Camden1
Morse1
Veil1
Compass1
Aurora1
Persian1
American1
Quinn6
persons
0"Aurora"
1"Quinn"
places
0"North"
globalScore0.98
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences37
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount688
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences54
matches
0"acknowledging that I"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs18
mean38.22
std22.7
cv0.594
sampleLengths
093
14
247
351
424
548
636
776
835
97
1024
1157
1255
1341
1437
1513
1619
1721
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences49
matches(empty)
71.79% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs104
matches
0"was seeing"
1"were recruiting"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences54
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount580
adjectiveStacks0
stackExamples(empty)
adverbCount12
adverbRatio0.020689655172413793
lyAdverbCount3
lyAdverbRatio0.005172413793103448
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences54
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences54
mean12.74
std8.43
cv0.662
sampleLengths
032
116
27
325
413
54
612
714
87
97
107
1118
1217
1316
1412
1512
165
1715
1810
1918
204
215
224
2311
245
257
2610
2712
2826
2919
305
314
3221
335
349
357
3614
3710
3820
3937
4014
4141
4210
439
4422
4520
4613
474
482
491
94.44% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.6111111111111112
totalSentences54
uniqueOpeners33
70.92% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences47
matches
0"Always trust the eye, not"
ratio0.021
66.81% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount18
totalSentences47
matches
0"I was here for something"
1"My heightened sense of smell"
2"She ran a hand over"
3"I'd never seen her like"
4"I asked, acknowledging that I"
5"It had all shaken my"
6"I rose from my duffel"
7"Her twisted approach to accuracy."
8"I stepped to the center"
9"I played the scene in"
10"He wasn't the target."
11"She moved slower, this case"
12"I pointed, not wanting to"
13"I pulled out a stapled"
14"I held out the handout,"
15"We'd seen how they were"
16"she said, tucking the paper"
17"I watched her go, not"
ratio0.383
100.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount30
totalSentences47
matches
0"The flickering neon light at"
1"The sign informed the public"
2"I was here for something"
3"My heightened sense of smell"
4"Nuhfakh, I thought, beelining it"
5"Quinn, my latest supervisor, stood"
6"She ran a hand over"
7"I'd never seen her like"
8"Quinn stepped closer to me"
9"I asked, acknowledging that I"
10"It had all shaken my"
11"Quinn said and wiped a"
12"That was all I needed."
13"I rose from my duffel"
14"Finger brushing against the compartment"
15"A tool that helped me"
16"Her twisted approach to accuracy."
17"I stepped to the center"
18"I played the scene in"
19"He wasn't the target."
ratio0.638
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences47
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences26
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags4
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags3
fancyCount0
fancyTags(empty)
dialogueSentences9
tagDensity0.333
leniency0.667
rawRatio0
effectiveRatio0
91.6937%