Run: 2026-02-24-01KJ8WEGFRHXPW434E2TRNX1NX

Run Details

Model:
Aion 2.0
Duration:
1m 14s
Cost:
$0.005110
Provider:
AionLabs

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 lashed the pavements of Soho, turning neon signs into smears of electric color. Detective Harlow Quinn’s boots hit the wet concrete with a rhythm she’d honed over eighteen years. Her breath came in sharp clouds, her salt-and-pepper hair plastered to her scalp. Ahead, a dark figure wove through the late-night crowd, a shadow slipping between pools of lamplight. She’d picked up the tail two hours ago outside The Raven’s Nest. The green neon had buzzed like a trapped insect. He’d emerged from the hidden back room, the one behind the bookshelf she’d only heard whispers about. He moved with a furtive speed that set every instinct she had on edge. Now he was leading her north, away from the bars and into the industrial grime behind Camden Lock. Her left wrist ached where the worn leather of her watch strap dug in. She ignored it. Three years. Three years since Morris had vanished on a night like this, his final transmission a burst of static and a choked-off word that might have been “veil”. She’d filed the report. Unexplained circumstances. She knew better now. The things that moved in the corners of this city weren’t all human. The suspect darted into an alley between two brick warehouses. Quinn followed, her hand going to the service pistol at her hip. The alley was a canyon of dripping pipes and overflowing dumpsters. At the far end, a chain-link fence. He was already scaling it. “Metropolitan Police! Stop!” He didn’t even glance back. He vaulted the top and dropped out of sight. Quinn reached the fence, grabbed the cold, wet links, and hauled herself up. Military precision. Her sharp jaw clenched. She landed in a crouch on the other side, a deserted service road. He was thirty yards ahead, sprinting toward the hulking silhouette of an abandoned Tube station entrance, its roundel long since stripped away. The rain intensified, hammering on corrugated iron roofs. Quinn pushed harder, her lungs burning. He reached a rusted metal door set into the station’s tiled wall. He didn’t knock. He pulled something from his pocket—a small, pale object—and held it up to a slit in the door. A moment later, the door swung inward, spilling a slice of eerie, green-tinged light onto the wet ground. He slipped inside. Quinn skidded to a halt five feet from the door. It was already closing. Her mind raced. An abandoned Tube station. Camden. The schedule moves every full moon. The Veil Market. The words from a confidential informant’s rambling testimony surfaced. A market for things that shouldn’t exist. Entry requirement: a bone token. She was unarmed for this kind of war. The door clicked shut. Quinn approached, her footsteps silent on the slick pavement. Up close, she could see the door was newer than the station, fitted with heavy hinges. No handle. She pressed her ear to the cold metal. A low hum of conversation, strange, discordant music, the clink of glass. Smells leaked out—ozone, burnt herbs, wet fur. She stepped back. Her hand went to her badge, tucked inside her coat. The Metropolitan Police meant nothing here. She knew that. Morris had learned it the hard way. The door remained shut. She could turn around. Walk back to the car, file a report that the suspect was lost in the Camden warrens. No one would question it. She could live. Quinn’s fingers brushed the scar on her left forearm, a reminder of a knife attack from a suspect who’d moved faster than any human should. She thought of Morris’s empty desk, his family’s unanswered questions. The unexplained circumstances. A decision crystallized, cold and hard in her gut. She didn’t have a bone token. She had a police-issue Glock 17 and a stubborn refusal to let another mystery fester in the dark. She raised her fist and knocked—three sharp, authoritative raps. Nothing. She knocked again, harder. A slit in the door, eye-level, slid open. A pair of luminescent yellow eyes peered out. No face, just eyes in a shadowed hole. “Token.” The voice was a dry rasp, like stones grinding together. “Detective Harlow Quinn, Metropolitan Police. I’m in pursuit of a suspect who just entered these premises. Open the door.” The eyes blinked slowly. “No token, no entry. This is not your jurisdiction, little hunter.” “I’m not asking.” Quinn’s voice dropped, low and steady. “Open the door.” A wet, chittering laugh. “You have no idea what you’re walking into. Your