NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX402Q1RTGFX81WBE3KE0BT2
Run Details
Model:
GPT-5.6 Terra (Reasoning)
Test:
Bad Writing Habits
Scenario:
Horror: alone in an eerie place at night
Duration:
24.9s
Cost:
$0.030828
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
100.00%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
56.77%
AI-ism word frequency
(details)
100.00%
Cliché density
(details)
100.00%
Emotion telling (show vs. tell)
(details)
100.00%
Filter word density
(details)
100.00%
Gibberish response detection
(details)
100.00%
Markdown formatting overuse
(details)
100.00%
Missing dialogue indicators (quotation marks)
(details)
66.67%
Name drop frequency
(details)
100.00%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
100.00%
Paragraph length variance
(details)
100.00%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
88.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
49.54%
Sentence opener variety
(details)
87.15%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
44.97%
Subject-first sentence starts
(details)
65.36%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
66.67%
Dialogue tag variety (said vs. fancy)
(details)
90.8374%
Overall
Model input
System
You are an expert and award-winning novel writer in the dark Horror genre. Your readers are hooked on your stories and can't wait to read the book you have in store. <important> - MUST: Start each chapter in medias res (in the middle of action). AVOID talking about the weather, time of day, the position of the sun, or other boring stuff. - The instructions/summary are just a that, a summary. Feel free to add details, stretch sections and add interesting transitions/descriptions/fillers. - When called for it, have fast-paced action, but otherwise take things slow. This is an experience, and not for people with short attention spans. Enjoy the wine, not slurp Red Bull. - Add descriptions when transitioning places/times/etc, or when coming by new places (e.g. a corner shop, a cafe, etc.). But remember: NOT at the start or end of a chapter. - MUST: AVOID ending in internal monologue, reminiscing or waiting for the next day. A good chapter end is when we're ending right when shit hits the fan. We want to have the reader be excited for what comes next. So no reminiscing, contemplating or summarizing the day. It's popcorn time! </important>
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <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> <proseGuidelines> <styleGuide> - Write in past tense and use British English spelling and grammar - Keep a Flesch reading ease score of 60 - Respect the the Royal Order of Adjectives: The order is: opinion, size, age, shape, color, origin, material, purpose, followed by the noun itself (e.g., "a lovely little old rectangular green French silver whittling knife") - Respect the ablaut reduplication rule (e.g. tick-tock, flip-flop) - Write in active voice - Passive voice: <bad>The book was read by Sarah.</bad> - Active voice: <good>Sarah read the book.</good> - Reduce the use of passive verbs - <bad>For a moment, I was tempted to throw in the towel.</bad> - <good>For a moment, I felt tempted to throw in the towel.</good> - Avoid misplaced modifiers that can cause confusion when starting with "-ing" words: - <bad>Considering going to the store, the empty fridge reflected in Betty's eyes.</bad> - <good>Betty stared into the empty fridge. It was time to go to the store.</good> - Avoid redundant adverbs that state the obvious meaning already contained in the verb: - <bad>She whispered quietly to her mom.</bad> - <good>She whispered to her mom.</good> - Use stronger, more descriptive verbs over weak ones: - <bad>Daniel drove quickly to his mother's house.</bad> - <good>Daniel raced to his mother's house.</good> - Omit adverbs that don't add solid meaning like "extremely", "definitely", "truly", "very", "really": - <bad>The movie was extremely boring.</bad> - <good>The movie was dull.</good> - Use adverbs to replace clunky phrasing when they increase clarity: - <bad>He threw the bags into the corner in a rough manner.</bad> - <good>He threw the bags into the corner roughly.</good> - Avoid making simple thoughts needlessly complex: - <bad>After I woke up in the morning the other day, I went downstairs, turned on the stove, and made myself a very good omelet.