NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-07-01KWZ56D9DMKVCXB8XTXEADY3A
Run Details
Model:
Aion 3.0 Mini
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
49.5s
Cost:
$0.005982
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
81.34%
AI-ism adverb frequency
(details)
80.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
58.02%
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)
100.00%
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)
96.49%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
96.66%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
62.56%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
60.00%
Pronoun-first sentence starts
(details)
6.15%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
88.0411%
Overall
Model input
System
You are an expert and award-winning novel writer in the dark Literary Fiction 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> <character id="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</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> </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 literary fiction genre. Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret. 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
Messages
Meta
AI
"I thought that was you."
The voice cut through the
low hum of conversation, through the clink of glasses and the distant thump of a bassline leaking from someone's headphones.
Rory's hand paused mid-reach for
her pint. She turned.
Marcus
stood there, two feet away, looking exactly like himself but wrong. Like a photograph someone had taken and then aged with software.
The same brown eyes, the
same slight asymmetry in his smile, but the boy she remembered had softer edges.
This man wore them like
armour. "I'm sorry," she said. "Do I-" "It's me.
Marcus
."
He laughed, but it came
out tight. "You probably don't-" "
Marcus
."
The name landed like a
stone in still water.
Ripples spread outward, pulling up
images from the deep. Library tables covered in textbooks. Late nights at the union.
His jacket, always smelling of
cheap coffee and grass. "God.
Marcus
." "Yeah."
He shifted his weight
. "Can I...?"
She gestured at the stool
beside her.
The leather creaked as he
sat. "Two years," she said. "No. Three? Four?" "Seven."
He said it like a
doctor delivering bad news. "Seven years, Rory."
The name sounded different in
his mouth. Older. Heavier. "I've been-" "You vanished."
He said it flatly, without
accusation, which somehow made it worse. "One day you were there, and then you weren't. Emails bounced. Your number changed. I asked your mum, she said you'd moved to London. That was all she'd tell me." Rory took a long drink.
The bitter ale burned going
down. "I needed a fresh start." "From what?"
She looked at the bottles
behind the bar. Glenfiddich. Jameson. Absolut.
A row of amber and
clear soldiers standing at attention. "From everything." Silas appeared from nowhere, the way he did, polishing a glass that didn't need polishing. "Another?" "Whisky,"
Marcus
said. "Neat." Silas's eyes
flicked
to Rory for half a second. An acknowledgment. A question. She gave a tiny shrug.
He produced a tumbler and
poured with the precision of a man who'd done it ten thousand times. "Thanks."
Marcus
didn't touch it. He just stared at her. Rory felt the
weight
of his gaze like a physical thing. "You look good." "Don't." "Don't what?" "Don't do that. Don't make small talk like we're strangers who happen to share a postcode." He picked up the whisky, swirled it, set it down without drinking. "I spent six months trying to find you. Six months. And then I stopped. Because it was clear you didn't want to be found." "It wasn't about you." "I know."
He finally drank
. "That's what made it worse. It wasn't about me at all. I was just collateral damage." The words hit like a punch to the chest.
She'd prepared for this moment
a thousand times, in those sleepless nights when the city pressed in around her.
She'd imagined the conversation, scripted
her responses, perfected her deflections. But preparation meant nothing when the real thing sat beside you, wearing his hurt like a second skin. "I'm sorry," she said. The words felt thin. Inadequate. "I don't want an apology. I want to understand." "Some things aren't meant to be understood." "That's a cop-out." "It's the truth."
He laughed again, and this
time there was no tightness. Just bitterness. "You always did that. Created these walls around yourself, these labyrinths of deflection. I used to think it was mysterious. Then I realised it was just fear." "You didn't know me as well as you thought." "I knew you well enough to know you were running." The bartop felt cool under her palms.
She traced the grain, followed
the lines where wood met varnish, watched her fingers move like they belonged to someone else. "There was a man." The words came out before she could stop them. "Evan. We were together. He was..." "Was what?" "Wrong."