authority is a paper shield here. Leave.” Quinn’s mind raced. Bluff. Force. She could shoot the lock, but the report would echo down the tunnel. She’d lose any element of surprise. “The man who just entered. He’s part of a clique I’m investigating. Drugs. Violence.” She leaned closer to the slit. “He’s selling something he shouldn’t be. Something that gets people killed. Like my partner.” The eyes narrowed. “Sentiment is currency for fools. Last chance. Walk away.” She saw Morris’s face then, not as he was in life, but as she’d imagined him in his final moments—confused, afraid, alone in the dark. She’d vowed never to let that happen again, to anyone, if she could stop it. Her hand fell from her badge. She reached into her coat pocket, her fingers closing around the only thing she had that might pass for strange in this place. A small, smooth stone Morris had given her for luck, the week before he died. It was warm to the touch, always, even now in the freezing rain. She didn’t know why. She pulled it out, held it up to the slit. “Will this do?” The yellow eyes stared at the stone. A long, silent moment passed. The rain dripped from the station roof onto her shoulders. The slit snapped shut. Quinn’s heart hammered against her ribs. She’d miscalculated. Then, with a deep, metallic groan, the door began to swing inward, revealing a steep, narrow staircase lit by flickering gas lamps that burned with a green flame. The sounds and smells washed over her—a bazaar of whispers and shadows. At the bottom of the stairs, the cavernous space of the abandoned station platform stretched out, transformed. Stalls made of scrap wood and moth-eaten velvet lined the walls. Creatures—some almost human, others decidedly not—milled about. The air thrummed with a low, magical pressure. And there, already melting into the crowd near a stall selling vials of swirling liquid, was the dark shape of her suspect. Quinn stood on the threshold, the rain at her back, the unknown before her. She had no backup. No protocol for this. Just a gun, a dead man’s lucky stone, and a question that had haunted her for three years. She took a deep breath, stepped over the threshold, and let the door swing shut behind her, cutting off the world of rain and streetlights for good.
created_at"2026-02-24T22:31:20.831Z" 2/24/2026, 10:31:20 PM
model"aion-labs/aion-2.0-20260223"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency4717
moderation_latency(null)
generation_time74191
tokens_prompt1140
tokens_completion3092
native_tokens_prompt1106
native_tokens_completion2641
native_tokens_completion_images(null)
native_tokens_reasoning1314
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"
usage0.0051104
router(null)
provider_responses
0
endpoint_id"1e93b0bb-eb0f-49bc-8fda-947105413b86"
id"b94e9460-f0b2-4c6d-9be0-c30ea23b031d"
is_byokfalse
latency127
model_permaslug"aion-labs/aion-2.0-20260223"
provider_name"AionLabs"
status200
api_type"completions"
id"gen-1771972280-ULDm7NHHxm7e9EOGIqY9"
upstream_id"b94e9460-f0b2-4c6d-9be0-c30ea23b031d"
total_cost0.0051104
cache_discount(null)
upstream_inference_cost0
provider_name"AionLabs"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags4
adverbTagCount0
adverbTags(empty)
dialogueSentences12
tagDensity0.333
leniency0.667
rawRatio0
effectiveRatio0
95.63% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1145
totalAiIsmAdverbs1
found
0
adverb"slowly"
count1
highlights
0"slowly"
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)
51.97% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1145
totalAiIsms11
found
0
word"electric"
count1
1
word"jaw clenched"
count1
2
word"hulking"
count1
3
word"tinged"
count1
4
word"raced"
count2
5
word"footsteps"
count1
6
word"reminder"
count1
7
word"crystallized"
count1
8
word"echo"
count1
9
word"velvet"
count1
highlights
0"electric"
1"jaw clenched"
2"hulking"
3"tinged"
4"raced"
5"footsteps"
6"reminder"
7"crystallized"
8"echo"
9"velvet"
66.67% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches2
maxInWindow2
found
0
label"eyes widened/narrowed"
count1
1
label"jaw/fists clenched"
count1
highlights
0"eyes narrowed"
1"jaw clenched"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences113
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences113
filterMatches
0"watch"
hedgeMatches
0"began to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences121
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen28
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1138
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions3
