NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXR7967D6472XTWAYDH60F
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Bad Writing Habits
Scenario:
Romance: separated couple reunites
Duration:
40.0s
Cost:
$0.086020
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
86.63%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
59.89%
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)
98.98%
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)
99.75%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
100.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
72.95%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
37.14%
Pronoun-first sentence starts
(details)
52.86%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
89.95%
Technical jargon density
(details)
72.37%
Useless dialogue additions
(details)
53.85%
Dialogue tag variety (said vs. fancy)
(details)
87.4789%
Overall
Model input
System
You are an expert and award-winning novel writer in the dark Romance 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="4415" name="Lucien Moreau" aliases="Lucien, Luc, the Frenchman" pronouns="he/him" species="Half-Demon" storyRole="Ally"> <eyeColor>heterochromatic — one amber, one black</eyeColor> <hair>slicked-back platinum blond</hair> <height>5'11"</height> <age>32</age> <cane>ivory-handled cane that conceals a thin blade</cane> <dress>tailored charcoal suits</dress> <description>An impeccably dressed fixer and information broker in London's supernatural underworld. He speaks four languages fluently.</description> <backstory>Born in Marseille to a human mother and a demon father from the realm of Avaros.</backstory> </character> <location id="858" name="Eva's Flat" aliases="Eva's place, the flat on Brick Lane" realm="Earth"> <cat>tabby cat named Ptolemy</cat> <security>three deadbolts on the front door</security> <description>A cramped one-bedroom flat above a curry house on Brick Lane, East London. Every surface is covered with books, scrolls, and research notes.</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 romance genre. Two people who parted on complicated terms are forced together again when one shows up unannounced at the other's flat. There's history between them — attraction, hurt, and things left unsaid. Write the scene from the moment the door opens. 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
The deadbolts slid back one
by one. Three of them.
Lucien counted each click from
the other side of the door, the ivory handle of his cane resting against his shoulder.
The door opened on a
chain. One bright blue eye appeared in the gap, then narrowed. "No." "You haven't even heard the question." "I don't need to."
Aurora moved to shut the
door.
His cane wedged into the
gap before the wood could meet the frame. "Three locks, Rory. You're either expecting trouble or you've already found it." "The trouble's currently standing in my hallway." "Eva's hallway," he corrected. "And it smells like curry and old paper. Charming, in a way that makes my eyes water." A long pause.
Somewhere behind her, a cat
meowed, low and indignant. Then the chain rattled loose, and the door swung wide.
She stood there in an
oversized jumper that swallowed her hands, black hair loose around her face. Tired.
He clocked the shadows beneath
her eyes, the way she held one wrist against her
stomach
.
The small crescent scar caught
the lamplight. "Five minutes," she said. "Generous."
She stepped back to let
him pass, and he caught the scent of her as he crossed the threshold. Bergamot and something warmer underneath. He
hated that he
noticed.
The flat was exactly as
advertised. Books stacked on every chair, scrolls unfurled across the kitchen table, a tabby cat perched atop a leaning tower of paperbacks like it owned the place. Ptolemy, presumably.
The cat regarded him with
the contempt of a creature that had read too much. "You left," she said. So they
were doing
this.
He set his cane against
the wall, taking his time. "I had business." "In Marseille. For six weeks. Without a word." "You knew where to find me." "That's not the point and you know it."
Her voice stayed level, but
her knuckles had gone white where she gripped the back of a chair. "You don't get to vanish after what happened and then turn up here like nothing's—" "Like nothing's what?" He turned.
The amber eye and the
black one both fixed on her. "Say it." She didn't. He stepped closer.
She held her ground, which
he admired and resented in equal measure. Most people gave way before him. She never had. Not in Silas' cellar with blood on her hands, not on the rain-slicked rooftop in Shoreditch, not now. "You're angry," he said. "Good. Angry I can work with. It's the
silence
that worries me." "I'm not angry." "You've got three deadbolts on a door that used to have one." Her jaw tightened. "Things changed while you were drinking rosé on the Riviera." "I wasn't drinking rosé." A pause. "It was a rather decent Bandol, if you must know." That earned him the ghost of something. Not a smile. The memory of where one used to live.
She looked away first, crossing
to the window, arms folded. "Why are you here, Lucien?" He could have lied.
He had a dozen good
lies ready, polished smooth as river stones. The job, the favour, the name of a man who needed finding. All true enough to pass.
He told her none of
them. "Because I spent six weeks across the Channel," he said, "and every single morning I woke up thinking about a woman who looked at me like I was worth saving. Even when I gave her no reason to." The room went
very
still.
