Run: 2026-10-13-01M4TB212F2V3H3YM9ZYCGPSJ2

Run Details

Duration:
1m 11s
Cost:
$0.061094
Provider:
Fireworks

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
The green neon above the Raven's Nest bled across the wet pavement, and Detective Harlow Quinn had watched it drip for three hours from a doorway opposite. Rain needled the collar of her coat. Her salt-and-pepper crop lay plastered flat, and the leather strap of her watch had gone dark with water, the face reading half eleven when she tilted it toward the light. The full moon sat somewhere behind the cloud, a bruise-coloured glow over the Soho rooftops. The bar door opened. Tomás Herrera stepped out with a leather satchel hugged to his chest, collar up, moving like a man late for a train. Then he saw her. He ran. "Herrera! Met Police. Stop!" He didn't stop. He cut left into an alley, and Quinn went after him, boots striking water, three hours of stillness burning out of her knees in the first fifty yards. Twenty-nine against forty-one. She'd chased worse odds. The alley spat them onto a back street. Herrera shoved a wheelie bin sideways without breaking stride; it crashed across her path and she went over it rather than round, palm scraping brick, momentum carrying her through. He glanced back. The Saint Christopher at his throat caught a streetlamp, a small gold flash in the rain. "You're making this worse, Herrera!" "Go home, Detective!" He didn't slow. "There's nothing for you at the end of this." She closed the gap on the next corner. Her fingers found his sleeve, wet wool, the ridge of the old scar along his forearm under her grip. He wrenched round and twisted free with a strength she hadn't expected, and the motion spun him into a shuttered shopfront. For a breath they were face to face, both of them heaving, rain running off his dark curls. "You don't know what you're chasing," he said. "Then stand still and explain it." He ducked under her arm and ran north. She followed the only way the streets let him run. Past the closed theatres, across the empty breadth of Euston Road where a night bus groaned past and drenched them both in its wake. Her lungs burned. Her watch read midnight, then ten past. The crowds thinned to nothing. Camden rose ahead, shuttered stalls and dark shopfronts, and the moon broke the cloud for the first time, fat and white over the rooftops. Herrera veered off the high street toward a side road fenced with hoardings. Quinn rounded the corner six seconds behind him and stopped. A disused Underground station sat behind the boards, its roundel stripped to a faded ghost, the tiling above the entrance cracked. A door stood open in the hoardings where no door should have been, and warm air breathed out of it, carrying a smell she couldn't place. Copper. Burnt herbs. Something underneath both that raised the hair on her arms. Herrera stood at a second doorway beyond the hoardings, palm extended to a man in a long grey coat. Something small and yellowed lay in his hand. Carved. The grey-coated man looked at it, then at Quinn, then stood aside. Herrera looked back at her. Not triumphant. Almost sorry. "Turn around, Detective. Whatever you think this is, it isn't. This place isn't yours." He went through the door and down, and the dark took him. Quinn reached the doorway with her warrant card already out. "Metropolitan Police. That man is wanted for questioning." The grey-coated man looked at the card the way a man looks at a bus ticket for the wrong city. "Token." "My authority is—" "Token." He held out his hand. Up close, his eyes had an odd sheen, like wet stone, and his shadow on the hoarding behind him didn't quite match the angle of the lamplight seeping up the stairs. Quinn filed it under bad lighting and worse drugs and kept her jaw set. "Bone. Carved. Everyone below carries one." "I don't have one." "Then you don't go below." She tried her radio. Static filled the earpiece, thick as static shouldn't be, and underneath it something that might have been a voice if voices ran backwards. She killed it. The warmth from the stairwell pressed against her wet clothes. From somewhere far down came sounds that weren't quite music and weren't quite a crowd, a murmur with too many textures in it. "How long is it open?" "Door closes when the moon goes." The grey coat shifted. "After that, there's no door at all. Not for a month. Not here." She thought of the evidence bag that wasn't in her pocket, the file on her desk with the clique's names in it, Herrera's among them, and every thread she'd pulled for eight months coming loose in her hands on a Camden side street. She thought of calling it in, waiting, doing it properly. By morning this place would be hoardings and a dead station again. She