Run: 2026-10-13-01M4TBR3W6DH3D01VR9BSZWK0D

Run Details

Duration:
1m 37s
Cost:
$0.086864
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
Rain came off the awning in ropes and turned Brewer Street into black glass. Quinn stood beneath it with her collar raised, watching the green neon of the Raven's Nest bleed across the pavement. Eleven-forty by the worn leather watch on her wrist. Third night this week. No overtime authorisation, no surveillance log, nothing the Met would sanction — just a gut feeling that had outlasted every sensible voice in her head. The bar's door swung open and Tomás Herrera stepped out into the wet, satchel slung across his chest, one hand pressed flat over it like a man carrying eggs. His Saint Christopher medallion caught the neon as he turned up his collar. Curly dark hair, olive skin gone pale with worry. He walked north without looking back. Quinn gave him half a street, then followed. He moved like someone who counted cameras. Cut through alleyways that bypassed the main roads, doubled back once through a late-night grocers, emerged checking the reflections in parked cars. She matched him shop window for shop window, her reflection a cropped-haired ghost among the mannequins. Soho gave way to the long straight haul north, and by the time the canal appeared below Camden Lock the rain had soaked through her coat to the shirt. He made her at the railway bridge. A stall mirror, angled wrong, did the work — she watched his shoulders lock, watched his hand come up to touch the medallion at his throat. Then he ran. "Herrera!" She went after him, boots skidding on wet cobbles. "Police! I only want to talk!" "That's what you people always want!" He threw it over his shoulder without slowing, vaulted the lock gate, and disappeared under the bridge's iron ribs. She followed him through the shuttered market, past padlocked stalls and awnings shedding water in sheets. A courier bike came out of nowhere and she twisted clear, horn dopplering off into the rain. Her lungs burned. Twenty-nine years old, Herrera, and built for this; she was forty-one and built for courtrooms, but three years of chasing dead ends had taught her legs things her age didn't know. "Tomás! Morris! That name mean anything to you?" He faltered. Half a stride, no more — but she saw it, and he knew she saw it, and the satchel betrayed him a moment later, snagging on a railing as he cut between two stalls. The clasp burst. Gauze, vials, a roll of surgical tape scattered across the wet stone, and he dropped to his knees scrabbling for the case itself, cursing in Sevillian Spanish, while something pale spun off the kerb and settled in the gutter. A disc of bone, no bigger than a two-pound coin, carved with a mark she couldn't read at distance. Herrera snatched up the case and ran. Quinn palmed the disc as she passed — warm, somehow, warmer than the rain allowed — and shoved it into her coat. He led her off the street into an alley she'd walked past a hundred times without seeing. Hoardings boarded up a dead Tube entrance, the roundel long since painted over, but the hoarding's door stood open on darkness, and a man waited in the gap wearing a bowler hat gone soft with damp. Herrera flashed something small and white at him. The man stepped aside. Gone. Quinn pulled up at the door, soaked through, breathing hard. The man in the bowler hat filled the gap. One of his eyes had gone the colour of milk. "Token." "Metropolitan Police." She held her warrant card up to the dark. "That man is wanted for questioning. Step aside." "Card's no good down here." He didn't look at it. "Token's good. Bone's good." "Move, or I'll have this door off its hinges by morning." "You won't." No heat in it. Flat as a ledger. "Nobody comes down here who isn't carried or called. Them's the rules. Older than your card." Beyond him, stairs dropped away into light the colour of a bruise. Sound rose up with it — a crowd, haggling, laughing, the saw of a violin tuning itself in uneven strokes — a whole market breathing under Camden where no market should be. The smell reached her next. Frankincense. Wet stone. Copper, faint and familiar, the smell that had been in the stairwell where they found Morris. Then she saw the wall. Chalk on the old tiles, half-lost to damp: a circle bitten through by a crooked line. The same mark from the Morris file. Photographed, bagged, logged, and never explained. Three years she'd carried that shape in the back of her head like a splinter, and here it was, fresh, still dusting white onto the step. Her radio came up to her mouth. "QC-4, request backup, Camden—" Static swallowed it. Under the static, something that wasn't quite a voice kept pace with her words, half a beat behind. She lowered the radio. Protocol sat on one shoulder, neat as epaulettes: withdraw, observe, call it in, wait for a team that would arrive to find boarded doors and nothing. Morris sat on the other shoulder the way he always did, grinning out of the photograph on her desk, three years dead of a cause the coroner had written down as inconclusive with his pen pressed hard enough to tear the page. Every lead had died at street level. This one