NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHTXAG3BYNQYE8VVK57JPQMD
Run Details
Model:
Minimax M2.5
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
6m 3s
Cost:
$0.003859
Provider:
Inceptron
Evaluation summary
Score
Evaluator
Details Link
88.89%
Adverbs in dialogue tags
(details)
96.30%
AI-ism adverb frequency
(details)
80.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
66.67%
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)
15.92%
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)
90.03%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
68.66%
Sentence opener variety
(details)
40.16%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
56.39%
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)
86.7670%
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
The woman at the bar
looked up when Aurora wiped down the counter for the third time in ten minutes. "You've got a nervous habit," she said.
Aurora's hand stilled on the
mahogany. That voice.
That particular lilt, somewhere between
Cardiff and somewhere else entirely.
She knew it the way
you
know
your own heartbeat, buried somewhere under years of deliberate forgetting. "No. Just thorough." "Always were."
Aurora set down the cloth
slowly
.
The Raven's Nest had emptied
out after the evening rush, leaving only the regulars nursing whiskeys in corners and the low murmur of jazz from the ancient speakers. Late November.
The kind of cold that
crept into your bones and stayed. Outside, Soho hummed its familiardirty song, but in here, under the green neon glow and the old maps lining the walls, it
felt like another world entirely
. She turned. Eva looked different. Of course she looked different.
The Eva she remembered had
been all sharp angles and restless energy, hair cropped short, always moving. This woman had curves now, soft ones, and her auburn hair fell in waves past her shoulders.
She'd filled out somehow, become
someone who occupied space differently. But her eyes were the same. Dark and knowing, with that perpetual amusement that used to drive Aurora mad. "Eva." "Rory."
Eva tilted her head
. "Still going by that, then?" "It's what people call me." "Aren't people original."
Eva took a sip of
whatever she'd been drinking.
Gin, by the look of
it. neat. "Funny, running into you here. Last I heard, you were in London. Just didn't picture you'd be behind a bar." "I don't work here. I live here." "Overnight, is it? Slumming it with the regulars?" "Upstairs."
Aurora gestured vaguely toward the
ceiling. "Flat above." "Ah."
Eva's expression flickered, something unreadable
passing across her features. "Made it, then." It wasn't a question.
Aurora wasn't sure how to
answer anyway, so she didn't. The
silence
stretched between them, filled with the smooth jazz and the soft clink of glasses from the back corner where old Tom
was getting
philosophical with his fifth pint. "You're staring," Eva said. "You look different." "Ten years will do that." "Has it been that long?" "Eleven in March." Aurora did the math.
She'd left Cardiff in March
of 2014. Left Eva behind, too, in that cramped flat they used to share, with the mould problem in the bathroom and the landlord who never fixed the heating. Left without saying goodbye properly, just a note on the kitchen table and a text that said *I'm sorry, I can't do this anymore.* She'd meant the relationship. The friendship. All of it. "What are you doing in London?" Aurora asked. "Work." "What kind of work?" "The paying kind." Eva smiled, but it didn't reach her eyes. "I'm over at the Savoy. Conference." "Sounds fancy." "Boring. The kind where men in suits talk for hours about things that could be said in minutes." Eva swirled her drink. "You
know
how it is." "I don't, actually." "No?" Eva looked at her properly then, taking in the black delivery uniform, the flat shoes, the lack of makeup. "What do you do these days, Rory? Besides living above bars and wiping down counters?" "I deliver food." "Food." "Chinese. From Golden Empress, two streets over." "Uh-huh." Eva's tone had shifted, something sharp creeping in. "And what's that like? Running deliveries around London? Exciting work?" "It's honest." "Is that what we're calling it now?" Aurora felt the old defensiveness rising, the urge to explain herself, to justify. She pushed it down. "Why are you here, Eva?" "I told you. Work conference." "That's not what I meant." Eva held her gaze for a long moment. The jazz shifted to something slower, sadder. In the corner, old Tom had nodded off, glass still pressed to his chest. "I heard you were here," Eva said finally. "From a mutual friend. Cardiff's smaller than you'd think, people talk. I thought..." She stopped. Took a breath. "I thought I'd come see for myself." "See what?" "If you were okay." The words hung there, strange and heavy. Aurora
tried to
find the angle, the hidden blade in them, but there was nothing. Just concern. After everything. "I'm fine." "Sure." "I am." "Rory." Eva set down her glass. "You don't have to pretend. Not with me. You never had to pretend with me." "I'm not pretending. I just..." Aurora ran a hand through her hair, the motion so
familiar
it was automatic. "I'm not who I was. That's all. I'm not trying to be." "I
know
." Eva's voice softened. "That's what I came to see. The not-being." The door at the front swung open, letting in a gust of cold air and two regulars from the accounting firm round the corner.