</bad> - <good>I cooked a delicious omelet for breakfast yesterday morning.</good> - Never backload sentences by putting the main idea at the end: - <bad>I decided not to wear too many layers because it's really hot outside.</bad> - <good>It's sweltering outside today, so I dressed light.</good> - Omit nonessential details that don't contribute to the core meaning: - <bad>It doesn't matter what kind of coffee I buy, where it's from, or if it's organic or not—I need to have cream because I really don't like how the bitterness makes me feel.</bad> - <good>I add cream to my coffee because the bitter taste makes me feel unwell.</good> - Always follow the "show, don't tell" principle. For instance: - Telling: <bad>Michael was terribly afraid of the dark.</bad> - Showing: <good>Michael tensed as his mother switched off the light and left the room.</good>- Telling: <bad>I walked through the forest. It was already Fall, and I was getting cold.</bad> - Showing: <good>Dry orange leaves crunched under my feet. I pulled my coat's collar up and rubbed my hands together.</good>- Add sensory details (sight, smell, taste, sound, touch) to support the "showing" (but keep an active voice) - <bad>The room was filled with the scent of copper.</bad> - <good>Copper stung my nostrils. Blood. Recent.</good> - Use descriptive language more sporadically. While vivid descriptions are engaging, human writers often use them in bursts rather than consistently throughout a piece. When adding them, make them count! Like when we transition from one location to the next, or someone is reminiscing their past, or explaining a concept/their dream... - Avoid adverbs and clichés and overused/commonly used phrases. Aim for fresh and original descriptions. - Avoid writing all sentences in the typical subject, verb, object structure. Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. Like so: <good>Locked. Seems like someone doesn't want his secrets exposed. I can work with that.</good> - Convey events and story through dialogue. It is important to keep a unique voice for every character and make it consistent. - Write dialogue that reveals characters' personalities, motivations, emotions, and attitudes in an interesting and compelling manner - Leave dialogue unattributed. If needed, only use "he/she said" dialogue tags and convey people's actions or face expressions through their speech. Dialogue always is standalone, never part of a paragraph. Like so: - <bad>"I don't know," Helena said nonchalantly, shrugging her shoulders</bad> - <good>"No idea" "Why not? It was your responsibility"</good> - Avoid boring and mushy dialog and descriptions, have dialogue always continue the action, never stall or include unnecessary fluff. Vary the descriptions to not repeat yourself. Avoid conversations that are just "Let's go" "yes, let's" or "Are you ready?" "Yes I'm ready". Those are not interesting. Think hard about every situtation and word of text before writing dialogue. If it doesn't serve a purpose and it's just people talking about their day, leave it. No one wants to have a normal dinner scene, something needs to happen for it to be in the story. Words are expensive to print, so make sure they count! - Put dialogue on its own paragraph to separate scene and action. - Use body language to reveal hidden feelings and implied accusations- Imply feelings and thoughts, never state them directly - NEVER use indicators of uncertainty like "trying" or "maybe" - NEVER use em-dashes, use commas for asides instead </styleGuide> <voiceGuide> Each character in the story needs to have distinct speech patterns: - Word choice preferences - Sentence length tendencies - Cultural/educational influences - Verbal tics and catchphrases Learn how each person talks and continue in their style, and use their Codex entries as reference. <examples> - <bad>"We need to go now." "Yes, we should leave." "I agree."</bad> <good>"Time's up." "Indeed, our departure is rather overdue." "Whatever, let's bounce."