went down. The bone disc had worked a warmth through her coat pocket into her hip. She drew it out. Heavier than it looked, the carved mark catching the bruise-coloured light, and the gatekeeper's good eye fixed on it the way miser's fix on gold. "Where'd a police come by that?" "Found it in the gutter." She kept it flat on her palm. "It's good, you said. Bone's good." His grin showed a gap where a canine should be. "New blood gets one warning free." He plucked the token from her palm with two fingers, quick as a bird taking seed. "Market keeps what it catches. Mind the tithe, mind your manners, and don't buy nothing you can't afford to lose." "And the man who just went through? Curly hair, medical bag?" "Tomás?" The gatekeeper tucked the bone disc somewhere inside his coat and stood aside, sweeping one arm towards the stairs with the ceremony of a man ushering royalty into a pit. "He's a regular. You'll find him where the bleeding stops." Quinn checked her watch out of habit — midnight, the second hand stuttering against the glass as though the rain had got inside the mechanism. She thought of Morris's file, shut in her desk drawer with its torn page. She thought of the empty stairwell on Camden High Street where backup would eventually stand, scratching their heads at a boarded door. Then she ducked under the lintel and went down. The stairs swallowed the rain behind her. Ahead, the ticket hall opened out into lantern light and noise — stalls packed between the old barriers, jars full of things that moved against the glass, a woman in a bridal veil selling bottles of dark liquid, the violin playing now with no hands on it. A hundred faces turned towards her at once, the way a field of poppies turns in wind. And there, halfway down the platform tunnel, a glint of gold at a running man's throat.
created_at"2026-10-13T10:08:22.42Z" 10/13/2026, 10:08:22 AM
model"fireworks/ember-1-20260923"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency406
moderation_latency(null)
generation_time97436
tokens_prompt1104
tokens_completion6461
native_tokens_prompt1087
native_tokens_completion5769
native_tokens_completion_images(null)
native_tokens_reasoning4189
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)
usage0.0868638
router(null)
user_agent"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer(null)
request_id"req-1791886102-c0emXkcbh4aZXo95Gmgq"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1791886102-4PpBfnAdrRQ3kIdSiGth"
upstream_id"chatcmpl-7a6a5d69086549e6b140bdd22b0b1119"
provider_responses
0
endpoint_id"b89a2f05-4051-4446-a9b0-7bc8ae7b7c90"
id"chatcmpl-7a6a5d69086549e6b140bdd22b0b1119"
is_byokfalse
latency406
model_permaslug"fireworks/ember-1-20260923"
provider_name"Fireworks"
status200
total_cost0.0868638
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
totalTags7
adverbTagCount0
adverbTags(empty)
dialogueSentences21
tagDensity0.333
leniency0.667
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1217
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)
87.67% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1217
totalAiIsms3
found
0
word"familiar"
count1
1
word"warmth"
count1
2
word"glint"
count1
highlights
0"familiar"
1"warmth"
2"glint"
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
narrationSentences76
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount2
hedgeCount0
narrationSentences76
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences89
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen46
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1226
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions2
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions31
wordCount1087
uniqueNames18
maxNameDensity0.46
worstName"Quinn"
maxWindowNameDensity1.5
worstWindowName"Morris"
discoveredNames
Brewer1
Street2
Raven1
Nest1
Met1
Tomás1
Herrera4
Saint1
Christopher1
Camden3
Lock1
Sevillian1
Spanish1
Tube1
Flat1
Morris4
Quinn5
High1
persons
0"Raven"
1"Nest"
2"Met"
3"Tomás"
4"Herrera"
5"Saint"
6"Christopher"
7"Lock"
8"Morris"
9"Quinn"
places
0"Brewer"
1"Street"
2"Camden"
3"Sevillian"
4"High"
globalScore1
windowScore1
63.79% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences58
glossingSentenceCount2
matches
0"appeared below Camden Lock the rain had soaked through her coat to the shirt"
1"quite a voice kept pace with her words, half a beat behind"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1226
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences89
matches
0"carried that shape"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs38
mean32.26
std24.48
cv0.759
sampleLengths
072
157
28
374
433
53
616
725
867
98
1078
1119
1229
1353
1413
1529
161
1719
1814
1911
2026
2168
225
2355
2411
2521
2672
2711
2843
296
3018
3152
3211
3341
3461
359
3671
3716
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences76
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs176
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount9
semicolonCount1
flaggedSentences8
totalSentences89
ratio0.09
matches
0"No overtime authorisation, no surveillance log, nothing the Met would sanction — just a gut feeling that had outlasted every sensible voice in her head."
