Run: 2026-02-17-01KHNFTNBQPTRG3M2CBVSZ4RAF

Run Details

Duration:
5.9s
Cost:
$0.000226
Provider:
Clarifai

Model input

System
You are an expert novelist with a gift for vivid, immersive prose. You write in tight third-person limited point of view with a strong narrative voice. Your prose is clean, precise, and engaging — you favor strong verbs, concrete details, and natural-sounding dialogue. You will be given a story bible (codex) containing canonical details about characters, locations, items, and lore. Use these details to ground your writing in the established world. Stay consistent with the codex. Write only the prose of the scene. Do not include titles, chapter headings, markdown formatting, or any commentary before or after the scene.
User/Human
<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> 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.

Model response

AI
The rain lashed thepavement like a thousand tiny fists, turning the London street into a slick, reflective mirror under the harsh glare of a single sodium-vapor lamp. Detective Harlow Quinn’s worn leather watch, its face smeared with grime, ticked steadily against her wrist as she pushed through the spray, her breath fogging in the cold night air. Her sharp jawline was set in a line of grim determination, eyes narrowed against the downpour, tracking the fleeting shadow that had just vanished around the corner of a narrow alley. The suspect, a man Quinn recognized from the precinct’s most wanted list, moved with desperate, jerky energy. He wasn’t running; he was fleeing, his movements a frantic dance of evasion. Quinn matched his pace, her military-trained bearing a stark contrast to his panic. She could smell the damp earth and the faint, metallic tang of fear on the night air. The alley opened into a wider street, choked with the neon glow of Soho’s bars and the muffled roar of traffic from the distant Underground. The man darted towards a grimy doorway, disappearing into the shadows just as Quinn’s boots splashed onto the wet cobbles. “Stop right there!” Quinn barked, her voice cutting through the rain’s roar. No response. She pushed the door open, stepping into a cramped, dimly lit corridor. The air here was stale, smelling of old wood and something else – something sharp and faintly chemical. The suspect’s footsteps echoed ahead, fading as he descended a narrow staircase. Quinn followed, her senses on high alert. The stairs were steep, the walls rough-hewn stone slick with moisture. At the bottom, a heavy, rusted door stood ajar. Beyond it, the world changed. The Veil Market. Quinn’s breath hitched. The air hummed with a low, resonant vibration, like distant thunder trapped underground. The smell was overwhelming: ozone, damp stone, and something else – something sweet and cloying, like rotting fruit. The space was vast, a cavernous chamber carved from the earth, lit by flickering gas lamps and the eerie green glow of a few hidden sigils. Maps, torn and faded, covered the walls, their edges curling in the damp. Black-and-white photographs, some showing faces Quinn didn’t recognize, others depicting impossible landscapes, were pinned haphazardly. The suspect was nowhere in sight. Instead, a figure emerged from the shadows near a stall draped in dark velvet. It was Tomás Herrera, his olive skin pale in the dim light, the Saint Christopher medallion around his neck catching the lamp’s glow. He held out a hand, palm up, revealing a small, polished bone – a token, Quinn realized, the entry requirement for this place. “Bone token, Detective,” Herrera’s voice was low, smooth as aged whiskey. “For the Veil Market. It’s not a place for outsiders.” Quinn’s gaze swept the market. Stalls overflowed with strange wares: vials of shimmering liquid that pulsed with inner light, amulets carved from obsidian, books bound in skin that seemed to shift in the lamplight. The air thrummed with whispered conversations in languages Quinn didn’t recognize, the scent of exotic spices mingling with the metallic tang. It was a den of the supernatural, a place where the rules of the mundane world held no sway. Herrera’s eyes, warm brown and unreadable, met hers. “He’s gone, Detective. Into the depths. The Bone Market. It moves every full moon. This is just the entrance.” Quinn’s hand drifted towards her holster, but she held it steady. The suspect had led her here, into this labyrinth of the unknown. She knew the risks – the supernatural origins of her partner’s death, the whispers of forces she didn’t understand. But the man she pursued was dangerous, and he’d led her straight to the heart of the darkness. The bone token lay in Herrera’s palm, a cold, hard barrier between her and the path ahead. “Where does he go from here?” Quinn’s voice was low, controlled, but the tension in her shoulders was palpable. The choice was hers: retreat into the rain-soaked streets, or step into the Veil Market’s embrace and confront whatever lay within. The bone token waited, a silent judge.
created_at"2026-02-17T09:45:19.738242+00:00" 2/17/2026, 9:45:19 AM
model"arcee-ai/trinity-mini-20251201"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency58
moderation_latency(null)
generation_time5798
tokens_prompt914
tokens_completion1581
native_tokens_prompt787
native_tokens_completion1273
native_tokens_completion_images(null)
native_tokens_reasoning503
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.000226365
router(null)
provider_responses
0
id"67a7bce0290d4a5dacddd0d17f7fa182"
status200
is_byokfalse
latency58
endpoint_id"73d82c49-90ae-4223-a860-83ed0810821f"
provider_name"Clarifai"
model_permaslug"arcee-ai/trinity-mini-20251201"
api_type"completions"
id"gen-1771321513-0M6KzJQCi49U276yL73i"
upstream_id"67a7bce0290d4a5dacddd0d17f7fa182"