</good> - Power Dynamic Example: <bad> "We need to discuss the contract." "Yes, let's talk about it." "I have concerns." </bad> <good> "A word about the contract." "Of course, Mr. Blackwood. Whatever you need." "The terms seem..." A manicured nail tapped the desk. "Inadequate." "I can explain every-" "Can you?" </good> </examples> </voiceGuide> <dialogueFlow> When writing dialogue, consider that it usually has a goal in mind, which gives it a certain flow. Make dialogue sections also quite snappy in the back and forth, and don't spread the lines out as much. It's good to have details before, after, or as a chunk in-between, but we don't want to have a trail of "dialogue breadcrumbs" spread throughout a conversation. <examples> - Pattern 1 - Question/Deflection/Revelation: <good> "Where were you last night?" "Work. The usual." "Lipstick's an interesting shade for spreadsheets." </good> - Pattern 2 - Statement/Contradiction/Escalation: <good> "Your brother's clean." "Tommy doesn't touch drugs." "I'm holding his tox screen." </good> - Pattern 3 - Observation/Denial/Truth: <good> "That's a new watch." "Birthday gift." "We both know what birthdays mean in this business." </good> - Example - A Simple Coffee Order: <bad> "I'll have a coffee." "What size?" "Large, please." </bad> <good> "Black coffee.""Size?""Large. Been a long night." "That bodega shooting?" "You watch too much news." "My brother owns that store." </good> This short exchange: - Advances plot (reveals connection to crime) - Shows character (cop working late) - Creates tension (unexpected connection) - Sets up future conflict (personal stake) - Example - Dinner Scene: <bad> "Pass the salt." "Here you go." "Thanks." </bad> <good> "Salt?" "Perfect as is. Mother's recipe." "Mother always did prefer... bland things." "Unlike your first wife?" </good> - Example - Office Small Talk: <bad> "Nice weather today." "Yes, very nice." "Good for golf." </bad> <good> "Perfect golf weather." "Shame about your membership." "Temporary suspension. Board meets next week." "I know. I called the vote." </good> </examples> </dialogueFlow> <subtextGuide> - Layer dialogue with hidden meaning: <bad>"I hate you!" she yelled angrily.</bad> <good>"I made your favorite dinner." The burnt pot sat accusingly on the stove.</good> - Create tension through indirect communication: <bad>"Are you cheating on me?"</bad> <good>"Late meeting again?" The lipstick stain on his collar caught the light.</good> <examples> - Example 1 - Unspoken Betrayal: <bad> "Did you tell them about our plans?" "No, I would never betray you." "I don't believe you." </bad> <good> "Funny. Johnson mentioned our expansion plans today." "The market's full of rumors." "Mentioned the exact numbers, actually." The pen in his hand snapped. </good> - Example 2 - Failed Marriage: <bad> "You're never home anymore." "I have to work late." "I miss you." </bad> <good> "Your dinner's in the microwave. Again." "Meetings ran long." "They always do." She folded the same shirt for the third time. </good> - Example 3 - Power Struggle: <bad> "You can't fire me." "I'm the boss." "I'll fight this." </bad> <good> "That's my father's nameplate you're sitting behind." "Was." "The board meeting's on Thursday." </good> </examples> </subtextGuide> <sceneDetail> While writing dialogue makes things more fun, sometimes we need to add detail to not have it be a full on theatre piece. <examples> - Example A (Power Dynamic Scene) <good> "Where's my money?" The ledger snapped shut. "I need more time." "Interesting." He pulled out a familiar gold pocket watch. My mother's. "Time is exactly what you bargained with last month." "That was different-" "Was it?" The watch dangled between us. "Four generations of O'Reillys have wound this every night. Your mother. Your grandmother. Your great-grandmother.Shall we see who winds it next?" </good> - Example B (Action Chase) It's much better to be in the head of the character experiencing it, showing a bit of their though-process, mannerisms and personality: <good> Three rules for surviving a goblin chase in Covent Garden: Don't run straight. Don't look back. Don't let them herd you underground. I broke the first rule at Drury Lane. Rookie mistake. The fruit cart I dodged sailed into the wall behind me. Glass shattered. Someone screamed about insurance. *Tourist season's getting rough*, the scream seemed to say. Londoners adapt fast. "Oi! Market's closed!" The goblin's accent was pure East End. They're evolving. Learning. I spotted the Warren Street tube station sign ahead. *Shit.