Run: 2026-10-13-01M4TBT3RD2P9X4MJAMJ0C482Q

Run Details

Duration:
1m 59s
Cost:
$0.097634
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 had bled into the wet cobbles long before Tomás Herrera gave her a reason to move. Quinn stood in a doorway opposite, collar turned up, six hours of surveillance settled into her shoulders like damp sand. Her coffee had gone cold at ten. Her watch read 23:47. Rain threaded through the neon light and stitched the street green, then black, then green again. The bar door opened. Herrera stepped out, curls already flattening in the rain, and something tipped him — a look from the doorman, a phone call from inside. His gaze swept the street and found her doorway. Found her. Recognition moved across his face like a blind drawn down. He ran. Quinn broke cover. "Herrera!" He cut left into Berwick Street, shoulder-checking a shuttered stall, sending a tarpaulin billowing. She took the corner low, palm skimming wet brick, and gained on him through the market passage. He was fit. She was precise. Eighteen years of this and her body ran the arithmetic without asking — his stride, her stride, the distance closing by inches at every junction. "You're making a mistake, Detective!" "Then stop and correct me!" He kicked through a gap between two wheelie bins. She went over them, landed, kept her feet. His medallion swung loose of his collar, Saint Christopher catching a streetlight for half a second before the rain took him again. Tottenham Court Road. He dropped down the station stairs three at a time and vaulted the gateline. A member of staff rose from his stool. Quinn held the warrant card up without breaking stride. "Police. Hold that gate." Down the escalator, two steps at a time, hand trailing the rail. The platform exhaled a northbound train as she hit the tiles. Herrera went in through the far doors; she took the nearest ones and watched him through the glass into the next carriage — his face strobing against the tunnel dark, one hand closed around the medallion at his throat. A drunk slept across three seats. A woman with a pram stared at her own reflection. Nobody looked at the man in the next car. Camden Town. The doors chimed and Herrera slipped out at the last instant. Quinn shouldered through as they closed, her coat snagging, tearing free. Up the escalators. Out into the rain again, the high street all shuttered fronts and sodium glare, the canal lock black under the bridge. He turned off between a chicken shop and a wall of old brick, and vanished. She reached the alley mouth at a walk, weapon-side hand loose, breathing controlled. A grille in the brickwork stood open that should have been locked. Behind it, stairs went down. Old tiling, pre-war cream and green, no roundel, no station name. No station she knew of had ever stood here. Her radio gave her static and nothing else. She checked her watch. 00:02. On the wall beside the grille, someone had chalked a symbol. A circle bitten through by a crooked line. She had seen it before — photographed on a skirting board in a flat in Peckham, three years ago, in the file she'd memorised against orders. The room where they'd found Morris. The room nobody had ever explained. Rain ran off her cropped hair and down her neck. Below, warm air rose up the stairs, carrying sound. Voices. Many of them. She went down. The tunnel narrowed, then widened, pipes sweating along the ceiling, cables stapled to brick in bundles thick as her wrist. The dark ahead wasn't dark. It was amber. The passage opened onto a platform, and the platform opened onto everything. Stalls filled the track bed, packed shoulder to shoulder down the length of the station. Lamps strung on cable threw light the colour of weak tea over hundreds of people dressed wrong for any decade she could name. A woman weighed something in a brass scale that moved against the weight. Jars on a trestle held light that pressed itself against the glass. A man turned to watch her pass, and his mouth had too much in it. At the tunnel mouth stood a warden — tall, grey, a long coat, eyes the flat sheen of coins at the bottom of a fountain. "Token." Forty feet ahead, Herrera lifted a cord from inside his shirt. A disc of yellowed bone hung from it, no bigger than a two-pound coin. The warden's people waved him through. He glanced back once. Not triumph on his face. Warning. Then the crowd folded over him. Quinn reached the gate. "Token." "Metropolitan Police." She opened the warrant card, held it level with his eyes. He didn't look at it. "That buys nothing down here. Token, or turn round." The smell reached her then, threading under the lamp smoke and the damp — burnt copper, sharp and hot at the back of her throat. For one second she stood in the Peckham flat again. Morris on the floor. The walls wrong. The report she'd written with half of it left out because half of it was impossible. Her watch had stopped. The second hand sat dead at twelve. Behind her: the