Run: 2026-05-27-01KSMFB0XSPERAKNGR3H4TM34R

Run Details

Duration:
17.1s
Cost:
$0.001159
Provider:
Parasail

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
Detective Harlow Quinn gripped the steering wheel, her knuckles white as she swerved through the narrow London streets at breakneck speed. The wipers struggled against the relentless downpour, barely allowing her to make out the taillights of the Vauxhall Astra up ahead. She'd finally gotten a lead on that damn clique after months of dead ends. They'd been spotted by an informant down by the docks, but had bolted before the Met could move in. Now the detective had a chance to collar one of them. A golden opportunity in an otherwise frustrating chase. "I'm chasing a lead down Euston Road, requesting backup," Quinn barked into her radio. A burst of static. "Negative, Detective. All units are tied up responding to a commotion near Camden Town Station. Rather than you getting in my way, how about I send someone once we clear that area up, yeah?" Quinn cursed under her breath as she struggled to keep the Astra in her sights. Bloody incompetence. No way would she let lead slip through her fingers. Suddenly, the van made a sharp right and vanished into an alleyway between two abandoned buildings. Quinn screeched to a halt, grabbing her raincoat as she leapt from the car and sprinted after it on foot. The alley was dark and never-ending. Puddles splashed up as Harlow ran, making it nearly impossible to maintain her footing. Where the hell are you going? Abruptly, the alleyway disappeared and before Harlow had a chance to slow down, she found herself stepping off the curving edge into open expanse. She teetered on the ledge with nothing but blackness below. Her heart leapt into her throat as she dug her heels in and fought to recover her balance. Trembling, she looked down to see the roof of an underground platform several stories below - and the distinctive green neon sign of a Raven's Nest pointing up at her from the empty station beneath Trying to still her racing heart, Harlow crept forward and grabbed the iron railing, letting herself back onto solid ground. This was illogical. Soho was over 5km from here... But time's a funnel - and it was sink or swim. Harlow spied a nearby ladder leading down into the darkness below and began to climb, every nerve on high alert. At the bottom, she found herself in a dimly lit tunnel-lined by grimy yellow brick and dripping aerosol cans as far as she could see. She started forward, her eyes straining to adjust to the scant light. After another half mile, the détective came upon an abandoned station entrance, littered with pizza boxes, filth and crap strewn on the floor. Suddenly a dim light shone through a door at the end of a vacant platform and Quinn proceeded forward searching the room. She found herself in a narrow windowed room encased in metal. Inside passengers sat in stiff-inclined seats ready for the Railway 1983 doors to close. But no conductor could be found. Just as Quinn was about to turn back, she heard a faint voice drifting up from the platform through the open window. She crept closer - "Yes, Sir. As you say." Quinn listened to the conversation, her eyes scanning the empty train car. "No. Disposal has been slow. Soil refresh decks are below schedule. Can you move up that order? This is red-hot. The Jobkeeper waddles with spider legs in the day-night sky. Copy that. Call back in 6." Silence. Quinn waited, listened. Her breathing was the only sound. "Sir... 33 here." Pause. "Yes. I copy. Initiating Phase 2 in TBD. Will keep you updated on movement in the Major. Don't worry, this is under control, Sir. Wilco over." More silence. And then... "Hello?" Quinn called out, stepping cautiously onto the platform, her hand resting on her holstered pistol. "Police! Come forward - " The door suddenly slammed shut, thrusting them into deep shadow. Hard footsteps. Quinn spun around, drawing her gun with a practiced movement. But it was too late. The blunt end of a baton hit her right in the back of the head and everything went black, taking with it the last words she heard. "Knock-knock, Detective. I've been waiting for you."
created_at"2026-05-27T10:23:01.061Z" 5/27/2026, 10:23:01 AM
model"thedrummer/skyfall-36b-v2"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency255
moderation_latency(null)
generation_time16932
tokens_prompt1140
tokens_completion1056
native_tokens_prompt1027
native_tokens_completion929
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached496
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)
usage0.00115925
router(null)
provider_responses
0
endpoint_id"1eb01ded-ae11-49e6-8aa6-3067584070bd"
id"chatcmpl-80445a5c4189584b"
is_byokfalse
latency255
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-1779877381-FTSNv4loXdeHtP4t1LoY"
session_id(null)
api_type"completions"
id"gen-1779877381-HxN6B5oJc89gMwxNPh66"
upstream_id"chatcmpl-80445a5c4189584b"
total_cost0.00115925
cache_discount0.0001488
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
totalTags2
adverbTagCount0
adverbTags(empty)
