Run: 2026-02-19-01KHSZ013A0X4MD292CTMY0GWH

Run Details

Duration:
43.1s
Cost:
$0.000466
Provider:
NextBit

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="4414" name="Eva Kowalski" aliases="Eva, Evie" pronouns="she/her" species="Human" storyRole="Best Friend"> <eyeColor>green</eyeColor> <hair>curly red</hair> <height>5'4"</height> <age>26</age> <glasses>round glasses</glasses> <satchel>worn leather satchel full of books</satchel> <freckles>freckled complexion</freckles> <nervousHabit>tucking hair behind her left ear</nervousHabit> <description>Aurora's childhood friend and an occult researcher.</description> <backstory>Moved to London two years before Aurora and works as a research assistant at the British Museum's restricted archives. She holds a master's degree in Ancient History from Oxford.</backstory> </character> <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> <item id="2004" name="Veil Compass" aliases="the Compass, shadow compass" type="Tool" origin="The Veil Market"> <casingMaterial>small brass compass</casingMaterial> <faceMarkings>face etched with protective sigils</faceMarkings> <needle>points toward the nearest supernatural rift or portal</needle> <patina>casing has a patina of verdigris</patina> <creator>crafted by a Shade artisan</creator> <description>A compass attuned to supernatural energy.</description> </item> </codex> Continue the story using the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the mystery genre. A detective arrives at a crime scene in an unusual location. Something is wrong — the evidence doesn't add up. A colleague is present, offering a different interpretation. Through careful observation and deduction, the detective begins to see what others have missed. 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 underground market was abuzz with activity, stalls draped in deep shadows. Detective Harlow Quinn's leather shoes echoed against the abandoned Tube platform as she approached the scene, her watchful eyes scanning the unusual gathering. A constable stopped her at the perimeter. "Detective Quinn, we didn't expect you here." "I go where the case takes me, officer." Quinn flashed her badge. "What have we got?" The constable led her to a stall where a body lay covered by a sheet. Quinn's sharp gaze took in the details—the small brass compass nearby, its needle twitching, the worn leather satchel spilled open, books strewn about. Eva Kowalski emerged from the swarm of uniforms, her freckled face pale. "Detective Quinn. I didn't think you'd be assigned to this." "I don't believe in coincidences, Eva. Not with our history." Quinn knelt beside the corpse, lifting the sheet. A young man, his eyes frozen in fear. "What do you know?" Eva tugged at her hair. "The Veil Market moves every full moon. This victim had a Veil Compass on him. I think he was searching for something." Quinn inspected the compass, its etched face glinting under the flickering lights. She stood, surveying the area. "Officer, what's your take on this?" The constable shuffled. "Looks like a robbery gone wrong, ma'am. He was into some shady dealings." But Quinn shook her head. "No. Look at the position of the body." She pointed. "And the books weren't taken. A thief would've grabbed them." She turned to Eva. "The compass. It points to supernatural rifts, correct?" At Eva's nod, she continued. "I think our victim was close to finding something. And someone didn't want that." As Quinn pieced it together, her eyes narrowed. "No signs of a struggle, but definite hesitation. He knew his killer." She glanced at Eva. "I need access to those restricted archives of yours. We're dealing with something bigger." Eva hesitated, then sighed. "I can get you in. But Quinn? Be careful. You don't know what you're getting into." But Detective Harlow Quinn was already striding away, her military precision cutting through the chaos of the market, her mind racing to uncover the truth hidden beneath the surface. Something had gone terribly wrong here, in this den of shadows and secrets. And she would find out what.
created_at"2026-02-19T03:27:15.571Z" 2/19/2026, 3:27:15 AM
model"nousresearch/hermes-3-llama-3.1-70b"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency5209
moderation_latency(null)
generation_time43008
tokens_prompt1171
tokens_completion597
native_tokens_prompt1025
native_tokens_completion527
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"
usage0.0004656
router(null)
provider_responses
0
endpoint_id"19e60da4-d0e0-4799-a949-ea786279a5cb"
id"cmpl-8f2bd54c3c4f4579bbe38551bef259af"
