Run: 2026-02-19-01KHTRHA03G89NM3W8HEJX433V

Run Details

Duration:
23.4s
Cost:
$0.000524
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="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
Detective Harlow Quinn splashed through ankle-deep puddles, her breathing labored, as she chased the dark silhouette darting through the rain-slicked streets of London. Her heart pounded in her chest, less from exertion than from the adrenaline that coursed through her veins. The chase had begun minutes earlier, when she spied her long-time suspect, Tommy, emerging from the shadows of Soho. She knew him on sight - his tall, lanky frame and curly dark hair were as familiar to her as her own reflection. He darted down alleys, across side streets, always just out of reach. Now, as she navigated the maze-like backstreets, she caught a glimpse of him again, his olive skin glistening with rain. Her pulse quickened. This was it - the moment she had been waiting for. She put on a final burst of speed, her shoes splashing through rivulets as she closed the distance. Tommy had reached the end of a dead-end alley. He whirled to face her, his eyes wide and alarmed. "You need to let this go, Quinn," he called out, his voice echoing off the brick walls. "You don't know what you're getting into." Harlow reached him in three long strides, her worn leather watch glinting under the streetlights as she grabbed his arm. "We both know you're hiding something, Tommy," she said, her breath coming in short puffs. "And I'll find out what it is. One way or another." Tommy's gaze flickered past her, to the alley mouth behind. Harlow turned to look, and in that split second, he wrenched free of her grip and broke into a run. She chased after him, their shoes skidding on the wet cobblestones as they raced back towards the main street. hurting than she was tired. But Tommy was skilled at this game of cat and mouse. He cut left suddenly, ducking behind a parked van. Harlow swore, rounding the vehicle just in time to see him vanish down a manhole, neatly flipping the heavy cover back into place above him. She stared at the grate, rainwater dripping down her face to mingle with the sweat. He had to be in some kind of underground tunnel system. But would she follow him into the unknown depths of London's underbelly? It was a risk - who knew what lay down there? Her heart hammered. She thought of DS Morris, her partner who had disappeared, never to be seen again. And of the strange markings she had found on the last crime scene they worked - strange arcane symbols she couldn't make head or tail of. Could this lead her to answers? Harlow looked down at the manhole, then back to the street. The glistening streets called to her, a promise of safety and Professional secrets and dangers of being an underground detective down here. She squeezed her eyes shut. This was a jump off a cliff - follow Tommy, or retain her sense and let him go and maybe never get a chance like this again Her jaw clenched. No, she told herself firmly. She had come too far to turn back now. She was getting to the bottom of this, no matter what. She gripped the manhole cover and heaved, grunting with the strain. With a final burst of willpower, she wrenched it free and hastily clambered down the ladder, dropping into damp darkness. The moment her feet hit the tunnel floor, she braced herself, one hand on the rusty ladder. The sounds of the city receded above, replaced by the dripping of water and the muffled skittering of unknown creatures in the gloom. She breathed steadily, waiting for her eyes to adjust, peering into the inky blackness ahead.
created_at"2026-02-19T10:53:36.136Z" 2/19/2026, 10:53:36 AM
model"thedrummer/rocinante-12b"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1513
moderation_latency(null)
generation_time23311
tokens_prompt1162
tokens_completion883
native_tokens_prompt1059
native_tokens_completion801
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"
usage0.00052446
router(null)
provider_responses
0
endpoint_id"94c3af54-1ed5-400c-affb-570e2935d725"
id"cmpl-d3f0743e1aac4765a53da0dfc842b9d6"
is_byokfalse
latency1128
model_permaslug"thedrummer/rocinante-12b"
provider_name"NextBit"
status200
api_type"completions"
id"gen-1771498416-KTde1hXnYZEIWW6BaymD"
upstream_id"cmpl-d3f0743e1aac4765a53da0dfc842b9d6"
total_cost0.00052446
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
totalTags2
adverbTagCount0
adverbTags(empty)
dialogueSentences4
tagDensity0.5
leniency1
rawRatio0
effectiveRatio0
91.83% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount612
totalAiIsmAdverbs1
found
0
adverb"suddenly"
count1
highlights
0"suddenly"
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)
0.00% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount612
totalAiIsms14
found
0
word"familiar"
count1
1
word"navigated"
count1
2
word"glistening"
count2
3
word"pulse"
count1
4
word"quickened"
count1
5
word"echoing"
count1
6
word"glinting"
count1
7
word"flickered"
count1
8
word"raced"
count1
9
word"depths"
count1
10
word"jaw clenched"
count1
11
word"firmly"
count1
12
word"gloom"
count1
highlights
0"familiar"
1"navigated"
2"glistening"
3"pulse"
4"quickened"
5"echoing"
6"glinting"
7"flickered"
8"raced"
9"depths"
10"jaw clenched"
11"firmly"
12"gloom"
66.67% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches2
maxInWindow2
found
0
label"heart pounded in chest"
count1
1
label"jaw/fists clenched"
count1
highlights
0"heart pounded in her chest"
1"jaw clenched"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences41
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences41
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences43
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
totalWords613
ratio0
matches(empty)
41.67% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions3
unquotedAttributions1
matches
0"No, she told herself firmly."