She said it softly
. "He was wrong,
Marcus
. And I stayed too long, and when I finally left, I had to do it clean. No threads. No connections. No way back." "You could have told me." "I couldn't tell anyone." She looked at him then,
really
looked. The crow's feet at the corners of his eyes, new since she'd last seen him. The grey flecking his temples. The wedding ring on his finger, catching the dim light. "I couldn't risk him finding me through you. Through anyone." "I would have-" "I know." She reached for his hand, stopped, pulled back. "I know you would have. That's exactly why I couldn't." The
silence
between them stretched, filled with the ambient noise of the bar. A woman laughed somewhere. Ice cubes clinked.
Somewhere a glass broke, and
someone cursed
softly
. "I got married,"
he said finally
. "I saw." "Her name's Priya. She's a paediatrician. We have a daughter." Rory's chest tightened. "That's wonderful." "Her name is Aurora." The bottom dropped out of her
stomach
. "
Marcus
..." "I wanted you to be part of her life. I wanted her to know you. But I couldn't find you." He drained the whisky in one long swallow. "Now I'm here, having a drink in some bar in Soho, and you just happen to be sitting at the counter." "I work here. Live upstairs." "That's not the point." He set the glass down with more force than necessary. "The point is that I stopped looking. I gave up. And then you appeared anyway. Like a ghost. Like you were never
really
gone." "I never wanted to hurt you." "Too late for that." He stood, buttoned his jacket. "I think I should go." "
Marcus
-" "Take care of yourself, Rory." He didn't look back as he walked to the door. The green neon sign
flickered
as he pushed through, casting his shadow long and thin across the floor. Then the door swung shut, and he
was gone
. Silas appeared again, collected the empty glass, wiped a ring of condensation from the bar. "Friend of yours?" "Was." She stared at the door. "Once." "He'll be back." "Don't think so." Silas shrugged. "Men who name their daughters after lost things aren't finished looking. They're just waiting for better directions." He walked away, leaving Rory alone with the
weight
of a name she hadn't earned and a past she couldn't outrun. The door stayed closed. The evening pressed in. And somewhere across the city, a little girl called Aurora was
being tucked
into bed by a father who still carried the ghost of her namesake in his chest.
created_at
"2026-07-07T20:44:28.376Z"
7/7/2026, 8:44:28 PM
model
"aion-labs/aion-3.0-mini-20260707"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
566
moderation_latency
(null)
generation_time
49338
tokens_prompt
4618
tokens_completion
2601
native_tokens_prompt
4208
native_tokens_completion
2278
native_tokens_completion_images
(null)
native_tokens_reasoning
952
native_tokens_cached
293
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
"stop"
service_tier
(null)
usage
0.00598244
router
(null)
provider_responses
0
endpoint_id
"0ad7ab68-a351-4a96-b2ef-fa8fe13adae3"
id
"e0fef8be077f4dbdb6dafe2f6ba67b8b"
is_byok
false
latency
566
model_permaslug
"aion-labs/aion-3.0-mini-20260707"
provider_name
"AionLabs"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1783457068-MaJq0EFSPorp1oRkDMFa"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783457068-GhOtGr7Fq2h1icixP6L5"
upstream_id
"e0fef8be077f4dbdb6dafe2f6ba67b8b"
total_cost
0.00598244
cache_discount
0.00015236
upstream_inference_cost
0
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
totalTags
21
adverbTagCount
2
adverbTags
0
"The name landed like [like]"
1
"he said finally [finally]"
dialogueSentences
72
tagDensity
0.292
leniency
0.583
rawRatio
0.095
effectiveRatio
0.056
81.34%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1072
totalAiIsmAdverbs
4
found
0
adverb
"softly"
count
2
1
adverb
"really"
count
2
highlights
0
"softly"
1
"really"
80.00%
AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0
"Blackwood"
found
0
"Marcus"
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
58.02%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1072
totalAiIsms
9
found
0
word
"weight"
count
3
1
word
"flicked"
count
1
2
word
"scripted"
count
1
3
word
"traced"
count
1
4
word
"silence"
count
1
5
word
"stomach"
count
1
6
word
"flickered"
count
1
highlights
0
"weight"
1
"flicked"
2
"scripted"
3
"traced"
