Run: 2026-02-26-01KJCS3843DCH2AD2JB2TN2CK8

Run Details

Model:
LFM2 24B
Duration:
26.4s
Cost:
$0.000182
Provider:
Together

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 fell in sheets across the cracked pavement. Streetlights blurred into smears of gold behind Detective Harlow Quinn’s goggles. She ran, boots splashing through puddles that reflected the neon glow of The Raven’s Nest sign. The air reeked of wet wool and burnt coffee. Behind her, footsteps echoed—quick, uneven, desperate. Tomás Herrera darted between alleyways, his scarred forearm catching stray raindrops. He glanced over his shoulder, eyes narrowing. The city seemed to shrink around him, shadows stretching like fingers. Harlow skidded around a corner, nearly colliding with a rusted fire escape. She cursed under her breath. “Not tonight,” she muttered. Tomás slipped through a side door marked by a faded Saint Christopher medallion. Harlow followed, her hand brushing the worn leather watch on her wrist. The metal was cool against her skin. She could hear the distant hum of a subway train, felt the vibration of distant sirens. Inside, the air was thick with smoke and the scent of incense. Stalls lined the walls, each piled high with strange objects: vials of shimmering liquid, bundles of dried herbs, folded papers sealed with wax. A woman in a velvet cloak watched them from behind a counter. Her eyes glinted like polished obsidian. “Looking for something specific?” the woman asked. Her voice was smooth, almost musical. Harlow kept her gaze fixed on Tomás. “He’s here.” The woman tilted her head. “Many seek what they cannot name. What is it you want?” Tomás paused, his breath fogging in the cold air. “Just passing through.” The woman smiled. “The market does not care about passing through.” Harlow stepped forward, her boots scraping against the wooden floorboards. The stalls seemed to shift, shadows moving just beyond the reach of flickering lanterns. A man in a tattered coat approached, holding out a small glass vial. Inside, a faint green light pulsed. “Drink this,” he whispered, “and you’ll see the truth.” Harlow’s hand tightened around her watch. “I don’t drink.” The man laughed, low and rough. “Everyone drinks eventually.” Tomás turned sharply, disappearing into a narrow corridor lined with mirrors. Each reflection showed a different version of himself—older, younger, distorted. Harlow hesitated, then followed. The corridor opened into a vast chamber. The ceiling disappeared into darkness. Stalls crowded the space, each more bizarre than the last. A group of figures stood around a table, their faces obscured by hoods. They spoke in hushed tones, hands gesturing toward a map spread across the wood. Harlow’s pulse quickened. She recognized symbols etched into the edges of the map—symbols from her own case files. The same markings she’d seen in the aftermath of her partner’s death. “What is this place?” she demanded, stepping closer. The leader lifted his hood. His eyes were hollow, sunken. “The Veil Market. Where secrets change hands.” Tomás emerged from the shadows, his face pale. “They’re selling memories.” Harlow’s eyes narrowed. “And who’s buying?” The leader gestured to a figure cloaked in black. The figure stepped forward, revealing a face Harlow knew too well—her partner, DS Morris. But his eyes were empty, his skin gray. “You died three years ago,” the figure said. “But here, death is just another transaction.” Harlow’s breath caught. She reached for her gun, but her hand trembled. The air grew heavy, charged with something unseen. Tomás moved, grabbing her arm. “Don’t shoot!” The figure raised a hand. A wave of cold washed over them. Memories flooded Harlow’s mind—her partner’s final moments, the unexplained energy, the way his body had dissolved into mist. “No,” she whispered. “Not again.” The leader smiled. “You’ve come far, Detective. But this is where the chase ends.” Tomás pulled her back, dragging her toward a hidden door. “We need to go. Now.” Harlow glanced at the map one last time. The symbols pulsed, alive. She made her choice. “Lead the way,” she said. They slipped through the secret room, the door slamming shut behind them. The market faded, replaced by the sound of dripping water and distant whispers. Somewhere above, thunder rolled. The rain intensified, drumming against the metal roof. Tomás led her deeper into the tunnels. The air grew colder, the smell of iron stronger. They passed stalls filled with broken clocks, their hands frozen at impossible times. A child offered her a mirror; inside, Harlow saw herself with eyes like her partner’s. “Don’t look too long,” Tomás warned. “It changes you.” They reached a final chamber. A single lantern burned in the center. On a pedestal lay a small box, carved from bone. The leader waited there, arms crossed. “Open it,” he said. “Or walk away.” Harlow’s hand hovered over the lid. Memories surged—her partner’s laughter, the weight of her badge, the moment everything changed. She closed her eyes. When she opened them, the box was empty. The leader nodded. “You’ve chosen wisely.” Tomás exhaled. “What now?” Harlow looked at the leader, then at Tomás. “Now we disappear.” They vanished into the tunnels, the lantern’s flame flickering behind them. The market swallowed them whole. Somewhere above, the rain continued to fall.
created_at"2026-02-26T10:49:43.647Z" 2/26/2026, 10:49:43 AM
model"liquid/lfm-2-24b-a2b-20260224"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency306
moderation_latency(null)
generation_time26324
tokens_prompt1140
tokens_completion1439
native_tokens_prompt1071
native_tokens_completion1251
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"
usage0.00018225
router(null)
provider_responses
0
endpoint_id"b5f259c3-1e77-40d6-8fa4-161cdf0e4a7c"
id"oYufzvw-2j9zxn-9d3ee09fe092e509"
is_byokfalse
latency306
model_permaslug"liquid/lfm-2-24b-a2b-20260224"
provider_name"Together"
status200
api_type"completions"
id"gen-1772102983-U56lr5LA8r9BoFlGnwSS"
upstream_id"oYufzvw-2j9zxn-9d3ee09fe092e509"
total_cost0.00018225
cache_discount(null)
upstream_inference_cost0
provider_name"Together"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags9