is_byokfalse
latency3494
model_permaslug"nousresearch/hermes-3-llama-3.1-70b"
provider_name"NextBit"
status200
api_type"completions"
id"gen-1771471635-okQAxJ0D3CWCvjYr7Lgo"
upstream_id"cmpl-8f2bd54c3c4f4579bbe38551bef259af"
total_cost0.0004656
cache_discount(null)
upstream_inference_cost0
provider_name"NextBit"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags5
adverbTagCount0
adverbTags(empty)
dialogueSentences16
tagDensity0.313
leniency0.625
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount384
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)
34.90% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount384
totalAiIsms5
found
0
word"echoed"
count1
1
word"scanning"
count1
2
word"etched"
count1
3
word"glinting"
count1
4
word"racing"
count1
highlights
0"echoed"
1"scanning"
2"etched"
3"glinting"
4"racing"
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"
88.77% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells1
narrationSentences23
matches
0"n in fear"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences23
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences34
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen29
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords383
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions1
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions20
wordCount217
uniqueNames6
maxNameDensity3.69
worstName"Quinn"
maxWindowNameDensity4
worstWindowName"Quinn"
discoveredNames
Harlow2
Quinn8
Tube1
Kowalski1
Eva6
Detective2
persons
0"Harlow"
1"Quinn"
2"Kowalski"
3"Eva"
places(empty)
globalScore0
windowScore0.333
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences13
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount383
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences34
matches(empty)
71.11% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs14
mean27.36
std10.91
cv0.399
sampleLengths
042
17
216
338
422
530
627
723
816
925
1031
1138
1220
1348
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences23
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs39
matches(empty)
58.82% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount1
semicolonCount0
flaggedSentences1
totalSentences34
ratio0.029
matches
0"Quinn's sharp gaze took in the details—the small brass compass nearby, its needle twitching, the worn leather satchel spilled open, books strewn about."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount218
adjectiveStacks0
stackExamples(empty)
adverbCount4
adverbRatio0.01834862385321101
lyAdverbCount1
lyAdverbRatio0.0045871559633027525
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences34
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences34
mean11.26
std6.3
cv0.56
sampleLengths
012
123
27
37
412
54
615
723
812
910
1018
118
124
135
1422
1512
165
176
183
1913
205
2110
2210
234
2413
2514
268
2716
2814
294
3016
3129
3213
336
73.53% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats0
diversityRatio0.4411764705882353
totalSentences34
uniqueOpeners15
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences22
matches(empty)
ratio0
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount3
totalSentences22
matches
0"She stood, surveying the area."
1"She turned to Eva."
2"She glanced at Eva"
ratio0.136
73.64% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount17
totalSentences22
matches
0"The underground market was abuzz"
1"Detective Harlow Quinn's leather shoes"
2"A constable stopped her at"
3"Quinn flashed her badge"
4"The constable led her to"
5"Quinn's sharp gaze took in"
6"Eva Kowalski emerged from the"
7"Quinn knelt beside the corpse,"
8"A young man, his eyes"
9"Eva tugged at her hair."
10"Quinn inspected the compass, its"
11"She stood, surveying the area."
12"The constable shuffled."
13"She turned to Eva."
14"She glanced at Eva"
15"Eva hesitated, then sighed."
16"Something had gone terribly wrong"
ratio0.773
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences22
matches(empty)
ratio0
53.57% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences8
technicalSentenceCount1
matches
0"But Detective Harlow Quinn was already striding away, her military precision cutting through the chaos of the market, her mind racing to uncover the truth hidde…"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags5
uselessAdditionCount0
matches(empty)
87.50% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags1
fancyCount1
fancyTags
0"At Eva's nod she continued (continue)"
dialogueSentences16
tagDensity0.063
leniency0.125
rawRatio1
effectiveRatio0.125
81.3946%