Even the cat had stopped
washing its paw. "Don't," she said. Quiet now. "Don't do that." "Do what?" "Make this about feelings when it's
really
about whatever job's gone wrong this week." She turned to face him, and there was heat in her eyes, the kind that came before tears or violence and sometimes both. "I waited. Do you understand that? I sat in this flat with Eva's cat and I waited like an idiot, and you didn't call. You didn't write. You let me think you were dead." "I thought it was kinder." "Kinder."
She laughed, and it cracked
down the middle. "God, you
really
believe that."
He closed the distance between
them in two steps. Close enough now to see the
pulse
jumping at her throat, to count her breaths going shallow. She didn't retreat.
She tilted her chin up
instead, defiant, and he wanted to ruin himself on that defiance. "I came back,"
he said, low
. "For the job." "Among other things." "What other things?" Her voice had dropped to match his. The air between them had gone thick,
electric
, the way it always did, the way he'd told himself in Marseille that he'd imagined. He reached up. Slow, giving her every chance to stop him. He tucked a strand of dark hair behind her ear, and his fingertips grazed the curve of her jaw. She shivered. Tried to hide it. Failed. "You felt it too," he murmured. "That's why you're furious. Not because I left. Because you missed me, and you hate that you did." "Don't flatter yourself." "Tell me I'm wrong, then." His thumb
traced
the line of her cheekbone. "Tell me to leave, and I'll walk out that door and find someone else for the job. You'll never see me again. Just say it." Her breath caught. He watched the war play out across her face, the want and the hurt
grappling
for ground. Her hand came up and closed around his wrist, and for a moment he was certain she'd pull him away. She didn't. She held him there, against her skin,
as though deciding whether to keep him or break him
. "You don't get to do this," she whispered. "You don't get to leave and come back and make me feel—" "Feel what?" "This." Her grip tightened. "Whatever this is." The cat leapt from the books with a soft thud. Neither of them looked. The space between their mouths had narrowed to nothing, her breath warm against his lips, and he
could feel
the shape of every word she
wasn't saying
. "Rory," he said, and her name came out rougher than he meant it. The deadbolt downstairs rattled. A key in the building's main door. Footsteps on the stairs, quick and uneven, taking them two at a time. Aurora's eyes snapped wide. She shoved his wrist away and stepped back so fast she knocked into the table, sending a scroll rolling to the floor. "That's Eva," she breathed. "She wasn't supposed to be back until—" The
footsteps
stopped outside the door. A pause.
Then a fist hammered against
the wood, frantic, and Eva's voice came through muffled and breathless. "Rory! Rory, open the door, they followed me, they're right behind—" Lucien's hand was already on his cane.
created_at
"2026-05-31T11:47:17.958Z"
5/31/2026, 11:47:17 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1200
moderation_latency
(null)
generation_time
39803
tokens_prompt
4556
tokens_completion
1662
native_tokens_prompt
6409
native_tokens_completion
2159
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
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
"end_turn"
service_tier
"default"
usage
0.08602
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01Hhyh1XpxVfk1DUF3b223aP"
is_byok
false
latency
1200
model_permaslug
"anthropic/claude-4.8-opus-20260528"
provider_name
"Anthropic"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer
(null)
request_id
"req-1780228038-3t9teqStFaNNlL47QlT6"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780228038-h9NqxHqCOT9fklG7tsUp"
upstream_id
"msg_01Hhyh1XpxVfk1DUF3b223aP"
total_cost
0.08602
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
19
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
52
tagDensity
0.365
leniency
0.731
rawRatio
0
effectiveRatio
0
86.63%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1122
totalAiIsmAdverbs
3
found
0
adverb
"very"
count
1
1
adverb
"really"
count
2
highlights
0
"very"
1
"really"
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)
59.89%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1122
totalAiIsms
9
found
0
word
"stomach"
count
1
1
word
"silence"
count
1
2
word
"pulse"
count
1
3
word
"electric"
count
1
4
word
"traced"
count
1
5
word
"grappling"
count
1
6
word
"could feel"
count
1
7
word
"footsteps"
count
2
highlights
0
"stomach"
1
"silence"
2
"pulse"
3
"electric"
4
"traced"
5
"grappling"
6
"could feel"
7
"footsteps"
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
90
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
1