knew it the way she knew the rain on her neck, without a single rational reason. "Then name a price," she said. "Everyone has one." The man studied her. The lamplight from below flickered, though there was no wind. "Something of the dead," he said. "Carried long. That's the price for the tokenless." Her hand went to her inside pocket before she'd decided to move it. The biro lay there, cheap plastic, the cap chewed into ridges. Morris's pen. He'd pressed it into her hand three years ago, the last night, complaining she'd stolen his good one. She'd carried it every shift since, through the inquiry, through the unexplained circumstances, through the closed file. Her thumb found the bite marks by memory. The smell rose from the stairwell again. Copper and burnt herbs. It was the smell from the corridor where they'd found Morris, the detail she'd never put in any report because there was no box on the form for it. For three years she'd told herself she believed in evidence. Evidence was down those stairs. So was Herrera. So, possibly, was the shape of the thing that had taken her partner and left no fingerprints on the world. She looked at the pen. The rain ticked against the hoardings. Down below, the murmur swelled and settled, and once, faintly, she heard Herrera's voice, too deep in the dark to make out words. "Take it," she said. The pen vanished into the grey coat. The man stood aside, and his shadow moved a half-second late, and she chose not to see it. "If you're lost below," he said, "no one comes looking. The market doesn't answer to your law." "Everything answers to the law." He laughed, once, and it wasn't unkind, and that was worse. She went through the door. Old stairs descended under her boots, green tiles sweating on the walls, a Way Out sign pointing up at her back with its arrow half-hanging. The warmth thickened. The murmur resolved into voices, haggling, laughing, one of them singing in no language she knew. Lamplight pooled at the bottom of the stairs, gold and steady, and no flame anywhere to make it. The old ticket hall opened up in front of her. Stalls crowded the space where commuters once queued, built from driftwood and black canvas and bones she told herself were animal. Jars lined a trestle, things floating in them that caught the lamplight and seemed to turn toward her as she passed. A woman with moth wings tattooed across her face weighed powder on brass scales. A man in a butcher's apron sold teeth from a velvet cloth, and his customers examined them like jewellery. No one looked at Quinn. That frightened her more than attention would have. She scanned the crowd with a detective's discipline, stall by stall, face by face. A flash of olive skin. A leather satchel swinging at a hip. Herrera, forty yards in, glancing back over his shoulder to see if the dark had swallowed her or spat her out. Their eyes met across the market. Quinn stepped down off the last stair and went in after him.
created_at"2026-10-13T09:56:18.648Z" 10/13/2026, 9:56:18 AM
model"fireworks/ember-1-20260923"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency599
moderation_latency(null)
generation_time70661
tokens_prompt1104
tokens_completion4504
native_tokens_prompt1087
native_tokens_completion4051
native_tokens_completion_images(null)
native_tokens_reasoning2329
native_tokens_cached1086
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)
usage0.0610938
router(null)
user_agent"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer(null)
request_id"req-1791885378-awlQXsuPWm533LXOk886"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1791885378-Am8xOeiDG8Y4Xc9UWAfj"
upstream_id"chatcmpl-ffc652964b894f7689c90ff3f1a9c6ea"
provider_responses
0
endpoint_id"b89a2f05-4051-4446-a9b0-7bc8ae7b7c90"
id"chatcmpl-ffc652964b894f7689c90ff3f1a9c6ea"
is_byokfalse
latency599
model_permaslug"fireworks/ember-1-20260923"
provider_name"Fireworks"
status200
total_cost0.0610938
cache_discount0.0029322
upstream_inference_cost0
provider_name"Fireworks"
response_cache_source_id(null)
data_region"global"
workspace_id"97e315e5-d303-487d-83c1-83180e8a13d4"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags8
adverbTagCount0
adverbTags(empty)
dialogueSentences24
tagDensity0.333
leniency0.667
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1339
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)
77.60% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1339
totalAiIsms6
found
0
word"warmth"
count2
1
word"flickered"
count1
2
word"resolved"
count1
3
word"velvet"
count1
4
word"scanned"
count1
highlights
0"warmth"
1"flickered"
2"resolved"
3"velvet"
4"scanned"
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
narrationSentences102
matches(empty)
