Run: 2026-02-19-01KHTYW2MFKS2SM8CZ8T33V3WP

Run Details

Duration:
55.7s
Cost:
$0.001948
Provider:
Minimax

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 rain turned the streets of Camden into a mirror of neon. Detective Harlow Quinn sprinted around the corner, her boots splashing through puddles that reflected the orange glow of streetlights. Three blocks ahead, the suspect vaulted over a railings and disappeared down the steps of an abandoned Tube station. Quinn didn't slow down. Eighteen years on the force had taught her that hesitation cost lives. She grabbed the iron railing and swung herself over, her leather watch catching on the metal as she dropped onto the slick concrete stairs. The station had been closed for years. Faded posters for concerts and films that had come and gone hung at odd angles from water-stained walls. Her flashlight cut through the darkness, but the suspect had a head start and knew these tunnels. "Police!" Her voice echoed off the tile. Useless, probably. But protocol demanded it. She heard the thud of a door somewhere ahead. The beam of her torch found a service entrance hanging open, its hinges rusted but recently disturbed. Cold air rushed up from below, carrying the smell of damp stone and something else—incense, maybe, or burning herbs. Quinn hesitated at the threshold. She'd heard rumors about this place. whispered tales in the locker room at the Met, cases that went cold because evidence vanished into thin air, suspects who slipped through fingers because they vanished into parts of the city that didn't exist on any map. Her partner, Morris, had been investigating something similar before he died. Three years later, she still didn't have answers about what had really happened to him. The darkness below called to her. Or maybe it was the echo of the chase, the need to close the distance before the suspect disappeared entirely. She descended. The stairs led to a corridor lit by strings of colored bulbs that hadn't been approved by any council. The walls were lined with stalls—impossible, there shouldn't be stalls here—but there they were. Tables covered in bottles and vials and objects she couldn't identify. People moved between them, their faces half-hidden by hoods and masks, their conversations dropping to whispers as her flashlight swept across the space. The Veil Market. The name surfaced from a case file she'd read six months ago and dismissed as superstition. A hand shot out from behind a curtain of beads and grabbed her arm. "You shouldn't be here." The man who held her was dark-skinned, curly hair, with warm brown eyes that studied her with wary intelligence. He wore a medallion around his neck that glinted in the low light. "Detective Quinn, isn't it? I've seen your picture." She pulled her arm free. "Step aside. I'm pursuing a suspect." "This isn't jurisdiction. This isn't even the same world as your streets." He gestured at the market around them. "Whatever you're chasing, let it go." "Someone ran down here. I'm bringing them in." "They came here to escape you. That's the point of this place." He blocked her path. "You walk any further in, you'll find things you can't unsee. Things that don't play by your rules." "I'm not leaving without my suspect." She pushed past him, but he fell into step beside her, matching her stride. "Tommy Herrera," he said. "Former paramedic. Lost my license when I started treating patients your doctors couldn't explain. I run medical help for people who fall through the cracks of your system." "Great. Stay out of my way." "You're not listening." He grabbed her arm again, more gently this time. "That man you're chasing—he owes money to people here. Dangerous people. If you drag him back to your world, you break agreements that keep both sides from burning. This isn't just about arrest quotas." She stopped walking. The market stretched out before her, a labyrinth ofhidden stalls and shadowed faces. Somewhere in this maze, the suspect had vanished. She could feel eyes on her, dozens of them, watching the uniform, watching the badge, watching the gun at her hip. "What kind of agreements?" she asked. Herrera exhaled. "The Veil Market exists because sometimes the world needs a middle ground. Supernatural and human. We handle trades that keep dangerous things out of ordinary hands. Weapons, information, artifacts. Every transaction keeps something worse from happening on the streets above." "And the suspect?" "He made a deal. Now he's running. That's not your concern." Quinn looked at the stalls, at the bottles glowing faintly blue, at the shelves of books with bindings made from materials she didn't want to identify. This was the world Morris had been investigating. This was what had gotten him killed. "Tell me about the man who runs this market," she said. "That's not—" "I'm not leaving. But I need to understand what I'm walking into." Herrera studied her for a long moment. Something shifted in his expression—recognition, maybe, or the memory of someone else who'd been stubborn enough to walk this far and not turn back. "Everyone calls him Silas," he said finally. "He's in the back room, behind the bookshelf. If you want to find your suspect, you'll have to go through him." Quinn moved toward the far end of the market, where a towering shelf of ancient-looking books stood against the wall. She didn't wait for Herrera to follow. The rain above was just a memory now, but the cold had settled into her bones. She'd spent three years chasing shadows, trying to understand what had happened to Morris. Now she stood in the middle of something that shouldn't exist, about to knock on a door that might swallow her whole. Her hand found the shelf. She pulled.
created_at"2026-02-19T12:44:20.51Z" 2/19/2026, 12:44:20 PM
model"minimax/minimax-m2.5-20260211"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency765
moderation_latency(null)
generation_time55486
tokens_prompt1140
tokens_completion1748
native_tokens_prompt978
native_tokens_completion1379