stairs, the dead radio, streets where backup would arrive and find an alley, a locked grille, nothing. Ahead: the clique's fixer, the man who patched knife wounds off the books and knew who held the knives, shrinking into light and crowd. Three months of surveillance ending at a gate with nothing to show but a stopped watch and a chalk mark. Footsteps came up the tunnel behind her. Three figures, hoods up against rain that no longer fell, bone tokens already dangling from their fists. They moved to pass her. Quinn made the decision the way she made all of them — quickly, completely, no rehearsal. She stepped aside, let them reach the gate, and fell in at the rear one's shoulder. Collar up. Pace matched. Head down to the height of the crowd. The warden's coin-flat gaze slid across the three of them, across her, and kept moving. The market took her in. Noise closed over her head — a stallholder calling prices in a language with too few vowels, a buyer haggling over a box that haggled back. She kept to the edge of the flow, hand loose at her side, eyes working the crowd the way she'd worked a thousand crowds at football matches and funerals and cordons. Looking for the things that didn't fit. There. Forty yards on, a glint at a throat. Gold against olive skin, catching lamplight between a stall of bottled light and a man selling teeth laid out on velvet. Curls. The scar along the left forearm as a hand reached up to pull a hood higher. Herrera thought he'd lost her at the gate. He wasn't running any more. He was walking, unhurried, a man home among his own. Quinn moved off the wall and went after him.
created_at"2026-10-13T10:09:27.832Z" 10/13/2026, 10:09:27 AM
model"fireworks/ember-1-20260923"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency457
moderation_latency(null)
generation_time119389
tokens_prompt1104
tokens_completion7249
native_tokens_prompt1087
native_tokens_completion6487
native_tokens_completion_images(null)
native_tokens_reasoning5004
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)
usage0.0976338
router(null)
user_agent"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer(null)
request_id"req-1791886167-j0XYKEuHbVN3bhceGe3N"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1791886167-SbzVMDhidnPylXwISa9O"
upstream_id"chatcmpl-ad16081d849149de8c619181b0b08a8d"
provider_responses
0
endpoint_id"b89a2f05-4051-4446-a9b0-7bc8ae7b7c90"
id"chatcmpl-ad16081d849149de8c619181b0b08a8d"
is_byokfalse
latency457
model_permaslug"fireworks/ember-1-20260923"
provider_name"Fireworks"
status200
total_cost0.0976338
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
totalTags1
adverbTagCount0
adverbTags(empty)
dialogueSentences8
tagDensity0.125
leniency0.25
rawRatio0
effectiveRatio0
91.33% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1154
totalAiIsmAdverbs2
found
0
adverb"quickly"
count1
1
adverb"completely"
count1
highlights
0"quickly"
1"completely"
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)
82.67% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1154
totalAiIsms4
found
0
word"weight"
count1
1
word"footsteps"
count1
2
word"glint"
count1
3
word"velvet"
count1
highlights
0"weight"
1"footsteps"
2"glint"
3"velvet"
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
narrationSentences106
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount3
hedgeCount0
narrationSentences106
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences113
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen38
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1162
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions1
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions27
wordCount1134
uniqueNames14
maxNameDensity0.62
worstName"Quinn"
maxWindowNameDensity1
worstWindowName"Herrera"
discoveredNames
Raven1
Nest1
Tomás1
Herrera6
Berwick1
Street1
Saint1
Christopher1
Court1
Road1
Town1
Peckham2
Morris2
Quinn7
persons
0"Raven"
1"Nest"
2"Tomás"
3"Herrera"
4"Saint"
5"Christopher"
6"Morris"
7"Quinn"
places
0"Berwick"
1"Street"
2"Court"
3"Road"
4"Town"
5"Peckham"
globalScore1
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences73
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1162
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences113
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs39
mean29.79
std23.78
cv0.798
sampleLengths
023
147
249
32
44
562
65
75
839
934
104
1187
1248
1315
1450
1513
1657
1723
183
1940
2078
2125
221
2347
244
251
2613
2714
2858
2911
3064
3129
3216
3343
345
3564
3647
3723
389
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences106
matches
0"been locked"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs180
matches
0"wasn't running"
1"was walking"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount8
semicolonCount1
flaggedSentences8
totalSentences113
ratio0.071
matches
0"Herrera stepped out, curls already flattening in the rain, and something tipped him — a look from the doorman, a phone call from inside."