They nodded at Aurora, made
their way to their usual spot. The moment
fractured
. "Can I get you another drink?" Aurora asked. "Vodka this time. Neat." Aurora poured. The bottle caught the green neon from the sign outside, casting strange shadows across the bar.
She slid the glass across
to Eva, who wrapped both hands around it like she was cold. "I thought about calling," Eva said quietly, so low Aurora almost missed it. "After you left. I thought about it all the time." "Why didn't you?" "You asked me not to." Aurora remembered. The note. *Don't
try to
find me.
I need to disappear.* She'd
meant it then.
She'd needed to become someone
new, someone without the
weight
of Cardiff and Brendan and Jennifer and Evan and everything else pressing down on her. "I was angry," Eva continued. "For a long time. You just...left. Like none of it mattered." "It mattered." "Did it?" "Eva—" "Ten years, Rory. Not a word. I had to hear from bloody
Marcus
that you were alive and working deliveries in Soho." "
Marcus
? How does
Marcus
even—" "People talk. Like I said." Aurora leaned against the counter. The
familiar
ache was back, the one she'd spent years trying to outrun. Eva had every right to be angry. Every right to be cold. But she was here anyway, drinking vodka in a bar she'd never normally enter, just to see. "I'm sorry," Aurora said. "Yeah." "I should have called. I should have...something." "Probably." "But I can't undo it." "No." Eva looked up, and this time her smile was different. Real, maybe. Tired. "But you're here now." "I'm here." The jazz finished. In the
silence
that followed, Aurora could hear the muffled sounds of the city outside, the distant wail of a siren, the hum of conversation from the street. Soho never slept, but The Raven's Nest did, eventually, like a slow exhale. "I should get back to my conference," Eva said, but she didn't move. "Early start tomorrow." "Of course." "This was..."
She gestured vaguely with her
glass. "Unexpected." "That's one word for it." Eva stood, pulling her coat tighter.
She hesitated, handbag dangling from
her elbow. "I'm at the Savoy until Friday. Room 412." "That's a lot of numbers to give someone." "It's a lot of numbers to give someone who doesn't want to be found." Eva met her eyes. "But I think maybe you're ready to be found now. Or maybe I am. I don't
know
."
She left without waiting for
an answer. The door swung shut behind her, green neon flaring briefly in the gap. Aurora stood behind the bar, the empty glass catching her reflection like a question. Old Tom stirred in the corner, blinking awake. "Last call?"
he asked hopefully
. "Not yet," Aurora said. "But soon."
She picked up the glass
Eva had left, ran her thumb across the rim where lipstick had stained the edge. A faint colour, somewhere between rose and rust. She thought about room 412. About the Savoy. About all the years between then and now. The front door opened again.
She looked up, expecting another
regular, but it was just the November night, cold and indifferent and waiting.
She put the glass in
the sink. Started wiping down the counter again. Some things, you couldn't wipe clean.
created_at
"2026-02-19T12:17:15.891Z"
2/19/2026, 12:17:15 PM
model
"minimax/minimax-m2.5-20260211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1734
moderation_latency
(null)
generation_time
362658
tokens_prompt
4618
tokens_completion
2877
native_tokens_prompt
4095
native_tokens_completion
2395
native_tokens_completion_images
(null)
native_tokens_reasoning
773
native_tokens_cached
16
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00385868
router
(null)
provider_responses
0
endpoint_id
"599420f9-bca1-43e6-a1e9-dfbb58096b13"
id
"chatcmpl-7fb9fa729dbd18a46c4a6769ad0c8788"
is_byok
false
latency
142
model_permaslug
"minimax/minimax-m2.5-20260211"
provider_name
"Inceptron"
status
200
api_type
"completions"
id
"gen-1771503435-csPnmGXhykyl4ExcxiP9"
upstream_id
"chatcmpl-7fb9fa729dbd18a46c4a6769ad0c8788"
total_cost
0.00385868
cache_discount
0.00000432
upstream_inference_cost
0
provider_name
"Inceptron"
Evaluation details
Result
Evaluator
Details
Meta Data
88.89%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
26
adverbTagCount
5
adverbTags
0
"Aurora gestured vaguely [vaguely]"
1
"Eva said finally [finally]"
2
"Eva said quietly [quietly]"
3
"She gestured vaguely [vaguely]"
4
"he asked hopefully [hopefully]"
dialogueSentences
90
tagDensity
0.289
leniency
0.578
rawRatio
0.192
effectiveRatio
0.111
96.30%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1350
totalAiIsmAdverbs
1
found
0
adverb
"slowly"
count
1
highlights
0
"slowly"
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)
66.67%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1350
totalAiIsms
9
found
0
word
"lilt"
count
1
1
word
"flickered"
count
1
2
word
"unreadable"
count
1
3
word
"silence"
count
2
4
word
"familiar"
count
2
5
word
"fractured"
count
1
6
word
"weight"
count
1
highlights
0
"lilt"
1
"flickered"
2
"unreadable"
3
"silence"
4
"familiar"
5
"fractured"
6
"weight"
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
103
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
2
narrationSentences
103
filterMatches
0
"know"
hedgeMatches
0
"tried to"
1
"try to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
167
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
30
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
2
markdownWords
16
totalWords
1348
ratio
0.012
matches
0
"I'm sorry, I can't do this anymore."