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions16
wordCount581
uniqueNames7
maxNameDensity0.86
worstName"Harlow"
maxWindowNameDensity1.5
worstWindowName"Harlow"
discoveredNames
Harlow5
Quinn1
London2
Tommy5
Soho1
Morris1
Professional1
persons
0"Harlow"
1"Quinn"
2"Tommy"
3"Morris"
places
0"London"
1"Soho"
globalScore1
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences36
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount613
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences43
matches(empty)
40.22% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs13
mean47.15
std13.71
cv0.291
sampleLengths
041
154
252
343
446
549
65
745
849
950
1065
1159
1255
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences41
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount1
totalVerbs100
matches
0"was getting"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount5
semicolonCount0
flaggedSentences5
totalSentences43
ratio0.116
matches
0"She knew him on sight - his tall, lanky frame and curly dark hair were as familiar to her as her own reflection."
1"This was it - the moment she had been waiting for."
2"It was a risk - who knew what lay down there?"
3"And of the strange markings she had found on the last crime scene they worked - strange arcane symbols she couldn't make head or tail of."
4"This was a jump off a cliff - follow Tommy, or retain her sense and let him go and maybe never get a chance like this again Her jaw clenched."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount580
adjectiveStacks0
stackExamples(empty)
adverbCount16
adverbRatio0.027586206896551724
lyAdverbCount7
lyAdverbRatio0.01206896551724138
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences43
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences43
mean14.26
std6.57
cv0.461
sampleLengths
023
118
219
323
412
520
63
711
818
99
1010
1117
127
1320
1415
1511
1610
1720
1819
195
2011
219
2225
2315
2411
2512
2611
273
2815
2926
306
3111
3222
335
3430
355
369
3711
3811
3920
4017
4123
4215
60.47% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats4
diversityRatio0.4186046511627907
totalSentences43
uniqueOpeners18
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences41
matches(empty)
ratio0
24.88% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount20
totalSentences41
matches
0"Her heart pounded in her"
1"She knew him on sight"
2"He darted down alleys, across"
3"Her pulse quickened."
4"She put on a final"
5"He whirled to face her,"
6"he called out, his voice"
7"she said, her breath coming"
8"She chased after him, their"
9"He cut left suddenly, ducking"
10"She stared at the grate,"
11"He had to be in"
12"It was a risk -"
13"Her heart hammered."
14"She thought of DS Morris,"
15"She squeezed her eyes shut."
16"She had come too far"
17"She was getting to the"
18"She gripped the manhole cover"
19"She breathed steadily, waiting for"
ratio0.488
57.56% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount33
totalSentences41
matches
0"Detective Harlow Quinn splashed through"
1"Her heart pounded in her"
2"The chase had begun minutes"
3"She knew him on sight"
4"He darted down alleys, across"
5"Her pulse quickened."
6"This was it - the"
7"She put on a final"
8"Tommy had reached the end"
9"He whirled to face her,"
10"he called out, his voice"
11"Harlow reached him in three"
12"she said, her breath coming"
13"Tommy's gaze flickered past her,"
14"Harlow turned to look, and"
15"She chased after him, their"
16"He cut left suddenly, ducking"
17"Harlow swore, rounding the vehicle"
18"She stared at the grate,"
19"He had to be in"
ratio0.805
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences41
matches
0"Now, as she navigated the"
ratio0.024
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences31
technicalSentenceCount0
matches(empty)
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags2
uselessAdditionCount2
matches
0"he called out, his voice echoing off the brick walls"
1"she said, her breath coming in short puffs"
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount1
fancyTags
0"he called out (call out)"
dialogueSentences4
tagDensity0.5
leniency1
rawRatio0.5
effectiveRatio0.5
72.7762%