1"Eighteen years of this and her body ran the arithmetic without asking — his stride, her stride, the distance closing by inches at every junction."
2"Herrera went in through the far doors; she took the nearest ones and watched him through the glass into the next carriage — his face strobing against the tunnel dark, one hand closed around the medallion at his throat."
3"She had seen it before — photographed on a skirting board in a flat in Peckham, three years ago, in the file she'd memorised against orders."
4"At the tunnel mouth stood a warden — tall, grey, a long coat, eyes the flat sheen of coins at the bottom of a fountain."
5"The smell reached her then, threading under the lamp smoke and the damp — burnt copper, sharp and hot at the back of her throat."
6"Quinn made the decision the way she made all of them — quickly, completely, no rehearsal."
7"Noise closed over her head — a stallholder calling prices in a language with too few vowels, a buyer haggling over a box that haggled back."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1130
adjectiveStacks0
stackExamples(empty)
adverbCount28
adverbRatio0.024778761061946902
lyAdverbCount2
lyAdverbRatio0.0017699115044247787
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences113
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences113
mean10.28
std7.6
cv0.739
sampleLengths
023
120
27
34
416
54
624
79
82
910
102
113
121
1314
1417
153
163
1725
185
195
209
218
2222
233
2414
258
269
274
2812
2911
3039
316
3210
339
342
3511
3611
373
3821
3915
4013
4112
425
4311
449
458
464
471
4811
498
72.62% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats7
diversityRatio0.4732142857142857
totalSentences112
uniqueOpeners53
34.72% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences96
matches
0"Then the crowd folded over"
ratio0.01
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount27
totalSentences96
matches
0"Her coffee had gone cold"
1"Her watch read 23:47."
2"His gaze swept the street"
3"He cut left into Berwick"
4"She took the corner low,"
5"He was fit."
6"She was precise."
7"He kicked through a gap"
8"She went over them, landed,"
9"His medallion swung loose of"
10"He dropped down the station"
11"He turned off between a"
12"She reached the alley mouth"
13"Her radio gave her static"
14"She checked her watch."
15"She had seen it before"
16"She went down."
17"It was amber."
18"He glanced back once."
19"She opened the warrant card,"
ratio0.281
79.79% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount73
totalSentences96
matches
0"The green neon above the"
1"Quinn stood in a doorway"
2"Her coffee had gone cold"
3"Her watch read 23:47."
4"Rain threaded through the neon"
5"The bar door opened."
6"Herrera stepped out, curls already"
7"His gaze swept the street"
8"Recognition moved across his face"
9"Quinn broke cover."
10"He cut left into Berwick"
11"She took the corner low,"
12"He was fit."
13"She was precise."
14"He kicked through a gap"
15"She went over them, landed,"
16"His medallion swung loose of"
17"Tottenham Court Road."
18"He dropped down the station"
19"A member of staff rose"
ratio0.76
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences96
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences49
technicalSentenceCount2
matches
0"Quinn shouldered through as they closed, her coat snagging, tearing free."
1"Noise closed over her head — a stallholder calling prices in a language with too few vowels, a buyer haggling over a box that haggled back."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags1
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
88.7045%