Run: 2026-02-19-01KHTQTPMQ5DKYXABG0Y3ZENW2

Run Details

Duration:
26.6s
Cost:
$0.015977
Provider:
Cohere

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
The heavy rain blurred the neon glow of the streetlights, casting a ghostly pallor over the city. Detective Harlow Quinn sprinted through the back alleys of Soho, her eyes fixed on her target. The suspect's dark coat flapped in the wind as he wove through the shadows, his movements nimble despite the downpour. Quinn's heart pounded in her ears, a rhythmic reminder of the urgency of the pursuit. Rain soaked her coat, but she paid it no mind, her military-sharp jaw set in determination. She had to catch this man; he was her only lead in a case that had gone cold two years ago. It had left her clinging to the edge of a career she once excelled at, chasing shadows ever since Morris died. The suspect darted across an intersection, narrowly avoiding the headlights of a speeding taxi. Quinn's worn leather boots splashed through puddles as she pursued, her eyes narrowing against the rain. She had dealt with beings far more terrifying than this street rat, but something about him set her instincts on edge. He was just a common crook, after all, another character peddling smuggled goods on the side. But it was something he had said that day, 'Big score...can't pass it up' to a couple of broke losers near Camden. This one made Morris stir from inside her. Something didn't add up. They'd started chasing him across the Square Mile until now through these alleys. Quinn weaved through the maze of trash bins and abandoned shopping carts, her mind racing with possible outcomes. She knew he was going to the Nest; the city's supernatural underworld wasn't infinite. She is older than this kid and that gave her an edge, even with a three-year head start. After all, his pal Morris himself once taught her that the spirit world doesn't always move in straight lines. Another neon sign flashed by—'The Raven's Nest'—its distinctive green glow announced her next steps. The suspect was going to Silas' place. While heading into the Nest meant playing ball in a devil's circle, she had fewer reservations now than ever before. Her gut told her it wasn't the end of the case and she didn't intend to bow out of the job she'd started, even if it was to solve Morris's death. But as she approached the bar entrance, her mind raced. What if he wasn't alone? She had no backup now and no time to call reinforcements. The thought of facing a room full of guards, or worse, rival criminals, made her hesitate. Something about this chase seemed too easy. If this guy was dealing with Silas, why lead her straight to him? Unless, of course, he had backup, and this was all a trap... Quinn quickened her pace, her hand tightening around her firearm. There was no time to waste on what-ifs and speculation. The unmarked door swung open, and a warm glow spilled out onto the drenched street. She could make out the outline of the suspect ducking inside. She took a breath, steeling herself for what may await within. Then, with a final glance at the damp, deserted street behind her, Detective Quinn stepped into the lion's den. The bar was dim, the air thick with smoke and the murmur of hushed conversations. Classic rock filled the room, the bass thumping through old wooden speakers. Quinn paused, taking in the scene. The place was packed with an eclectic mix of patrons—rough-looking men and women, their eyes sharp and alert, as if ready for a fight at any moment. At the bar, a young man with curly dark hair and a torn leather jacket glanced at Quinn. It was Tommy, an ex-paramedic who'd gone rogue after his NHS license was revoked. A tiny brass medallion hanging from his neck winked, reflecting the green neon of the bar sign. "You're looking for someone?" Tommy asked, his voice raising above the music. Despite his scruffy appearance, his eyes showed a quiet determination. Quinn nodded, her eyes scanning the crowd. "You seen a man come in here? Dark hair, athletic build, maybe your age?" Tommy frowned. "Nah, no one like that's been here tonight. This ain't no five-star hotel either. Why you looking for him?" "Same reason your Saint Christopher's dangling round your neck; we all want something," Quinn replied, her eyes still searching for her target. "And something tells me he's here—just in a less obvious spot." Understanding flickered in Tommy's eyes. "Ah, one of Silas' private rooms. You won't get in without an invitation, Detective. Unless you're here for the market." Quinn turned to face him, her sharp eyes boring into his. "Market?" He nodded towards an old bookshelf at the far end of the room. "Market's held behind there when it's in town. It only happens when the moon's round. But mind you, it ain't no farmers' market. You need a bone to get in." A bone—a token to enter an underground market in an old Tube station beneath Camden. It made sense, and it fit with the information she had on her case. The suspect had been boasting about a big score—was this it? Quinn turned back to the bookshelf, her curiosity piqued. "How often does this market happen?" "Every full moon, in a different spot. This time it's here, next time who knows? That's the Veil Market for you." A full moon. It was on its first quarter phase when she approached the suspect that evening. He didn't plan to cash in yet. Something else was going on. "And who controls this market?" Tommy's eyes darted around the room. "You really don't want to go down that rabbit hole, Detective. Silas is bad news. And if you're sticking your nose in his business, I'd keep it above the ground if I were you." Quinn's grip tightened around her firearm. Silas—rumoured to be a demonic figure who controlled much of the supernatural underworld in London. If Quinn's gut was right, this whole thing could lead straight back to him. She turned her gaze back to the bookshelf, her mind made up. "I'll take the risk."