unquotedAttributions0
matches(empty)
97.17% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions31
wordCount1041
uniqueNames14
maxNameDensity1.06
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Soho1
Harlow1
Quinn11
Raven1
Nest1
Camden3
Lock1
Morris5
Tube2
Veil1
Market1
Metropolitan1
Police1
Glock1
persons
0"Harlow"
1"Quinn"
2"Morris"
3"Police"
places
0"Soho"
1"Raven"
globalScore0.972
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences73
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords0.879
wordCount1138
matches
0"not as he was in life, but as she’d imagined him in his final moments"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences121
matches
0"let that happen"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs39
mean29.18
std21.04
cv0.721
sampleLengths
059
170
269
345
43
568
668
752
88
958
1029
114
1229
1338
149
1524
169
171
184
1924
2011
2119
2215
2312
2420
2524
2634
2712
2840
2961
3013
3122
324
338
3440
3543
3622
3740
3827
99.05% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences113
matches
0"was unarmed"
1"was lost"
80.95% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs168
matches
0"was leading"
1"was already scaling"
2"was already closing"
1.18% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount8
semicolonCount0
flaggedSentences6
totalSentences121
ratio0.05
matches
0"He pulled something from his pocket—a small, pale object—and held it up to a slit in the door."
1"Smells leaked out—ozone, burnt herbs, wet fur."
2"She raised her fist and knocked—three sharp, authoritative raps."
3"She saw Morris’s face then, not as he was in life, but as she’d imagined him in his final moments—confused, afraid, alone in the dark."
4"The sounds and smells washed over her—a bazaar of whispers and shadows."
5"Creatures—some almost human, others decidedly not—milled about."
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1057
adjectiveStacks1
stackExamples
0"eerie, green-tinged light"
adverbCount29
adverbRatio0.027436140018921477
lyAdverbCount4
lyAdverbRatio0.003784295175023652
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences121
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences121
mean9.4
std6.4
cv0.681
sampleLengths
014
116
213
316
412
59
617
714
818
914
103
112
1227
134
142
154
1613
1710
1812
1911
207
215
223
235
249
2513
262
274
2813
2922
308
316
3212
333
3418
3518
363
3710
384
393
404
411
426
433
449
457
465
478
484
499
39.94% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats15
diversityRatio0.3140495867768595
totalSentences121
uniqueOpeners38
64.10% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences104
matches
0"Then, with a deep, metallic"
1"Just a gun, a dead"
ratio0.019
50.77% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount44
totalSentences104
matches
0"Her breath came in sharp"
1"She’d picked up the tail"
2"He’d emerged from the hidden"
3"He moved with a furtive"
4"Her left wrist ached where"
5"She ignored it."
6"She’d filed the report."
7"She knew better now."
8"He was already scaling it."
9"He didn’t even glance back."
10"He vaulted the top and"
11"Her sharp jaw clenched."
12"She landed in a crouch"
13"He was thirty yards ahead,"
14"He reached a rusted metal"
15"He didn’t knock."
16"He pulled something from his"
17"He slipped inside."
18"It was already closing."
19"Her mind raced."
ratio0.423
17.69% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount92
totalSentences104
matches
0"Rain lashed the pavements of"
1"Detective Harlow Quinn’s boots hit"
2"Her breath came in sharp"
3"She’d picked up the tail"
4"The green neon had buzzed"
5"He’d emerged from the hidden"
6"He moved with a furtive"
7"Her left wrist ached where"
8"She ignored it."
9"She’d filed the report."
10"She knew better now."
11"The things that moved in"
12"The suspect darted into an"
13"Quinn followed, her hand going"
14"The alley was a canyon"
15"He was already scaling it."
16"He didn’t even glance back."
17"He vaulted the top and"
18"Quinn reached the fence, grabbed"
19"Her sharp jaw clenched."
ratio0.885
48.08% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences104
matches
0"Now he was leading her"
ratio0.01
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences44
technicalSentenceCount1
matches
0"Then, with a deep, metallic groan, the door began to swing inward, revealing a steep, narrow staircase lit by flickering gas lamps that burned with a green flam…"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags4
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
83.5734%