Run: 2026-05-27-01KSMETXE8HQMED8M0ZPHJGEES

Run Details

Duration:
15.1s
Cost:
$0.001167
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 pressed herself against the damp brick wall, peering around the corner. The male suspect had darted down this alley seconds ago. She blinked rain from her lashes, her leather jacket plastered to her back, but she didn't remove her eyes from the wet cobblestones. Quinn amended her grip on the gun in her holster, and inched forward. Her foot splashed through a puddle, the cold water seeping into her boot. She hissed under her breath, cursing. She was getting too old for this shit. Low and steady, her colleague, Detective Jake Thompson, radioed, "Sighted him crossing Chancellor Street. Oh, shite. He's heading underground! قلبي said that abandoned Tube station." The damp alley spit Quinn onto a bustling side street, cars splashing through puddles. She glimpsed Moreau weaving through the crowd across the way, his bobbing red hair like a beacon. As she sprinted after him, the pedestrian road suddenly yawned open, the mouth of Tremorangate Station gaping like a monstrous, open maw. Thompson cursed under his breath. "I don't wanna go down there, boss. You thinking what I'm thinking?" Quinn swiped at the rain running down her face. In the distance, a flash of red disappeared down the station stairs, but her cramped chest barely allowed her lungs to fill as her breath came in short pants. Thompson's eyes also darted to the station entrance, and then back to Quinn. "So, uhm, we're not stopping her, right? This is Quinn's lead. She's chasing, you and me have got the back door on lock. Let's go over to the alley, get it set up, yeah?" She pursed her lips, glancing over at her officer, who took a slow, deep breath and nodded. "Veil Market." They both said it at the same time, the horror in their voices echoing off the alley walls. Her mind raced. Veil Market, lurked just beyond that station entrance. She remembered the last time Moreau dragged them through its twisting tunnels, delved down through the infernal dark to the maddening markets. She shook her head, taking a deep breath. "No. We can't. Jake, if Moreau gets away, this case...this lead..." The rain poured down on them. Quinn flattened her lips. "You see that flash? Muddy, dark red shirt. Don't let him out, and if he gets away, you shoot him on sight. Understand?" Thompson merely nodded and ran. Thompson sprinted to the alley, tightly gripping his service weapon, a cold stream of sweat trickling down his backbone. The clock on the wall read 2:15 AM. Shit. Should have brought a flashlight. The rain poured onto him, turning the sidewalks into rivers, making his boots slip on the wet concrete. His stomach heaved. She's in there, boss. He followed her lead, but his steel-trapped heart, it just wasn't in this. Thompson shot a look at his boss, red hair plastered to her face. "I don't like it, boss. Quinn, this looks familiar, Jim. Remember Moreau's last stunt? The thing said--" "What about it?" She frowned. "Shove that crap where the sun doesn't shine, would you?" "I'm just saying, boss." His eyes darted to the station entrance. "We shouldn't--." "Silence, Jake," interrupted Moreau. How long had that . . . thing . . . spoken through Moreau and when did Moreau grow so spiteful. " I haven't got time for one of your alarms." Quinn scraped her teeth over a hangnail, pondering, before brushing off her sleeve and squaring her shoulders. "Let's go, Jake. We don't have time to wait." Thompson followed his sister, silently cursing, and as he hit the grey steps, a blood-chilling shriek rang out in the darkness.