created_at"2026-02-19T10:41:15.42Z" 2/19/2026, 10:41:15 AM
model"cohere/command-r-plus-08-2024"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency265
moderation_latency180
generation_time26048
tokens_prompt1140
tokens_completion1499
native_tokens_prompt1023
native_tokens_completion1342
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"
usage0.0159775
router(null)
provider_responses
0
endpoint_id"cd63714a-d459-4806-bdf2-0dfea4f6614c"
id"edfb83d7-35b8-4fe6-b91f-031058e921c1"
is_byokfalse
latency265
model_permaslug"cohere/command-r-plus-08-2024"
provider_name"Cohere"
status200
api_type"completions"
id"gen-1771497675-rEb0NLbexPMTZNzjPdy6"
upstream_id"edfb83d7-35b8-4fe6-b91f-031058e921c1"
total_cost0.0159775
cache_discount(null)
upstream_inference_cost0
provider_name"Cohere"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags4
adverbTagCount0
adverbTags(empty)
dialogueSentences13
tagDensity0.308
leniency0.615
rawRatio0
effectiveRatio0
95.14% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1029
totalAiIsmAdverbs1
found
0
adverb"really"
count1
highlights
0"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)
65.99% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1029
totalAiIsms7
found
0
word"rhythmic"
count1
1
word"reminder"
count1
2
word"racing"
count1
3
word"raced"
count1
4
word"quickened"
count1
5
word"scanning"
count1
6
word"flickered"
count1
highlights
0"rhythmic"
1"reminder"
2"racing"
3"raced"
4"quickened"
5"scanning"
6"flickered"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches0
maxInWindow0
found(empty)
highlights(empty)
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells1
narrationSentences64
matches
0"t in determination"
98.21% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount2
narrationSentences64
filterMatches(empty)
hedgeMatches
0"tend to"
1"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences75
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen34
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1018
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions5
unquotedAttributions0
matches(empty)
63.90% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions39
wordCount813
uniqueNames16
maxNameDensity1.72
worstName"Quinn"
maxWindowNameDensity3
worstWindowName"Quinn"
discoveredNames
Harlow1
Quinn14
Soho1
Morris4
Square1
Mile1
Nest2
Raven1
Silas2
Detective2
Tommy5
Despite1
Understanding1
Tube1
Camden1
London1
persons
0"Harlow"
1"Quinn"
2"Morris"
3"Raven"
4"Silas"
5"Detective"
6"Tommy"
7"Understanding"
places
0"Soho"
1"Square"
2"Nest"
3"London"
globalScore0.639
windowScore0.667
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences57
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1018
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences75
matches
0"said that day"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs25
mean40.72
std24.14
cv0.593
sampleLengths
053
173
2101
382
472
574
646
730
860
949
1022
1121
1221
1333
1425
1512
1643
1740
1815
1921
2029
215
2240
2335
2416
94.30% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences64
matches
0"was packed"
1"was revoked"
0.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount4
totalVerbs130
matches
0"was going"
1"was going"
2"was dealing"
3"was going"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount6
semicolonCount3
flaggedSentences8
totalSentences75
ratio0.107
matches
0"She had to catch this man; he was her only lead in a case that had gone cold two years ago."
