Run: 2026-02-17-01KHMMD7PPCPN83H59B54K6MSV

Run Details

Duration:
35.8s
Cost:
$0.000678
Provider:
DeepInfra

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 pounded against the pavement in heavy sheets, the night sky flickering with distant lightning. Detective Harlow Quinn blinked the water from her eyes, her sharp gaze locked on the shadowy figure darting through the slick, deserted streets. The suspect, a young man with an olive complexion and short, curly dark brown hair, seemed to melt into the darkness between the infrequent streetlamps. Quinn's sensible flats splashed through the puddles as she pursued, her worn leather watch strapping her fitness tracker to her wrist. She was getting too old for this, she thought bitterly, the sharp pains in her joints agreeing with the sentiment. But she couldn't let this lead go. Not when she'd finally found a thread connected to the case that had haunted her for years. The file on the late DS Morris was still open on her desk, a cold case that never stopped bleeding chill into her heart. She'd lost her partner, her closest friend in the department, to something she couldn't understand. Something with claws dipped in the supernatural. And now, finally, she had a scent. She followed the suspect down the twisting alleys, heart pounding in her chest. He seemed to know exactly where he was going, never hesitating as he navigated the maze of wet cobblestones. They came to a stop in front of a green neon sign, buzzing and flickering in the rain, advertising 'The Raven's Nest'. The suspect glanced back at her, his warm brown eyes flashing in the light, before disappearing inside. Quinn gritted her teeth, weighing her options. She could call for backup, but by the time they arrived, the thread would be gone. No, she had to do this herself. She had to know what lay at the end of it. She pushed through the door, stepping into the dimly lit warmth of the bar. The walls were covered in old maps and black-and-white photographs, the air heavy with the scent of stale beer and cigarette smoke. She scanned the room quickly, looking for the suspect. He was nowhere to be seen. Quinn approached the bar, keeping her voice low and urgent. "The man who just came in? Where did he go?" The bartender, a grizzled man with more beard than hair, just shrugged. "Haven't seen anyone." Quinn's patience snapped like a twig under a boot. "Don't waste my time." She glanced around, looking for any other exit. Her gaze landed on a bookshelf. She strode over to it, running her fingers along the spines of the ancient tomes. Headlines screamed of war and disaster in languages dead and living. Her fingers found a switch hidden in the dust, a click sounding in the quiet room. The bookshelf swung open with a creak, revealing a hidden staircase leading down into darkness. Quinn hesitated for a moment, then drew her gun from her holster. She had a feeling she was going to need it. The stairs led to a tunnel, old railway tracks running along the floor. The air was thick with the stink of mildew and something else, something Quinn couldn't quite place. Something that made her nose wrinkle in disgust. She followed the tracks, the only light coming from the flickering bulbs strung haphazardly along the walls. The tunnel opened up into a cavern, the abandoned Tube station bustling with life. Stalls and tables lined the walls, selling everything from enchanted weapons to alchemical concoctions. Quinn kept to the shadows, watching as the suspect moved through the crowd, his medallion glinting in the dull light. He spoke to a few of the vendors, exchanging coins and tokens for small packages. Quinn's heart raced in her chest, adrenalin flooding her system. This was it, the underground