created_at"2026-05-27T10:14:13.204Z" 5/27/2026, 10:14:13 AM
model"thedrummer/skyfall-36b-v2"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency252
moderation_latency(null)
generation_time15029
tokens_prompt1140
tokens_completion923
native_tokens_prompt1027
native_tokens_completion867
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached304
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)
usage0.00116725
router(null)
provider_responses
0
endpoint_id"1eb01ded-ae11-49e6-8aa6-3067584070bd"
id"chatcmpl-ae155c2be0b67ac0"
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-1779876853-kJJmMD3xne9WbYAbRegw"
session_id(null)
api_type"completions"
id"gen-1779876853-Ashk9FEa6FAj08LDOixI"
upstream_id"chatcmpl-ae155c2be0b67ac0"
total_cost0.00116725
cache_discount0.0000912
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)
dialogueSentences14
tagDensity0.286
leniency0.571
rawRatio0
effectiveRatio0
83.28% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount598
totalAiIsmAdverbs2
found
0
adverb"suddenly"
count1
1
adverb"tightly"
count1
highlights
0"suddenly"
1"tightly"
80.00% AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions(empty)
found
0"Thompson"
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
24.75% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount598
totalAiIsms9
found
0
word"beacon"
count1
1
word"maw"
count1
2
word"echoing"
count1
3
word"raced"
count1
4
word"delved"
count1
5
word"stomach"
count1
6
word"familiar"
count1
7
word"silence"
count1
8
word"chilling"
count1
highlights
0"beacon"
1"maw"
2"echoing"
3"raced"
4"delved"
5"stomach"
6"familiar"
7"silence"
8"chilling"
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
narrationSentences41
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences41
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences50
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen34
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords605
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions5
unquotedAttributions0
matches(empty)
71.52% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions26
wordCount446
uniqueNames9
maxNameDensity1.57
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Harlow1
Quinn7
Detective2
Jake1
Thompson7
Moreau5
Tremorangate1
Station1
Market1
persons
0"Harlow"
1"Quinn"
2"Detective"
3"Jake"
4"Thompson"
5"Moreau"
6"Market"
places
0"Station"
globalScore0.715
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences29
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount605
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences50
matches(empty)
83.41% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs22
mean27.5
std12.15
cv0.442
sampleLengths
047
140
225
353
417
538
647
717
820
933
1019
1133
125
1333
1418
1520
1630
1715
1813
1935
2026
2121
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences41
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount1
totalVerbs79
matches
0"was getting"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences50
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount446
adjectiveStacks0
stackExamples(empty)
adverbCount13
adverbRatio0.02914798206278027
lyAdverbCount5
lyAdverbRatio0.011210762331838564
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences50
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences50
mean12.02
std7.51
cv0.625
sampleLengths
014
110
223
313
413
56
68
725
814
917
1022
115
1212
139
1429
1513
1634
1717
1820
193
208
2122
228
2311
246
254
2623
275
2819
298
301
315
3218
333
344
3513
3613
3717
385
3910
4011
412
424
435
442
4510
4610
4717
489
4921
80.67% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.52
totalSentences50
uniqueOpeners26
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences37
matches(empty)
ratio0
68.65% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount14
totalSentences37
matches
0"She blinked rain from her"
1"Her foot splashed through a"
2"She hissed under her breath,"
3"She was getting too old"
4"She glimpsed Moreau weaving through"
5"She pursed her lips, glancing"
6"They both said it at"
7"Her mind raced."
8"She remembered the last time"
9"She shook her head, taking"
10"His stomach heaved."
11"She's in there, boss."
12"He followed her lead, but"
13"His eyes darted to the"
ratio0.378
41.08% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount31
totalSentences37
matches
0"Detective Harlow Quinn pressed herself"
1"The male suspect had darted"
2"She blinked rain from her"
3"Quinn amended her grip on"
4"Her foot splashed through a"
5"She hissed under her breath,"
6"She was getting too old"
7"The damp alley spit Quinn"
8"She glimpsed Moreau weaving through"
9"Thompson cursed under his breath."
10"Quinn swiped at the rain"
11"Thompson's eyes also darted to"
12"She pursed her lips, glancing"
13"They both said it at"
14"Her mind raced."
15"Veil Market, lurked just beyond"
16"She remembered the last time"
17"She shook her head, taking"
18"The rain poured down on"
19"Quinn flattened her lips."
ratio0.838
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences37
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences19
technicalSentenceCount1
matches
0"She pursed her lips, glancing over at her officer, who took a slow, deep breath and nodded."
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
totalTags1
fancyCount0
fancyTags(empty)
dialogueSentences14
tagDensity0.071
leniency0.143
rawRatio0
effectiveRatio0
84.4453%