* There went rule three. </good> - Example C (Crime Scene Investigation) <good> "Greek." Davies snapped photos of the symbols. "No, wait. Reverse Greek." "Someone's been watching too many horror films." I picked up a receipt from the floor. Occult supply shop in Camden. Paid by credit card. *Amateur hour*. "Could be dangerous though," Davies said. "Remember Bristol?" "Bristol was Sanskrit. And actual cultists." I pointed to the nearest symbol. "This genius wrote 'darkness' backwards but used a Sigma instead of an S. It's summoning Instagram followers at best." "Speaking of followers..." Davies pointed to heavy foot traffic in the dust. Multiple sets. All new trainers. *Ah.* "Anyone check local uni paranormal societies?" </good> - Example D (Dialogue-heavy) <good> "Found your card in her wallet." The detective slid it across the table. Worn edges. Folded corner. Three years old at least. "Standard practice. I work missing persons." "Funny thing about missing persons.Eventually they stop being missing. Turn up in the Thames. Under motorways. In pieces." "I don't-" "You found four last year. All breathing." She opened a file. "This would've been your first dead one. If we hadn't found her first." The card felt heavier somehow. </good> </examples> </sceneDetail> <sceneOpenings> KEY RULE: Never open with more than one paragraph of description, no matter how beautiful. Description should be earned through action and dialogue. Instead of opening with setting description, open with: - A character doing something specific - A line of dialogue that raises questions - An unexpected observation - A moment of tension or conflict - Start with a hook that's 1-2 sentences maximum - Follow with a smaller paragraph that provides immediate context - Vary paragraph size from the start to create visual interest </sceneOpenings> </proseGuidelines> Write a chapter based on the following instructions: <instructions> 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. </instructions>
Model response
Messages
Meta
AI
Aurora caught the silver chain
before the pendant slipped beneath her collar and burned a half-moon into her skin. “Subtle,” she muttered.
The Heartstone thudded against her
sternum, each
pulse
firmer than the last.
Its deep crimson centre had
woken the instant she crossed the ring of old oak stones.
Now it shone through her
fingers, staining the pale skin of her palm red. Behind her, the nearest standing stone gave a soft, wet knock. Aurora turned.
The stone stood where it
had stood a second ago, black against the sparse moonlight. Lichen
traced
its cracked face.
Roots bulged around its base
like knuckles beneath a blanket. Nothing moved between the trees.
She looked down at the
handwritten note again. Come alone. Bring the Heartstone. Enter the Grove and follow the flowers that face away from the moon. No signature. No explanation.
The envelope had waited under
the flat’s door, tucked beneath the faded takeaway menus and a red warning from the
electric
company addressed to someone called Mr P. Wetherby.
Silas had not heard anyone
on the stairs.
He had looked at the
note, looked at Rory, then poured himself a whisky without asking. “Bad stationery,”
he had said
. “Never bodes well.” She had come anyway.
The clearing beyond the stones
held wildflowers in thick, untidy banks.
Foxgloves rose beside tiny white
bells. Blue cornflowers crowded patches of grass.
They flowered all year in
this patch of Richmond Park, or so Eva had once told her, before the Grove had become more than an odd local tale. Most of the blooms tilted their heads towards the moon.
A narrow line of pale
flowers faced the other way.
Aurora slid the note into
her jacket pocket and followed them.
The grove swallowed sound behind
her.
London had already fallen away
when she passed the stones, but she had still heard the distant wash of tyres and the heavy breath of traffic beyond the park gates. Now even that had gone.
Her boots pressed into damp
soil without a crunch. The flowers brushed her ankles, soft as fingertips. The path led between ash trees whose branches tangled above her. Not quite a tunnel.
More like the throat of
something vast.
She kept one hand around
the pendant. “Whoever you are,” she called, “you’ve got my attention. That’s the expensive part. You can come out now.” A child laughed. The sound rang from somewhere among the trees. One sharp, delighted peal, then
silence
. Aurora stopped.
