Run: 2026-07-07-01KWZ3MPSXN8K15Y7ZK3EAJB7H

Run Details

Duration:
6.1s
Cost:
$0.000771
Provider:
AionLabs

Model input

System
You are an expert novelist with a gift for vivid, immersive prose. You write in tight third-person limited point of view with a strong narrative voice. Your prose is clean, precise, and engaging — you favor strong verbs, concrete details, and natural-sounding dialogue. You will be given a story bible (codex) containing canonical details about characters, locations, items, and lore. Use these details to ground your writing in the established world. Stay consistent with the codex. Write only the prose of the scene. Do not include titles, chapter headings, markdown formatting, or any commentary before or after the scene.
User/Human
<codex> <character id="4412" name="Aurora Carter" aliases="Rory, Laila, Aurora, Carter, Malphora" pronouns="she/her" species="Human" storyRole="Protagonist"> <eyeColor>bright blue</eyeColor> <hair>straight shoulder-length black</hair> <height>5'6"</height> <age>25</age> <scar>small crescent-shaped scar on her left wrist from a childhood accident</scar> <description>Aurora, referred to by her friends as Rory, is cool-headed, intelligent, and known for quick out-of-the-box thinking.</description> <backstory>Born in Cardiff to an Irish barrister father (Brendan Carter) and Welsh teacher mother (Jennifer Carter née Ellis), Rory reluctantly pursued Pre-Law at Cardiff University. She fled to London at the behest of her childhood friend Eva after leaving an abusive ex named Evan. By day, Rory works part-time as a delivery person for Yu-Fei Cheung's Golden Empress restaurant. She lives in a flat above Silas' bar.</backstory> </character> <location id="861" name="The Fae Grove" aliases="Isolde's grove, Richmond grove, the Grove" realm="Earth (Fae-touched)"> <parkLocation>Richmond Park</parkLocation> <standingStones>ancient oak standing stones mark the boundary</standingStones> <timeBehavior>time moves differently — an hour inside can be minutes or days outside</timeBehavior> <flora>wildflowers bloom year-round</flora> <description>A hidden clearing that exists in a pocket between Earth and the Fae realm.</description> </location> <item id="2001" name="Heartstone Pendant" aliases="the pendant, Heartstone" type="Artifact" origin="Dymas"> <gemstoneColor>deep crimson</gemstoneColor> <chainMaterial>silver chain</chainMaterial> <size>roughly the size of a thumbnail</size> <behavior>pulses faintly with warmth when near a Hel portal</behavior> <glow>faint inner glow</glow> <description>Given to Aurora by an unknown benefactor.</description> </item> </codex> Write a fully fleshed out scene of at least 1000 words in the horror genre. A character is alone in a strange, isolated place at night. They came here for a reason, but something feels off from the moment they arrive. The wrongness builds slowly — sounds that shouldn't be there, things that move at the edge of vision, a growing certainty that they are not alone. Build tension through restraint, not through gore. Use the codex entries above as your world reference for the character and setting. Only include the prose of the scene without any markdown or commentary.

Model response

AI
I need to write a horror scene using the provided codex. Aurora Carter, at night, in the Fae Grove. She has a reason to be there, but something feels wrong. Tension builds slowly, restraint, no gore. Establish the setting: night, Fae Grove in Richmond Park. Use sensory details: cold air, strange sounds, distorted time. Aurora's motivation: she came here because of the Heartstone Pendant's behavior near Hel portals. Perhaps she's investigating or seeking something. She's alone. Build the wrongness: sounds without source, peripheral movement, growing certainty of being watched. Use Fae-touched nature of grove to introduce otherworldly elements. No monsters, just suggestion, unease. End with climax that maintains horror without resolution, leaving her trapped or transformed. Let's start with her arrival.
created_at"2026-07-07T20:17:19.696Z" 7/7/2026, 8:17:19 PM
model"aion-labs/aion-3.0-mini-20260707"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency954
moderation_latency(null)
generation_time5936
tokens_prompt812
tokens_completion209
native_tokens_prompt752
native_tokens_completion175
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)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
service_tier(null)
usage0.0007714
router(null)
provider_responses
0
endpoint_id"0ad7ab68-a351-4a96-b2ef-fa8fe13adae3"
id"ad3e700140e941ca9e319fb7b6cc57d4"
is_byokfalse
latency954
model_permaslug"aion-labs/aion-3.0-mini-20260707"
provider_name"AionLabs"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer(null)
request_id"req-1783455439-z0nsTKRXTGlji9FjBKIA"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1783455439-WSenHHCUlNeMpb32hOp2"
upstream_id"ad3e700140e941ca9e319fb7b6cc57d4"
total_cost0.0007714
cache_discount(null)
upstream_inference_cost0
provider_name"AionLabs"
response_cache_source_id(null)
data_region"global"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags0
58.68% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount121
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)
17.36% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount121
totalAiIsms2
found
0
word"tension"
count1
1
word"otherworldly"
count1
highlights
0"tension"
1"otherworldly"
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
narrationSentences14
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences14
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences14
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen14
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords121
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions0
unquotedAttributions0
matches(empty)
26.03% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions12
wordCount121
uniqueNames9
maxNameDensity2.48
worstName"Fae"
maxWindowNameDensity1.5
worstWindowName"Fae"
discoveredNames
Carter1
Fae3
Grove2
Richmond1
Park1
Heartstone1
Pendant1
Hel1
Fae-touched1
persons
0"Carter"
1"Pendant"
places
0"Fae"
1"Grove"
2"Richmond"
3"Park"
4"Hel"
globalScore0.26
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences11
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount121
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences14
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs4
mean0
std0
cv0
sampleLengths
036
140
227
318
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences14
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs25
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences14
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount122
adjectiveStacks0
stackExamples(empty)
adverbCount4
adverbRatio0.03278688524590164
lyAdverbCount2
lyAdverbRatio0.01639344262295082
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences14
echoCount0
echoWords(empty)
98.02% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences14
mean8.64
std3.41
cv0.395
sampleLengths
011
18
211
36
49
59
614
76
82
913
109
115
1213
135
100.00% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats0
diversityRatio0.7857142857142857
totalSentences14
uniqueOpeners11
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences13
matches
0"Perhaps she's investigating or seeking"
ratio0.077
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount2
totalSentences13
matches
0"I need to write a"
1"She has a reason to"
ratio0.154
100.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount5
totalSentences13
matches
0"I need to write a"
1"Aurora Carter, at night, in"
2"She has a reason to"
3"Tension builds slowly, restraint, no"
4"Aurora's motivation: she came here"
ratio0.385
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences13
matches(empty)
ratio0
23.81% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences6
technicalSentenceCount1
matches
0"End with climax that maintains horror without resolution, leaving her trapped or transformed."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags0
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
87.4633%