1
"Don't try to find me. I need to disappear."
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
18
unquotedAttributions
0
matches
(empty)
15.92%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
67
wordCount
895
uniqueNames
16
maxNameDensity
2.68
worstName
"Eva"
maxWindowNameDensity
4.5
worstWindowName
"Eva"
discoveredNames
Aurora
21
Cardiff
3
Raven
2
Nest
2
November
2
Soho
2
Eva
24
Gin
1
Tom
3
March
1
Took
1
Brendan
1
Jennifer
1
Evan
1
Real
1
Savoy
1
persons
0
"Aurora"
1
"Raven"
2
"Nest"
3
"Eva"
4
"Tom"
5
"Brendan"
6
"Jennifer"
7
"Evan"
places
0
"Cardiff"
1
"Soho"
2
"March"
globalScore
0.159
windowScore
0.167
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
60
glossingSentenceCount
1
matches
0
"felt like another world entirely"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1348
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
167
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
90
mean
14.98
std
16.36
cv
1.092
sampleLengths
0
20
1
7
2
35
3
3
4
2
5
74
6
2
7
71
8
1
9
10
10
5
11
39
12
7
13
8
14
9
15
13
16
44
17
4
18
3
19
5
20
5
21
3
22
62
23
9
24
8
25
1
26
4
27
17
28
2
29
27
30
3
31
35
32
3
33
1
34
7
35
19
36
2
37
7
38
22
39
5
40
5
41
29
42
33
43
2
44
4
45
26
46
2
47
1
48
2
49
21
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
103
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
1
totalVerbs
154
matches
0
"was getting"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
167
ratio
0
matches
(empty)
90.03%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
895
adjectiveStacks
0
stackExamples
(empty)
adverbCount
46
adverbRatio
0.05139664804469274
lyAdverbCount
15
lyAdverbRatio
0.01675977653631285
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
167
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
167
mean
8.07
std
6.59
cv
0.817
sampleLengths
0
20
1
7
2
6
3
2
4
10
5
17
6
3
7
2
8
6
9
28
10
2
11
11
12
27
13
2
14
3
15
5
16
17
17
17
18
10
19
6
20
13
21
1
22
5
23
5
24
5
25
12
26
6
27
1
28
20
29
7
30
8
31
7
32
2
33
10
34
3
35
4
36
10
37
30
38
4
39
3
40
5
41
5
42
3
43
4
44
7
45
27
46
24
47
4
48
2
49
3
68.66%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
7
diversityRatio
0.437125748502994
totalSentences
167
uniqueOpeners
73
40.16%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
83
matches
0
"Of course she looked different."
ratio
0.012
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
18
totalSentences
83
matches
0
"She knew it the way"
1
"She'd filled out somehow, become"
2
"It wasn't a question."
3
"She'd left Cardiff in March"
4
"She'd meant the relationship."
5
"She pushed it down."
6
"They nodded at Aurora, made"
7
"She slid the glass across"
8
"I need to disappear.* She'd"
9
"She'd needed to become someone"
10
"She gestured vaguely with her"
11
"She hesitated, handbag dangling from"
12
"She left without waiting for"
13
"he asked hopefully"
14
"She picked up the glass"
15
"She thought about room 412."
16
"She looked up, expecting another"
17
"She put the glass in"
ratio
0.217
56.39%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
67
totalSentences
83
matches
0
"The woman at the bar"
1
"Aurora's hand stilled on the"
2
"That particular lilt, somewhere between"
3
"She knew it the way"
4
"Aurora set down the cloth"
5
"The Raven's Nest had emptied"
6
"The kind of cold that"
7
"Eva looked different."
8
"The Eva she remembered had"
9
"This woman had curves now,"
10
"She'd filled out somehow, become"
11
"Eva tilted her head"
12
"Eva took a sip of"
13
"Gin, by the look of"
14
"Aurora gestured vaguely toward the"
15
"Eva's expression flickered, something unreadable"
16
"It wasn't a question."
17
"Aurora wasn't sure how to"
18
"The silence stretched between them,"
19
"Aurora did the math."
ratio
0.807
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
83
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
30
technicalSentenceCount
1
matches
0
"Dark and knowing, with that perpetual amusement that used to drive Aurora mad."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
26
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
11
fancyCount
1
fancyTags
0
"Eva continued (continue)"
dialogueSentences
90
tagDensity
0.122
leniency
0.244
rawRatio
0.091
effectiveRatio
0.022
86.7670%