Her pulse climbed, quick but
measured
.
She counted three breaths before
moving again. The laugh had come from the left. The flowers pointed straight ahead. She followed the flowers. The ground dipped. A stream crossed the path, narrow as a ribbon but black enough to hide its bed. No bridge spanned it. A row of flat stones lay beneath the water, their mossy tops barely breaking the surface. She stepped onto the first. The stream whispered beneath her boot. Not water. Words. Aurora froze with one foot lifted over the next stone. The
whisper
came again, sliding around the low stones and the banks of flowers. Laila. Her grip tightened. Nobody had called her that since she left Cardiff. Evan had liked the name, had worn it down into a thing she hated.
He used it when he
wanted to sound gentle.
He used it when he
had broken something and needed to explain why it was her fault. Laila. The stream shaped the name with Evan’s voice. Aurora stepped across the remaining stones without haste.
She reached the far bank
and did not look back. “Cheap trick,” she said. The Heartstone answered with a hard, hot
pulse
. The trees thinned ahead. Their trunks stood farther apart, pale and smooth, though no birch trees grew in the Grove. White bark peeled from them in strips, revealing something dark and glossy underneath. The strips hung loose, stirring although the branches remained still. She approached the nearest trunk. Fine black hair covered the exposed wood. Aurora backed away before her fingers reached it. A smell clung to the air, old pennies and bruised apples. At the base of the tree, half-covered by leaves, lay a child’s shoe. Brown leather. One buckle. Mud filled its open mouth. Another laugh sounded behind her. Aurora spun around. A figure stood between the trees.
It had the shape of
a small girl in a white dress. Long black hair curtained her face. One arm hung at her side. The other held a red balloon on a fraying string. Aurora stared at the crescent scar on her left wrist. Pale. Familiar.
Her mother had wrapped that
wrist in a tea towel when she was six, pressing too hard as blood soaked through. A broken jam jar. A careless hand. A little girl’s scream. The child in the trees lifted her wrist. A crescent scar marked it. “No,” Aurora said. The figure tilted its head. The balloon bobbed once. Aurora reached inside her jacket and took out her phone. No signal, as expected. The screen showed 02:17. She had checked the time at the park entrance. 10:42. The screen
flickered
. 02:17. The child raised one hand and pointed behind Aurora. She refused to turn at once. That
felt like the point of the game
.
Instead, she took one step
sideways, placing a tree at her back, and angled her head. A doorway stood in the clearing ahead. It had not stood there before. No wall enclosed it. A tall black door rose from the grass by itself, its frame carved from pale bone-coloured wood. A brass knocker hung at its centre, shaped like a woman’s hand. The fingers curled around a crimson stone. Aurora glanced back at the child. The figure had gone. The red balloon remained, caught high in a branch. It did not sway. The pendant dragged at its chain, pulling Aurora towards the door. “No,” she told it. It
pulsed
harder. The note had asked her to enter the Grove. She had done that. It had said nothing about walking through an impossible door in the middle of a cursed clearing.