86.83% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount2
hedgeCount2
narrationSentences102
filterMatches
0"watch"
hedgeMatches
0"tended to"
1"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences118
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen43
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1339
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions10
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions32
wordCount1199
uniqueNames15
maxNameDensity0.75
worstName"Herrera"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Raven1
Nest1
Detective1
Harlow1
Quinn8
Soho1
Herrera9
Saint1
Christopher1
Euston1
Road1
Underground1
Camden2
Morris2
Way1
persons
0"Raven"
1"Nest"
2"Harlow"
3"Quinn"
4"Herrera"
5"Saint"
6"Christopher"
7"Morris"
8"Way"
places
0"Soho"
1"Euston"
2"Road"
globalScore1
windowScore1
75.37% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences67
glossingSentenceCount2
matches
0"quite match the angle of the lamplight seeping up the stairs"
1"quite music and weren't quite a crowd, a murmur with too many textures in it"
2"quite a crowd, a murmur with too many textures in it"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1339
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences118
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs46
mean29.11
std26.62
cv0.914
sampleLengths
079
130
22
34
438
556
65
715
866
98
106
118
1273
1323
1460
1540
169
1714
1812
1918
2021
213
2257
234
245
2563
265
2723
2882
299
3014
3114
3269
3378
3434
354
3625
3717
385
3911
4067
4110
4288
4347
446
4512
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences102
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs197
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount1
flaggedSentences1
totalSentences118
ratio0.008
matches
0"Herrera shoved a wheelie bin sideways without breaking stride; it crashed across her path and she went over it rather than round, palm scraping brick, momentum carrying her through."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1208
adjectiveStacks0
stackExamples(empty)
adverbCount30
adverbRatio0.024834437086092714
lyAdverbCount4
lyAdverbRatio0.0033112582781456954
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences118
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences118
mean11.35
std8.26
cv0.728
sampleLengths
027
17
230
315
44
522
64
72
84
93
1028
113
124
138
1429
153
1616
175
186
199
208
2119
2221
2318
248
256
268
2710
2824
293
307
315
3224
3313
3410
3521
3626
371
382
3910
4019
418
421
4312
445
452
462
4714
4812
4910
65.54% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats11
diversityRatio0.4491525423728814
totalSentences118
uniqueOpeners53
37.04% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences90
matches
0"Then he saw her."
ratio0.011
86.67% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount30
totalSentences90
matches
0"Her salt-and-pepper crop lay plastered"
1"He didn't stop."
2"He cut left into an"
3"She'd chased worse odds."
4"He glanced back."
5"He didn't slow"
6"She closed the gap on"
7"Her fingers found his sleeve,"
8"He wrenched round and twisted"
9"He ducked under her arm"
10"She followed the only way"
11"Her lungs burned."
12"Her watch read midnight, then"
13"He went through the door"
14"He held out his hand"
15"She tried her radio."
16"She killed it."
17"She thought of the evidence"
18"She thought of calling it"
19"She knew it the way"
ratio0.333
32.22% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount77
totalSentences90
matches
0"The green neon above the"
1"Rain needled the collar of"
2"Her salt-and-pepper crop lay plastered"
3"The full moon sat somewhere"
4"The bar door opened."
5"Tomás Herrera stepped out with"
6"He didn't stop."
7"He cut left into an"
8"She'd chased worse odds."
9"The alley spat them onto"
10"Herrera shoved a wheelie bin"
11"He glanced back."
12"The Saint Christopher at his"
13"He didn't slow"
14"She closed the gap on"
15"Her fingers found his sleeve,"
16"He wrenched round and twisted"
17"He ducked under her arm"
18"She followed the only way"
19"Her lungs burned."
ratio0.856
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences90
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences54
technicalSentenceCount2
matches
0"Static filled the earpiece, thick as static shouldn't be, and underneath it something that might have been a voice if voices ran backwards."
1"She thought of the evidence bag that wasn't in her pocket, the file on her desk with the clique's names in it, Herrera's among them, and every thread she'd pull…"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags8
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags5
fancyCount0
fancyTags(empty)
dialogueSentences24
tagDensity0.208
leniency0.417
rawRatio0
effectiveRatio0
88.7089%