native_tokens_completion_images(null)
native_tokens_reasoning234
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"
usage0.0019482
router(null)
provider_responses
0
endpoint_id"c61d37ec-745c-4efd-8129-a68371e056b2"
is_byokfalse
latency165
model_permaslug"minimax/minimax-m2.5-20260211"
provider_name"Fireworks"
status429
1
endpoint_id"3afb00c4-6135-4c55-96e9-6befa9679b06"
id"05e638a4732c9147500743916bc0bad9"
is_byokfalse
latency765
model_permaslug"minimax/minimax-m2.5-20260211"
provider_name"Minimax"
status200
api_type"completions"
id"gen-1771505060-z7OaKTWnjPM5FTFou5ef"
upstream_id"05e638a4732c9147500743916bc0bad9"
total_cost0.0019482
cache_discount(null)
upstream_inference_cost0
provider_name"Minimax"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags9
adverbTagCount1
adverbTags
0"he said finally [finally]"
dialogueSentences24
tagDensity0.375
leniency0.75
rawRatio0.111
effectiveRatio0.083
89.43% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount946
totalAiIsmAdverbs2
found
0
adverb"really"
count1
1
adverb"gently"
count1
highlights
0"really"
1"gently"
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)
84.14% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount946
totalAiIsms3
found
0
word"echoed"
count1
1
word"echo"
count1
2
word"could feel"
count1
highlights
0"echoed"
1"echo"
2"could feel"
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
emotionTells0
narrationSentences58
matches(empty)
68.97% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount2
narrationSentences58
filterMatches
0"watch"
hedgeMatches
0"happened to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences72
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen40
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords937
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions7
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions18
wordCount677
uniqueNames10
maxNameDensity0.74
worstName"Quinn"
maxWindowNameDensity1.5
worstWindowName"Quinn"
discoveredNames
Camden1
Harlow1
Quinn5
Tube1
Useless1
Met1
Morris3
Veil1
Market1
Herrera3
persons
0"Harlow"
1"Quinn"
2"Morris"
3"Herrera"
places
0"Met"
globalScore1
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences42
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount937
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences72
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs35
mean26.77
std18.47
cv0.69
sampleLengths
050
140
242
313
445
55
670
726
82
967
1019
1114
1244
1311
1425
158
1634
1720
1832
196
2046
2145
226
2342
243
2511
2641
2711
282
2912
3031
3128
3243
3336
347
87.11% Passive voice overuse
Target: ≤2% passive sentences
passiveCount3
totalSentences58
matches
0"been closed"
1"been approved"
2"were lined"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs126
matches(empty)
23.81% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount4
semicolonCount0
flaggedSentences3
totalSentences72
ratio0.042
matches
0"Cold air rushed up from below, carrying the smell of damp stone and something else—incense, maybe, or burning herbs."
1"The walls were lined with stalls—impossible, there shouldn't be stalls here—but there they were."
2"Something shifted in his expression—recognition, maybe, or the memory of someone else who'd been stubborn enough to walk this far and not turn back."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount685
adjectiveStacks0
stackExamples(empty)
adverbCount19
adverbRatio0.027737226277372264
lyAdverbCount8
lyAdverbRatio0.01167883211678832
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences72
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences72
mean13.01
std8.55
cv0.657
sampleLengths
012
119
219
34
412
524
67
718
817
97
102
114
129
1317
1419
155
166
1738
1811
1915
206
2120
222
2319
2414
2511
2623
273
2816
2914
3023
3113
328
335
346
3519
366
378
3816
3918
4020
414
4228
436
4412
4534
463
4713
488
4921
81.48% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.5138888888888888
totalSentences72
uniqueOpeners37
65.36% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences51
matches
0"Somewhere in this maze, the"
ratio0.02
78.82% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount18
totalSentences51
matches
0"She grabbed the iron railing"
1"Her flashlight cut through the"
2"Her voice echoed off the"
3"She heard the thud of"
4"She'd heard rumors about this"
5"Her partner, Morris, had been"
6"He wore a medallion around"
7"She pulled her arm free."
8"He gestured at the market"
9"He blocked her path"
10"She pushed past him, but"
11"He grabbed her arm again,"
12"She stopped walking."
13"She could feel eyes on"
14"he said finally"
15"She didn't wait for Herrera"
16"She'd spent three years chasing"
17"Her hand found the shelf."
ratio0.353
58.04% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount41
totalSentences51
matches
0"The rain turned the streets"
1"Detective Harlow Quinn sprinted around"
2"Quinn didn't slow down."
3"She grabbed the iron railing"
4"The station had been closed"
5"Her flashlight cut through the"
6"Her voice echoed off the"
7"She heard the thud of"
8"The beam of her torch"
9"Quinn hesitated at the threshold."
10"She'd heard rumors about this"
11"Her partner, Morris, had been"
12"The darkness below called to"
13"The stairs led to a"
14"The walls were lined with"
15"Tables covered in bottles and"
16"People moved between them, their"
17"The Veil Market."
18"The name surfaced from a"
19"A hand shot out from"
ratio0.804
98.04% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences51
matches
0"Now she stood in the"
ratio0.02
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences28
technicalSentenceCount1
matches
0"Detective Harlow Quinn sprinted around the corner, her boots splashing through puddles that reflected the orange glow of streetlights."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags9
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags4
fancyCount0
fancyTags(empty)
dialogueSentences24
tagDensity0.167
leniency0.333
rawRatio0
effectiveRatio0
91.1735%