market she'd heard whispers about. The Veil Market. Where anything could be bought for the right price. Where secrets were sold like cheap perfume. She had to get closer, had to hear what was being said. She pulled her jacket tighter around her shoulders, tucking her gun into the waistband of her trousers. She stepped into the light, moving through the throng of people. She kept her eyes on the suspect, watching as he handed a bone token to a vendor. The vendor, a tall woman with hair like snakes, handed him a vial in exchange. Quinn's eyes widened. She knew what that was. She'd seen it before, in the file on DS Morris. Her partner had been investigating the same thing before he died. Before he was torn apart by something that shouldn't exist. Something that lived in the shadows and fed on fear. Quinn's hand inched towards her gun as she approached the vendor. She had to get that vial. She had to know what was in it. What had killed her partner. She drew her gun, leveling it at the vendor. "Metropolitan Police! Step away from the table and put your hands where I can see them!" The vendor laughed, a sound like the hiss of a thousand snakes. "You have no power here, detective. You are not in your world anymore." Quinn's finger tightened on the trigger as the crowd around her started to grow restless. She could see the glint of weapons in the shadows, the flash of teeth and claws. She was in over her head. She knew it. But she couldn't back down. Not now. Not when she was so close to finding the answers she'd been seeking for years. She glanced at the suspect, seeing the fear in his eyes. He held up his hands in surrender, the vial clutched in his fist. "I can help you," he said, his voice barely audible over the murmurs of the crowd. "But we have to go, now." Quinn hesitated for a moment, then nodded. She kept her gun trained on the vendor as she backed away, the suspect leading her through the crowd. They ran back through the tunnels, the sound of pursuit echoing behind them. They burst into the night, the rain still falling in sheets. Quinn holstered her gun, coughing as she tried to catch her breath. The suspect handed her the vial, his hand shaking. "It's everything you need to know," he said, his voice thick with exhaustion. "To find out what happened to your partner. To find out what's been happening in this city." Quinn took the vial, tucking it into her jacket. She looked at the suspect, really looked at him for the first time. He was young, younger than she'd thought. His face was lined with stress, his eyes shadowed with fear. She reached out, placing a hand on his shoulder. "Thank you, Tomás," she said, using his name for the first time. "I promise I'll find out what happened. I'll make it right." He nodded, a small smile tugging at the corners of his mouth. "I know you will, detective. I know you will."
created_at"2026-02-17T01:46:38.117703+00:00" 2/17/2026, 1:46:38 AM
model"nousresearch/hermes-3-llama-3.1-70b"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency164
moderation_latency(null)
generation_time35709
tokens_prompt936
tokens_completion1665
native_tokens_prompt815
native_tokens_completion1446
native_tokens_completion_images(null)
native_tokens_reasoning0
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"
usage0.0006783
router(null)
provider_responses
0
id"cmpl-0cc6544b652441f2b5ba435ad41440fd"
status200
is_byokfalse
latency77
endpoint_id"2151651b-f4e9-4db7-b20d-8b91fb524bf8"
provider_name"DeepInfra"
model_permaslug"nousresearch/hermes-3-llama-3.1-70b"
api_type"completions"
id"gen-1771292761-PO9mF9dNqHwUbgHEUDb5"
upstream_id"cmpl-0cc6544b652441f2b5ba435ad41440fd"
total_cost0.0006783
cache_discount(null)
upstream_inference_cost0
provider_name"DeepInfra"