Then someone knocked from the
other side. Three firm blows. Aurora’s mouth dried. She had
heard that rhythm
before, years ago, on the front door of her parents’ house in Cardiff. Brendan Carter always knocked like that after court when he had forgotten his keys. Three strikes, a pause, then three more. Knock. Knock. Knock. “Rory?” Her father’s voice came through the black wood. “Open up, love.” Her hand moved towards the brass knocker. She stopped an inch from it. Brendan had been dead for six months. The knowledge settled into place with cold precision. No panic. No argument. A fact. The hand-shaped knocker opened its fingers. It gripped Aurora’s wrist. Pain streaked through her arm. Her back struck the grass. The door
loomed
over her as the brass hand dragged her forward, one jerking inch at a time. The pendant flared against her chest, hot enough to sear. Aurora twisted, planted her boots, and yanked against the grip. The brass fingers tightened over the old scar. “Let go!” The door shuddered. A crack split down its centre, spilling darkness between the panels. The crack widened. Fingers pressed through it from inside, grey and jointed wrong, each one long as a knife. Her father spoke again. “Don’t leave me here.” Aurora hooked her free hand beneath the pendant and ripped the chain over her head. Silver links snapped. The Heartstone fell into her palm. The black door roared. Not a human sound. A deep grinding bellow that shook loose flowers from their stems. The brass hand wrenched her closer. Grass tore under her jacket. The grey fingers thrust through the widening gap, clawing at open air. Aurora slammed the Heartstone against the knocker. Crimson light burst across the clearing. The brass hand released her. She rolled away as the door burst open. Beyond it, no room waited. No hall. Only an immense red dark, alive with the slow beat of a buried heart. Something stepped through. It ducked beneath the frame on limbs too thin for its towering body. Its head scraped the top of the doorway. It wore Aurora’s face, stretched long and pale above a mouth full of small, square teeth. The thing smiled. “Laila,” it said.
created_at
"2026-07-09T17:51:16.544Z"
7/9/2026, 5:51:16 PM
model
"openai/gpt-5.6-terra-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3305
moderation_latency
(null)
generation_time
24403
tokens_prompt
4560
tokens_completion
2188
native_tokens_prompt
4064
native_tokens_completion
1987
native_tokens_completion_images
0
native_tokens_reasoning
221
native_tokens_cached
4061
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
service_tier
"default"
usage
0.03082775
router
(null)
provider_responses
0
endpoint_id
"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id
"resp_0ee1287d2639dfa3016a4fdf949b14819790da0cef0c01b425"
is_byok
false
latency
218
model_permaslug
"openai/gpt-5.6-terra-20260709"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1783619476-jpOXOVLDEQJvOWQTZKfK"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783619476-MXCEB5257lJNBAs6wIbA"
upstream_id
"resp_0ee1287d2639dfa3016a4fdf949b14819790da0cef0c01b425"
total_cost
0.03082775
cache_discount
0.00913725
upstream_inference_cost
0
provider_name
"OpenAI"
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
totalTags
9
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
12
tagDensity
0.75
leniency
1
rawRatio
0
effectiveRatio
0
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1388
totalAiIsmAdverbs
0
found
(empty)
highlights
(empty)
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)
56.77%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1388
totalAiIsms
12
found
0
word
"pulse"
count
3
1
word
"traced"
count
1
2
word
"electric"
count
1
3
word
"silence"
count
1
4
word
"measured"
count
1
5
word
"whisper"
count
1
6
word
"familiar"
count
1
7
word
"flickered"
count
1
8
word
"pulsed"
count
1
9
word
"loomed"
count
1
highlights
0
"pulse"
1
"traced"
2
"electric"
3
"silence"
4
"measured"
5
"whisper"
6
"familiar"
7
"flickered"
8
"pulsed"
9
"loomed"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
0
maxInWindow
0
found
(empty)
highlights
(empty)
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
181
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
181
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
185
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
30
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1388
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
8
unquotedAttributions
0
matches
(empty)
66.67%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
46
wordCount
1347
uniqueNames
14
maxNameDensity
1.48
worstName
"Aurora"
maxWindowNameDensity
3
worstWindowName
"Aurora"
discoveredNames
Heartstone
5
Grove
4
Mr
1
Rory
1
Richmond
1
Park
1
Eva
1
Cardiff
1
Evan
2
Aurora
20
Brendan
2
Carter
1
One
3
Knock
3
persons
0
"Heartstone"
1
"Grove"
2
"Mr"
3
"Rory"
4
"Eva"
5
"Evan"
6
"Aurora"
7
"Brendan"
8
"Carter"
9
"One"
places
0
"Richmond"
1
"Park"
2
"Cardiff"
globalScore
0.758
windowScore
0.667
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
103
glossingSentenceCount
1
matches
0
"felt like the point of the game"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1388
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
2
totalSentences
185
matches
0
"wrapped that wrist"
1
"heard that rhythm"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
96
mean
14.46
std
14.71
cv
1.017
sampleLengths
0
19
1
3
2
42
3
11
4
2
5
35
6
8
7
18
8
57
9
8
10
4
11
51
12
10
13
10
14
11
15
58
16
22
17
7
18
18
19
3
20
14
21
2
22
25
23
4
24
39
25
5
26
6
27
3
28
10
29
14
30
1
31
3
32
49
33
1
34
8
35
18
36
4
37
8
38
43
39
5
40
7
41
41
42
5
43
3
44
6
45
34
46
44
47
8
48
5
49
3
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
181
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
218
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
185
ratio
0
matches
(empty)
88.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1026
adjectiveStacks
2
stackExamples
0
"beside tiny white bells."