dialogueSentences9
tagDensity0.222
leniency0.444
rawRatio0
effectiveRatio0
71.22% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount695
totalAiIsmAdverbs4
found
0
adverb"suddenly"
count3
1
adverb"cautiously"
count1
highlights
0"suddenly"
1"cautiously"
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)
64.03% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount695
totalAiIsms5
found
0
word"racing"
count1
1
word"scanning"
count1
2
word"silence"
count2
3
word"footsteps"
count1
highlights
0"racing"
1"scanning"
2"silence"
3"footsteps"
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
narrationSentences46
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount1
narrationSentences46
filterMatches(empty)
hedgeMatches
0"began to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences52
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen54
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords700
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions5
unquotedAttributions0
matches(empty)
62.89% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions24
wordCount574
uniqueNames10
maxNameDensity1.74
worstName"Quinn"
maxWindowNameDensity3
worstWindowName"Quinn"
discoveredNames
Harlow5
Quinn10
London1
Vauxhall1
Astra2
Met1
Raven1
Nest1
Trying1
Railway1
persons
0"Harlow"
1"Quinn"
2"Met"
3"Raven"
4"Nest"
places
0"London"
1"Vauxhall"
globalScore0.629
windowScore0.667
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences34
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount700
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences52
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs27
mean25.93
std13.7
cv0.528
sampleLengths
042
152
214
338
427
536
626
752
835
940
1020
1125
1235
1333
1420
1526
165
1712
1836
191
209
2130
224
2321
2422
2532
267
97.64% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences46
matches
0"been spotted"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs101
matches(empty)
32.97% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount2
semicolonCount0
flaggedSentences2
totalSentences52
ratio0.038
matches
0"Trembling, she looked down to see the roof of an underground platform several stories below - and the distinctive green neon sign of a Raven's Nest pointing up at her from the empty station beneath Trying to still her racing heart, Harlow crept forward and grabbed the iron railing, letting herself back onto solid ground."
1"But time's a funnel - and it was sink or swim."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount574
adjectiveStacks0
stackExamples(empty)
adverbCount15
adverbRatio0.02613240418118467
lyAdverbCount10
lyAdverbRatio0.017421602787456445
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences52
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences52
mean13.46
std10.33
cv0.767
sampleLengths
021
121
214
319
411
58
614
74
834
915
102
1110
1216
1320
146
1514
166
1724
1810
1918
2055
213
226
2311
2420
2525
2612
2723
2822
2911
3014
316
3222
334
345
3512
3636
371
383
396
404
4126
422
432
4416
455
4610
472
4810
495
100.00% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats0
diversityRatio0.6538461538461539
totalSentences52
uniqueOpeners34
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences40
matches
0"Suddenly, the van made a"
1"Abruptly, the alleyway disappeared and"
2"Suddenly a dim light shone"
ratio0.075
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount8
totalSentences40
matches
0"She'd finally gotten a lead"
1"They'd been spotted by an"
2"She teetered on the ledge"
3"Her heart leapt into her"
4"She started forward, her eyes"
5"She found herself in a"
6"She crept closer -"
7"Her breathing was the only"
ratio0.2
100.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount26
totalSentences40
matches
0"Detective Harlow Quinn gripped the"
1"The wipers struggled against the"
2"She'd finally gotten a lead"
3"They'd been spotted by an"
4"A golden opportunity in an"
5"Quinn barked into her radio"
6"A burst of static."
7"Quinn cursed under her breath"
8"Quinn screeched to a halt,"
9"The alley was dark and"
10"Puddles splashed up as Harlow"
11"She teetered on the ledge"
12"Her heart leapt into her"
13"This was illogical."
14"Soho was over 5km from"
15"Harlow spied a nearby ladder"
16"She started forward, her eyes"
17"She found herself in a"
18"She crept closer -"
19"Quinn listened to the conversation,"
ratio0.65
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount2
totalSentences40
matches
0"Now the detective had a"
1"Just as Quinn was about"
ratio0.05
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences27
technicalSentenceCount1
matches
0"Trembling, she looked down to see the roof of an underground platform several stories below - and the distinctive green neon sign of a Raven's Nest pointing up …"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags2
uselessAdditionCount0
matches(empty)
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount2
fancyTags
0"Quinn barked (bark)"
1"Quinn called out (call out)"
dialogueSentences9
tagDensity0.222
leniency0.444
rawRatio1
effectiveRatio0.444
90.9582%