adverbTagCount0
adverbTags(empty)
dialogueSentences28
tagDensity0.321
leniency0.643
rawRatio0
effectiveRatio0
94.06% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount842
totalAiIsmAdverbs1
found
0
adverb"sharply"
count1
highlights
0"sharply"
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)
28.74% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount842
totalAiIsms12
found
0
word"footsteps"
count1
1
word"echoed"
count1
2
word"velvet"
count1
3
word"pulsed"
count2
4
word"pulse"
count1
5
word"quickened"
count1
6
word"etched"
count1
7
word"aftermath"
count1
8
word"trembled"
count1
9
word"charged"
count1
10
word"weight"
count1
highlights
0"footsteps"
1"echoed"
2"velvet"
3"pulsed"
4"pulse"
5"quickened"
6"etched"
7"aftermath"
8"trembled"
9"charged"
10"weight"
66.67% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches2
maxInWindow2
found
0
label"eyes widened/narrowed"
count1
1
label"air was thick with"
count1
highlights
0"eyes narrowed"
1"the air was thick with"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences90
matches(empty)
79.37% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount2
hedgeCount2
narrationSentences90
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)
analyzedSentences109
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen23
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords836
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions8
unquotedAttributions0
matches(empty)
38.89% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions36
wordCount720
uniqueNames10
maxNameDensity2.22
worstName"Harlow"
maxWindowNameDensity3
worstWindowName"Harlow"
discoveredNames
Detective1
Harlow16
Quinn1
Raven1
Nest1
Herrera1
Tomás12
Saint1
Christopher1
Morris1
persons
0"Harlow"
1"Quinn"
2"Raven"
3"Herrera"
4"Tomás"
5"Saint"
6"Christopher"
7"Morris"
places(empty)
globalScore0.389
windowScore0.667
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences60
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount836
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences109
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs41
mean20.39
std13.99
cv0.686
sampleLengths
050
129
221
348
453
513
69
716
812
911
1043
119
129
139
1425
1549
1630
178
1817
1911
206
2131
2215
2320
247
2530
265
2714
2815
2916
305
3137
3244
339
3428
357
3623
3714
384
3911
4023
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences90
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs143
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount6
semicolonCount1
flaggedSentences7
totalSentences109
ratio0.064
matches
0"Behind her, footsteps echoed—quick, uneven, desperate."
1"Each reflection showed a different version of himself—older, younger, distorted."
2"She recognized symbols etched into the edges of the map—symbols from her own case files."
3"The figure stepped forward, revealing a face Harlow knew too well—her partner, DS Morris."
4"Memories flooded Harlow’s mind—her partner’s final moments, the unexplained energy, the way his body had dissolved into mist."
5"A child offered her a mirror; inside, Harlow saw herself with eyes like her partner’s."
6"Memories surged—her partner’s laughter, the weight of her badge, the moment everything changed."
88.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount726
adjectiveStacks2
stackExamples
0"faint green light pulsed."
1"cold washed over them."
adverbCount16
adverbRatio0.02203856749311295
lyAdverbCount2
lyAdverbRatio0.0027548209366391185
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences109
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences109
mean7.67
std4.09
cv0.533
sampleLengths
08
111
216
39
46
511
67
711
812
95
104
1113
1212
137
1416
1512
1623
1712
186
197
206
217
222
235
2411
259
263
273
288
2910
3014
3113
326
339
346
353
366
373
3811
3910
404
417
425
4310
4413
4514
463
4715
4812
498
55.35% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.3486238532110092
totalSentences109
uniqueOpeners38
80.32% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences83
matches
0"Somewhere above, thunder rolled."
1"Somewhere above, the rain continued"
ratio0.024
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount17
totalSentences83
matches
0"She ran, boots splashing through"
1"He glanced over his shoulder,"
2"She cursed under her breath."
3"She could hear the distant"
4"Her eyes glinted like polished"
5"Her voice was smooth, almost"
6"They spoke in hushed tones,"
7"She recognized symbols etched into"
8"she demanded, stepping closer"
9"His eyes were hollow, sunken."
10"She reached for her gun,"
11"She made her choice."
12"They slipped through the secret"
13"They passed stalls filled with"
14"They reached a final chamber."
15"She closed her eyes."
16"They vanished into the tunnels,"
ratio0.205
8.19% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount75
totalSentences83
matches
0"Rain fell in sheets across"
1"Streetlights blurred into smears of"
2"She ran, boots splashing through"
3"The air reeked of wet"
4"Tomás Herrera darted between alleyways,"
5"He glanced over his shoulder,"
6"The city seemed to shrink"
7"Harlow skidded around a corner,"
8"She cursed under her breath."
9"Tomás slipped through a side"
10"Harlow followed, her hand brushing"
11"The metal was cool against"
12"She could hear the distant"
13"Stalls lined the walls, each"
14"A woman in a velvet"
15"Her eyes glinted like polished"
16"the woman asked"
17"Her voice was smooth, almost"
18"Harlow kept her gaze fixed"
19"The woman tilted her head."
ratio0.904
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences83
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences31
technicalSentenceCount1
matches
0"She ran, boots splashing through puddles that reflected the neon glow of The Raven’s Nest sign."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags9
uselessAdditionCount0
matches(empty)
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags9
fancyCount5
fancyTags
0"she muttered (mutter)"
1"he whispered (whisper)"
2"she demanded (demand)"
3"she whispered (whisper)"
4"Tomás warned (warn)"
dialogueSentences28
tagDensity0.321
leniency0.643
rawRatio0.556
effectiveRatio0.357
77.9863%