4
"silence"
5
"stomach"
6
"flickered"
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
80
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
80
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
130
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
31
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1072
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
13
unquotedAttributions
0
matches
(empty)
100.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
15
wordCount
638
uniqueNames
5
maxNameDensity
0.94
worstName
"Rory"
maxWindowNameDensity
1.5
worstWindowName
"Rory"
discoveredNames
Ripples
1
Rory
6
Silas
4
Aurora
1
Marcus
3
persons
0
"Rory"
1
"Silas"
2
"Marcus"
places
(empty)
globalScore
1
windowScore
1
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
46
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1072
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
130
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
66
mean
16.24
std
15.73
cv
0.968
sampleLengths
0
5
1
32
2
2
3
48
4
6
5
13
6
40
7
7
8
13
9
7
10
13
11
9
12
2
13
43
14
16
15
2
16
23
17
16
18
4
19
36
20
10
21
14
22
1
23
2
24
52
25
4
26
21
27
56
28
9
29
9
30
7
31
3
32
3
33
39
34
9
35
10
36
28
37
19
38
2
39
32
40
5
41
51
42
3
43
20
44
28
45
6
46
2
47
10
48
5
49
4
96.49%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
2
totalSentences
80
matches
0
"was gone"
1
"being tucked"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
117
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
130
ratio
0
matches
(empty)
96.66%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
639
adjectiveStacks
0
stackExamples
(empty)
adverbCount
28
adverbRatio
0.04381846635367762
lyAdverbCount
7
lyAdverbRatio
0.010954616588419406
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
130
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
130
mean
8.25
std
7.13
cv
0.864
sampleLengths
0
5
1
25
2
7
3
2
4
12
5
11
6
19
7
6
8
4
9
2
10
10
11
3
12
10
13
9
14
5
15
5
16
9
17
2
18
5
19
2
20
7
21
6
22
4
23
3
24
10
25
3
26
7
27
1
28
1
29
2
30
13
31
30
32
5
33
6
34
5
35
2
36
8
37
1
38
1
39
1
40
10
41
2
42
15
43
1
44
3
45
1
46
9
47
2
48
2
49
5
62.56%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
12
diversityRatio
0.4307692307692308
totalSentences
130
uniqueOpeners
56
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
2
totalSentences
65
matches
0
"Somewhere a glass broke, and"
1
"Then the door swung shut,"
ratio
0.031
60.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
26
totalSentences
65
matches
0
"He laughed, but it came"
1
"His jacket, always smelling of"
2
"He shifted his weight"
3
"She gestured at the stool"
4
"He said it like a"
5
"He said it flatly, without"
6
"She looked at the bottles"
7
"She gave a tiny shrug."
8
"He produced a tumbler and"
9
"He just stared at her."
10
"He picked up the whisky,"
11
"He finally drank"
12
"She'd prepared for this moment"
13
"She'd imagined the conversation, scripted"
14
"He laughed again, and this"
15
"She traced the grain, followed"
16
"She said it softly"
17
"She looked at him then,"
18
"She reached for his hand,"
19
"he said finally"
ratio
0.4
6.15%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
59
totalSentences
65
matches
0
"The voice cut through the"
1
"Rory's hand paused mid-reach for"
2
"Marcus stood there, two feet"
3
"The same brown eyes, the"
4
"This man wore them like"
5
"He laughed, but it came"
6
"The name landed like a"
7
"Ripples spread outward, pulling up"
8
"Library tables covered in textbooks."
9
"His jacket, always smelling of"
10
"He shifted his weight"
11
"She gestured at the stool"
12
"The leather creaked as he"
13
"He said it like a"
14
"The name sounded different in"
15
"He said it flatly, without"
16
"Rory took a long drink."
17
"The bitter ale burned going"
18
"She looked at the bottles"
19
"A row of amber and"
ratio
0.908
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
65
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
20
technicalSentenceCount
1
matches
0
"Silas appeared from nowhere, the way he did, polishing a glass that didn't need polishing."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
21
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
9
fancyCount
1
fancyTags
0
"He laughed (laugh)"
dialogueSentences
72
tagDensity
0.125
leniency
0.25
rawRatio
0.111
effectiveRatio
0.028
88.0411%