narrationSentences
90
filterMatches
(empty)
hedgeMatches
0
"tried to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
122
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
38
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1122
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
20
unquotedAttributions
0
matches
(empty)
100.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
3
wordCount
736
uniqueNames
3
maxNameDensity
0.14
worstName
"Quiet"
maxWindowNameDensity
0
worstWindowName
(null)
discoveredNames
Quiet
1
Marseille
1
Eva
1
persons
0
"Eva"
places
0
"Marseille"
globalScore
1
windowScore
1
98.98%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
49
glossingSentenceCount
1
matches
0
"as though deciding whether to keep him or break him"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1122
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
122
matches
0
"hated that he"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
61
mean
18.39
std
15.13
cv
0.822
sampleLengths
0
31
1
6
2
11
3
6
4
10
5
25
6
7
7
21
8
22
9
41
10
4
11
1
12
29
13
49
14
4
15
18
16
8
17
6
18
41
19
18
20
2
21
42
22
16
23
3
24
12
25
13
26
16
27
28
28
5
29
33
30
6
31
38
32
13
33
8
34
2
35
71
36
5
37
14
38
45
39
6
40
3
41
3
42
33
43
37
44
24
45
3
46
38
47
40
48
2
49
17
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
90
matches
(empty)
99.75%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
2
totalVerbs
133
matches
0
"were doing"
1
"wasn't saying"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
122
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
490
adjectiveStacks
0
stackExamples
(empty)
adverbCount
16
adverbRatio
0.0326530612244898
lyAdverbCount
4
lyAdverbRatio
0.00816326530612245
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
122
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
122
mean
9.2
std
7.54
cv
0.819
sampleLengths
0
7
1
3
2
21
3
6
4
10
5
1
6
6
7
10
8
13
9
12
10
7
11
4
12
17
13
3
14
9
15
10
16
17
17
1
18
16
19
7
20
4
21
1
22
19
23
5
24
5
25
6
26
26
27
2
28
15
29
4
30
5
31
10
32
3
33
8
34
6
35
26
36
15
37
5
38
11
39
2
40
2
41
3
42
12
43
6
44
3
45
18
46
4
47
12
48
3
49
12
72.95%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
6
diversityRatio
0.4672131147540984
totalSentences
122
uniqueOpeners
57
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
5
totalSentences
70
matches
0
"Somewhere behind her, a cat"
1
"Then the chain rattled loose,"
2
"All true enough to pass."
3
"Even the cat had stopped"
4
"Then a fist hammered against"
ratio
0.071
37.14%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
32
totalSentences
70
matches
0
"His cane wedged into the"
1
"She stood there in an"
2
"He clocked the shadows beneath"
3
"She stepped back to let"
4
"He hated that he noticed."
5
"He set his cane against"
6
"Her voice stayed level, but"
7
"He stepped closer."
8
"She held her ground, which"
9
"She never had."
10
"Her jaw tightened."
11
"She looked away first, crossing"
12
"He could have lied."
13
"He had a dozen good"
14
"He told her none of"
15
"She turned to face him,"
16
"She laughed, and it cracked"
17
"He closed the distance between"
18
"She didn't retreat."
19
"She tilted her chin up"
ratio
0.457
52.86%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
57
totalSentences
70
matches
0
"The deadbolts slid back one"
1
"Lucien counted each click from"
2
"The door opened on a"
3
"Aurora moved to shut the"
4
"His cane wedged into the"
5
"A long pause."
6
"She stood there in an"
7
"He clocked the shadows beneath"
8
"The small crescent scar caught"
9
"She stepped back to let"
10
"Bergamot and something warmer underneath."
11
"He hated that he noticed."
12
"The flat was exactly as"
13
"Books stacked on every chair,"
14
"The cat regarded him with"
15
"He set his cane against"
16
"Her voice stayed level, but"
17
"The amber eye and the"
18
"He stepped closer."
19
"She held her ground, which"
ratio
0.814
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
70
matches
(empty)
ratio
0
89.95%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
27
technicalSentenceCount
2
matches
0
"She stood there in an oversized jumper that swallowed her hands, black hair loose around her face."
1
"Close enough now to see the pulse jumping at her throat, to count her breaths going shallow."
72.37%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
19
uselessAdditionCount
2
matches
0
"Her voice stayed, but her knuckles had gone white where she gripped the back of a chair"
1
"he said, low"
53.85%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
12
fancyCount
5
fancyTags
0
"he corrected (correct)"
1
"She laughed (laugh)"
2
"he murmured (murmur)"
3
"she whispered (whisper)"
4
"she breathed (breathe)"
dialogueSentences
52
tagDensity
0.231
leniency
0.462
rawRatio
0.417
effectiveRatio
0.192
87.4789%