Evaluation details

Result Evaluator Details Meta Data
33.33% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags5
adverbTagCount1
adverbTags
0"She glanced around [around]"
dialogueSentences12
tagDensity0.417
leniency0.833
rawRatio0.2
effectiveRatio0.167
91.27% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1146
totalAiIsmAdverbs2
found
0
adverb"quickly"
count1
1
adverb"really"
count1
highlights
0"quickly"
1"really"
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)
60.73% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1146
totalAiIsms9
found
0
word"chill"
count1
1
word"pounding"
count1
2
word"navigated"
count1
3
word"warmth"
count1
4
word"scanned"
count1
5
word"glinting"
count1
6
word"raced"
count1
7
word"glint"
count1
8
word"echoing"
count1
highlights
0"chill"
1"pounding"
2"navigated"
3"warmth"
4"scanned"
5"glinting"
6"raced"
7"glint"
8"echoing"
33.33% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches3
maxInWindow3
found
0
label"heart pounded in chest"
count1
1
label"eyes widened/narrowed"
count1
2
label"air was thick with"
count1
highlights
0"heart raced in her chest"
1"eyes widened"
2"The air was thick with"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells1
narrationSentences88
matches
0"d with fear"
61.69% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount4
narrationSentences88
filterMatches
0"watch"
hedgeMatches
0"seemed to"
1"started to"
2"tried to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences96
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen25
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1146
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions5
unquotedAttributions0
matches(empty)
77.95% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions21
wordCount1041
uniqueNames6
maxNameDensity1.44
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Harlow1
Quinn15
Morris2
Tube1
Veil1
Market1
persons
0"Harlow"
1"Quinn"
2"Morris"
places(empty)
globalScore0.78
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences81
glossingSentenceCount1
matches
0"quite place"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1146
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences96
matches
0"get that vial"
61.01% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs29
mean39.52
std14.37
cv0.364
sampleLengths
064
165
253
332
480
551
620
715
827
942
1037
1138
1245
1335
1439
1540
1650
1731
1830
1925
2025
2131
2231
2346
2450
2551
2640
2732
2821
85.33% Passive voice overuse
Target: ≤2% passive sentences
passiveCount5
totalSentences88
matches
0"were covered"
1"were sold"
2"being said"
3"was torn"
4"was lined"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs174
matches
0"was getting"
1"was going"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences96
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount311
adjectiveStacks0
stackExamples(empty)
adverbCount9
adverbRatio0.028938906752411574
lyAdverbCount5
lyAdverbRatio0.01607717041800643
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences96
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences96
mean11.94
std4.99
cv0.418
sampleLengths
016
123
225
321
420
57
617
724
815
97
107
1113
1219
1322
1417
157
1616
177
1811
1914
2022
219
226
2310
2410
2512
263
279
2812
296
3015
3111
3216
3315
3412
3510
3613
3717
388
3917
4014
4114
4220
4315
4410
4510
463
479
487
4912
36.46% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats13
diversityRatio0.28125
totalSentences96
uniqueOpeners27
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences87
matches(empty)
ratio0
22.30% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount43
totalSentences87
matches
0"She was getting too old"
1"She'd lost her partner, her"
2"She followed the suspect down"
3"He seemed to know exactly"
4"They came to a stop"
5"She could call for backup,"
6"She had to know what"
7"She pushed through the door,"
8"She scanned the room quickly,"
9"He was nowhere to be"
10"She glanced around, looking for"
11"Her gaze landed on a"
12"She strode over to it,"
13"Her fingers found a switch"
14"She had a feeling she"
15"She followed the tracks, the"
16"He spoke to a few"
17"She had to get closer,"
18"She pulled her jacket tighter"
19"She stepped into the light,"
ratio0.494
17.47% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount77
totalSentences87
matches
0"The rain pounded against the"
1"Detective Harlow Quinn blinked the"
2"The suspect, a young man"
3"Quinn's sensible flats splashed through"
4"She was getting too old"
5"The file on the late"
6"She'd lost her partner, her"
7"Something with claws dipped in"
8"She followed the suspect down"
9"He seemed to know exactly"
10"They came to a stop"
11"The suspect glanced back at"
12"Quinn gritted her teeth, weighing"
13"She could call for backup,"
14"She had to know what"
15"She pushed through the door,"
16"The walls were covered in"
17"She scanned the room quickly,"
18"He was nowhere to be"
19"Quinn approached the bar, keeping"
ratio0.885
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount2
totalSentences87
matches
0"Where secrets were sold like"
1"Before he was torn apart"
ratio0.023
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences55
technicalSentenceCount2
matches
0"She was getting too old for this, she thought bitterly, the sharp pains in her joints agreeing with the sentiment."
1"Quinn kept to the shadows, watching as the suspect moved through the crowd, his medallion glinting in the dull light."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags5
uselessAdditionCount2
matches
0"he said, his voice barely audible over the murmurs of the crowd"
1"he said, his voice thick with exhaustion"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags3
fancyCount0
fancyTags(empty)
dialogueSentences12
tagDensity0.25
leniency0.5
rawRatio0
effectiveRatio0
76.0294%