total_cost0.000226365
cache_discount(null)
upstream_inference_cost0
provider_name"Clarifai"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags1
adverbTagCount0
adverbTags(empty)
dialogueSentences5
tagDensity0.2
leniency0.4
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount686
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)
19.83% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount686
totalAiIsms11
found
0
word"fleeting"
count1
1
word"dance"
count1
2
word"stark"
count1
3
word"footsteps"
count1
4
word"echoed"
count1
5
word"velvet"
count1
6
word"pulsed"
count1
7
word"unreadable"
count1
8
word"depths"
count1
9
word"tension"
count1
10
word"palpable"
count1
highlights
0"fleeting"
1"dance"
2"stark"
3"footsteps"
4"echoed"
5"velvet"
6"pulsed"
7"unreadable"
8"depths"
9"tension"
10"palpable"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"eyes widened/narrowed"
count1
highlights
0"eyes narrowed"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences43
matches(empty)
76.41% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences43
filterMatches
0"watch"
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences45
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen31
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords684
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions2
unquotedAttributions0
matches(empty)
48.91% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions28
wordCount643
uniqueNames11
maxNameDensity2.02
worstName"Quinn"
maxWindowNameDensity3
worstWindowName"Quinn"
discoveredNames
London1
Harlow1
Quinn13
Soho1
Underground1
Veil2
Market2
Tomás1
Herrera4
Saint1
Christopher1
persons
0"Harlow"
1"Quinn"
2"Market"
3"Tomás"
4"Herrera"
5"Saint"
6"Christopher"
places
0"London"
1"Soho"
2"Veil"
globalScore0.489
windowScore0.667
84.21% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences38
glossingSentenceCount1
matches
0"skin that seemed to shift in the lamplight"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount684
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences45
matches(empty)
69.45% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs10
mean68.4
std26.89
cv0.393
sampleLengths
088
1105
283
396
466
521
674
727
877
947
97.10% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences43
matches
0"were pinned"
65.32% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs99
matches
0"was fleeing"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount4
semicolonCount1
flaggedSentences5
totalSentences45
ratio0.111
matches
0"He wasn’t running; he was fleeing, his movements a frantic dance of evasion."
1"The air here was stale, smelling of old wood and something else – something sharp and faintly chemical."
2"The smell was overwhelming: ozone, damp stone, and something else – something sweet and cloying, like rotting fruit."
3"He held out a hand, palm up, revealing a small, polished bone – a token, Quinn realized, the entry requirement for this place."
4"She knew the risks – the supernatural origins of her partner’s death, the whispers of forces she didn’t understand."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount645
adjectiveStacks0
stackExamples(empty)
adverbCount9
adverbRatio0.013953488372093023
lyAdverbCount4
lyAdverbRatio0.006201550387596899
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences45
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences45
mean15.2
std7.37
cv0.485
sampleLengths
027
130
231
317
413
513
617
725
820
912
102
1112
1218
1312
147
1511
169
175
183
193
2013
2118
2226
2313
2415
256
2614
2723
2823
2911
3010
315
3229
3321
3419
358
3619
3711
3812
3919
4018
4117
4219
4321
447
62.96% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats5
diversityRatio0.4444444444444444
totalSentences45
uniqueOpeners20
79.37% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences42
matches
0"Instead, a figure emerged from"
ratio0.024
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount8
totalSentences42
matches
0"Her sharp jawline was set"
1"He wasn’t running; he was"
2"She could smell the damp"
3"She pushed the door open,"
4"It was Tomás Herrera, his"
5"He held out a hand,"
6"It was a den of"
7"She knew the risks –"
ratio0.19
31.43% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount36
totalSentences42
matches
0"The rain lashed thepavement like"
1"Detective Harlow Quinn’s worn leather"
2"Her sharp jawline was set"
3"The suspect, a man Quinn"
4"He wasn’t running; he was"
5"Quinn matched his pace, her"
6"She could smell the damp"
7"The alley opened into a"
8"The man darted towards a"
9"Quinn barked, her voice cutting"
10"She pushed the door open,"
11"The air here was stale,"
12"The suspect’s footsteps echoed ahead,"
13"Quinn followed, her senses on"
14"The stairs were steep, the"
15"The Veil Market."
16"Quinn’s breath hitched."
17"The air hummed with a"
18"The smell was overwhelming: ozone,"
19"The space was vast, a"
ratio0.857
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences42
matches(empty)
ratio0
95.24% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences30
technicalSentenceCount2
matches
0"Her sharp jawline was set in a line of grim determination, eyes narrowed against the downpour, tracking the fleeting shadow that had just vanished around the co…"
1"Stalls overflowed with strange wares: vials of shimmering liquid that pulsed with inner light, amulets carved from obsidian, books bound in skin that seemed to …"
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags1
uselessAdditionCount1
matches
0"Quinn barked, her voice cutting through the rain’s roar"
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags1
fancyCount1
fancyTags
0"Quinn barked (bark)"
dialogueSentences5
tagDensity0.2
leniency0.4
rawRatio1
effectiveRatio0.4
74.3408%