1"She knew he was going to the Nest; the city's supernatural underworld wasn't infinite."
2"Another neon sign flashed by—'The Raven's Nest'—its distinctive green glow announced her next steps."
3"The place was packed with an eclectic mix of patrons—rough-looking men and women, their eyes sharp and alert, as if ready for a fight at any moment."
4"\"Same reason your Saint Christopher's dangling round your neck; we all want something,\" Quinn replied, her eyes still searching for her target."
5"A bone—a token to enter an underground market in an old Tube station beneath Camden."
6"The suspect had been boasting about a big score—was this it?"
7"Silas—rumoured to be a demonic figure who controlled much of the supernatural underworld in London."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount416
adjectiveStacks0
stackExamples(empty)
adverbCount11
adverbRatio0.026442307692307692
lyAdverbCount3
lyAdverbRatio0.007211538461538462
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences75
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences75
mean13.57
std6.64
cv0.489
sampleLengths
017
116
220
315
416
521
621
714
816
921
1016
1122
128
134
1413
1518
1614
1718
1819
1914
207
2120
2231
2310
245
2511
2616
277
2813
2912
3010
3110
3215
3311
3411
3519
3615
3712
386
3927
4018
4114
4217
4312
4410
457
4614
472
4819
4922
77.33% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats2
diversityRatio0.48
totalSentences75
uniqueOpeners36
52.91% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences63
matches
0"Then, with a final glance"
ratio0.016
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount17
totalSentences63
matches
0"She had to catch this"
1"It had left her clinging"
2"She had dealt with beings"
3"He was just a common"
4"They'd started chasing him across"
5"She knew he was going"
6"She is older than this"
7"Her gut told her it"
8"She had no backup now"
9"She could make out the"
10"She took a breath, steeling"
11"It was Tommy, an ex-paramedic"
12"He nodded towards an old"
13"It made sense, and it"
14"It was on its first"
15"He didn't plan to cash"
16"She turned her gaze back"
ratio0.27
71.11% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount49
totalSentences63
matches
0"The heavy rain blurred the"
1"Detective Harlow Quinn sprinted through"
2"The suspect's dark coat flapped"
3"Quinn's heart pounded in her"
4"She had to catch this"
5"It had left her clinging"
6"The suspect darted across an"
7"Quinn's worn leather boots splashed"
8"She had dealt with beings"
9"He was just a common"
10"This one made Morris stir"
11"Something didn't add up."
12"They'd started chasing him across"
13"Quinn weaved through the maze"
14"She knew he was going"
15"She is older than this"
16"Another neon sign flashed by—'The"
17"The suspect was going to"
18"Her gut told her it"
19"She had no backup now"
ratio0.778
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount3
totalSentences63
matches
0"While heading into the Nest"
1"If this guy was dealing"
2"If Quinn's gut was right,"
ratio0.048
95.24% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences45
technicalSentenceCount3
matches
0"Quinn weaved through the maze of trash bins and abandoned shopping carts, her mind racing with possible outcomes."
1"The place was packed with an eclectic mix of patrons—rough-looking men and women, their eyes sharp and alert, as if ready for a fight at any moment."
2"Silas—rumoured to be a demonic figure who controlled much of the supernatural underworld in London."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags4
uselessAdditionCount2
matches
0"Tommy asked, his voice raising above the music"
1"Quinn replied, her eyes still searching for her target"
73.08% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags3
fancyCount1
fancyTags
0"something he had (have)"
dialogueSentences13
tagDensity0.231
leniency0.462
rawRatio0.333
effectiveRatio0.154
82.9069%