1"A stall mirror, angled wrong, did the work — she watched his shoulders lock, watched his hand come up to touch the medallion at his throat."
2"Twenty-nine years old, Herrera, and built for this; she was forty-one and built for courtrooms, but three years of chasing dead ends had taught her legs things her age didn't know."
3"Half a stride, no more — but she saw it, and he knew she saw it, and the satchel betrayed him a moment later, snagging on a railing as he cut between two stalls."
4"Quinn palmed the disc as she passed — warm, somehow, warmer than the rain allowed — and shoved it into her coat."
5"Sound rose up with it — a crowd, haggling, laughing, the saw of a violin tuning itself in uneven strokes — a whole market breathing under Camden where no market should be."
6"Quinn checked her watch out of habit — midnight, the second hand stuttering against the glass as though the rain had got inside the mechanism."
7"Ahead, the ticket hall opened out into lantern light and noise — stalls packed between the old barriers, jars full of things that moved against the glass, a woman in a bridal veil selling bottles of dark liquid, the violin playing now with no hands on it."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1086
adjectiveStacks0
stackExamples(empty)
adverbCount25
adverbRatio0.02302025782688766
lyAdverbCount2
lyAdverbRatio0.001841620626151013
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences89
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences89
mean13.78
std10.28
cv0.746
sampleLengths
014
120
29
34
425
529
613
79
86
98
107
1122
1216
1329
147
1526
163
1710
186
1925
2016
2117
223
2331
248
252
2634
273
2839
2919
307
3122
3217
3336
348
354
361
3710
389
3910
401
4111
428
4310
444
4511
466
474
4816
4912
98.88% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.6179775280898876
totalSentences89
uniqueOpeners55
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences72
matches
0"Then he ran."
1"Then she saw the wall."
2"Then she ducked under the"
ratio0.042
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount20
totalSentences72
matches
0"His Saint Christopher medallion caught"
1"He walked north without looking"
2"He moved like someone who"
3"She matched him shop window"
4"He made her at the"
5"She went after him, boots"
6"He threw it over his"
7"She followed him through the"
8"Her lungs burned."
9"He led her off the"
10"She held her warrant card"
11"He didn't look at it"
12"Her radio came up to"
13"She lowered the radio."
14"She drew it out."
15"She kept it flat on"
16"His grin showed a gap"
17"He plucked the token from"
18"She thought of Morris's file,"
19"She thought of the empty"
ratio0.278
98.89% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount52
totalSentences72
matches
0"Rain came off the awning"
1"Quinn stood beneath it with"
2"The bar's door swung open"
3"His Saint Christopher medallion caught"
4"He walked north without looking"
5"Quinn gave him half a"
6"He moved like someone who"
7"She matched him shop window"
8"Soho gave way to the"
9"He made her at the"
10"A stall mirror, angled wrong,"
11"She went after him, boots"
12"He threw it over his"
13"She followed him through the"
14"A courier bike came out"
15"Her lungs burned."
16"The clasp burst."
17"Gauze, vials, a roll of"
18"A disc of bone, no"
19"Herrera snatched up the case"
ratio0.722
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences72
matches(empty)
ratio0
67.67% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences38
technicalSentenceCount4
matches
0"Cut through alleyways that bypassed the main roads, doubled back once through a late-night grocers, emerged checking the reflections in parked cars."
1"Gauze, vials, a roll of surgical tape scattered across the wet stone, and he dropped to his knees scrabbling for the case itself, cursing in Sevillian Spanish, …"
2"Quinn checked her watch out of habit — midnight, the second hand stuttering against the glass as though the rain had got inside the mechanism."
3"Ahead, the ticket hall opened out into lantern light and noise — stalls packed between the old barriers, jars full of things that moved against the glass, a wom…"
53.57% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags7
uselessAdditionCount1
matches
0"She went after, boots skidding on wet cobbles"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
89.0158%