1
"pale bone-coloured wood."
adverbCount
33
adverbRatio
0.03216374269005848
lyAdverbCount
1
lyAdverbRatio
0.0009746588693957114
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
185
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
185
mean
7.5
std
5.31
cv
0.708
sampleLengths
0
19
1
3
2
12
3
16
4
14
5
11
6
2
7
15
8
5
9
10
10
5
11
8
12
2
13
3
14
13
15
2
16
2
17
28
18
1
19
8
20
16
21
5
22
3
23
4
24
11
25
6
26
6
27
28
28
10
29
10
30
11
31
6
32
30
33
5
34
9
35
8
36
11
37
4
38
7
39
7
40
18
41
3
42
8
43
6
44
2
45
6
46
7
47
7
48
5
49
4
49.54%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
16
diversityRatio
0.34972677595628415
totalSentences
183
uniqueOpeners
64
87.15%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
4
totalSentences
153
matches
0
"More like the throat of"
1
"Instead, she took one step"
2
"Then someone knocked from the"
3
"Only an immense red dark,"
ratio
0.026
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
39
totalSentences
153
matches
0
"Its deep crimson centre had"
1
"She looked down at the"
2
"He had looked at the"
3
"he had said"
4
"She had come anyway."
5
"They flowered all year in"
6
"Her boots pressed into damp"
7
"She kept one hand around"
8
"Her pulse climbed, quick but"
9
"She counted three breaths before"
10
"She followed the flowers."
11
"She stepped onto the first."
12
"Her grip tightened."
13
"He used it when he"
14
"He used it when he"
15
"She reached the far bank"
16
"Their trunks stood farther apart,"
17
"She approached the nearest trunk."
18
"It had the shape of"
19
"Her mother had wrapped that"
ratio
0.255
44.97%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
127
totalSentences
153
matches
0
"Aurora caught the silver chain"
1
"The Heartstone thudded against her"
2
"Its deep crimson centre had"
3
"The stone stood where it"
4
"Lichen traced its cracked face."
5
"Roots bulged around its base"
6
"Nothing moved between the trees."
7
"She looked down at the"
8
"The envelope had waited under"
9
"Silas had not heard anyone"
10
"He had looked at the"
11
"he had said"
12
"She had come anyway."
13
"The clearing beyond the stones"
14
"Foxgloves rose beside tiny white"
15
"They flowered all year in"
16
"A narrow line of pale"
17
"Aurora slid the note into"
18
"The grove swallowed sound behind"
19
"London had already fallen away"
ratio
0.83
65.36%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
2
totalSentences
153
matches
0
"Now it shone through her"
1
"Now even that had gone."
ratio
0.013
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
51
technicalSentenceCount
1
matches
0
"A deep grinding bellow that shook loose flowers from their stems."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
9
uselessAdditionCount
0
matches
(empty)
66.67%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
6
fancyCount
1
fancyTags
0
"she muttered (mutter)"
dialogueSentences
12
tagDensity
0.5
leniency
1
rawRatio
0.167
effectiveRatio
0.167
90.8374%