NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2E6RPJ945WBYD0PMC99FAP
Run Details
Model:
DeepSeek V4 Flash
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
21.1s
Cost:
$0.000970
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
100.00%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
70.21%
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)
73.08%
Name drop frequency
(details)
70.63%
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)
100.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
72.82%
Sentence opener variety
(details)
81.97%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
87.05%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
71.43%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
90.9061%
Overall
Model input
System
You are an expert and award-winning novel writer in the dark Thriller 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="4416" name="Detective Harlow Quinn" aliases="Quinn, Detective Quinn, Harlow" pronouns="she/her" species="Human" storyRole="Antagonist"> <eyeColor>brown</eyeColor> <hair>closely cropped salt-and-pepper</hair> <height>5'9"</height> <age>41</age> <jawline>sharp jaw</jawline> <watch>worn leather watch on her left wrist</watch> <bearing>military precision</bearing> <description>A Metropolitan Police detective with 18 years of decorated service who suspects the clique is involved in criminal activity.</description> <backstory>She lost her partner, DS Morris, during a case three years ago under unexplained circumstances that had supernatural origins she doesn't yet understand.</backstory> </character> <character id="4417" name="Tomás Herrera" aliases="Tommy, Tomás, Herrera" pronouns="he/him" species="Human" storyRole="Support"> <eyeColor>warm brown</eyeColor> <hair>short curly dark brown</hair> <height>5'10"</height> <age>29</age> <skinTone>olive skin</skinTone> <scar>scar running along his left forearm from a knife attack</scar> <medallion>Saint Christopher medallion around his neck</medallion> <birthplace>Seville, Spain</birthplace> <description>A former paramedic who provides off-the-books medical care for the clique.</description> <backstory>Born in Seville, Spain. He moved to London to work for the NHS but lost his license after administering unauthorized treatments to supernatural patients.</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> <location id="856" name="The Veil Market" aliases="Veil Market, the Market, underground market" realm="Earth"> <currentLocation>abandoned Tube station beneath Camden</currentLocation> <entryRequirement>bone token</entryRequirement> <schedule>moves locations every full moon</schedule> <description>A hidden supernatural black market that sells enchanted goods, banned alchemical substances, and information.</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 thriller genre. A detective is pursuing a suspect through rain-soaked city streets at night. The chase takes them from the street level down into an underground market. The detective must decide whether to follow the suspect into unfamiliar and potentially dangerous territory. 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
Footsteps splashed ahead. Quinn counted them. Three sets. Two heavy, one light.
The light one was her
mark.
She hit the alley at
full sprint, leather soles sliding on wet cobblestones.
The rain had stopped ten
minutes ago but London refused to dry. Refused to make this easy. "Metropolitan Police. Stop." The figure ahead didn't stop. They never did.
Quinn vaulted a bin bag
that someone had left split open. Rotten vegetables and something that
smelled like death
.
The suspect cleared it with
an athletic leap that spoke of training. Military, maybe.
Definitely not your average street
runner. She pressed her earpiece. "Suspect heading east on Berwick Street. Moving towards Oxford Street. Requesting backup." Static. *Perfect.* The tunnels always did this. Dead zones where signal went to die. The suspect glanced back.
Quinn caught a flash of
pale skin beneath a hood. Young. Male. Something
familiar
about the jawline, the way he moved. She'd seen him before.
The thought sat wrong in
her gut.
They burst onto Oxford Street
together. Tourists scattered. A group of teenagers cheered. Someone filmed on their phone. *Another night in London's greatest hits compilation.*
The suspect cut right, towards
the Tottenham Court Road station entrance. Quinn's legs burned. Forty-one was too old for this. Eighteen years on the force and she still chased ghosts through rain-slicked streets while her knees screamed their retirement
notice
. But the station wasn't right. Something prickled at the back of her neck. The way he'd chosen it. Deliberate. Like he wanted her to follow. Too late now. Down the steps. Past the ticket barriers. The suspect produced a token from somewhere. Not an Oyster card. Not a contactless. Something small and bone-white that caught the fluorescent light. Quinn drew her baton. "Police. Stop or I'll—" The token clicked into a reader she'd never seen before. Hidden beside the
standard
ticket machine. The wall behind it
shimmered
. Shifted. Became something else entirely. A tunnel. Dark. Damp. The air that breathed out smelled of copper and old earth and something sweet that made her teeth ache. The suspect vanished into it. Quinn stood at the threshold. Her radio crackled uselessly. Backup was four minutes out minimum. Her phone showed no signal. The tunnel stretched into
darkness that seemed to drink light
. *This is how they get you,* a voice whispered. Her late partner's voice. *This is exactly how they get you.* Three years ago, DS Morris had chased a suspect into an alley. Just an alley. Brick walls on both sides. A dead end. Except he'd never come out.
They found his wallet by
a bin. His badge three blocks away. His body nowhere. Case went cold. Stayed cold. But Quinn had seen things since then. Things that made her question physics. Things that made her question sanity. Things that told her the world had layers she couldn't see until they wanted to be seen. The tunnel's darkness
pulsed
. Like it
was breathing
. Her mark was getting away. The one she'd been hunting for six months. The one connected to three disappearances, two deaths, and a pattern of violence that made no sense through normal lenses. She stepped forward. The air changed temperature. Dropped ten degrees in an instant. The sweet smell intensified. Quinn's hand found her torch, clicked it on. The beam cut through the dark but couldn't find the walls. The tunnel was wider than it should be. Deeper. *Impossible.* The floor sloped down. She followed it. Sounds emerged. Distant at first, then closer. Voices. Music. Something that could have been machinery or could have been screaming. Hard to tell in the acoustics. Another token reader appeared ahead. This one
was built
into an archway of carved stone. Bones set in mortar. Human bones. Quinn's training screamed at her to stop, to document, to call it in.
Her hand reached for the
reader anyway. "You don't want to do that." The voice came from behind her. Spanish accent. Young. Quinn spun, baton raised. A man stood in the tunnel's entrance. Late twenties. Dark curls plastered to his forehead from the rain. Olive skin. A Saint Christopher medallion caught the torchlight. "You're bleeding," she said.
He looked down at his
forearm. A fresh cut ran along an older scar. "Occupational hazard." "Who are you?" "Someone who knows what's through that door."
He stepped closer
. "Someone who knows you followed Tomás Herrera tonight." The name hit like ice water. Her mark. The one she'd been chasing. "You know him?" "We're colleagues." The man's smile was tired. "Sort of. He'll die if you go through there. So will you." "Threatening a police officer—" "I'm saving your life."
He pulled a cloth from
his pocket, wrapped it around his bleeding arm. "The Veil Market doesn't welcome your kind. Not without an invitation. Not without protection." "Protection from what?" He held up his medallion. "From the truth, Detective Quinn." Her name. He knew her name. Quinn's finger tightened on the baton. "Morris sent me," he said. "Before he died. He knew you'd come looking eventually." The world tilted. "Morris has been dead for three years." "Has he?" The man's eyes held something ancient. Something that didn't belong in a twenty-nine-year-old face. "Are you sure?" Quinn looked at the bone archway. At the darkness beyond. At the tunnel that shouldn't exist. Her suspect
was gone
. But the questions remained. The questions that had haunted her since Morris vanished. Since the cases started piling up. Since she'd begun to
suspect that the
world she knew was a lie painted over something much older and much hungrier. "Come with me," the man said. "I'll explain what I can. But not here. Not when they're watching." "Who?" "The Nest. Silas' bar. It's safe." "Nothing about this is safe." "No." He turned and walked back towards the station platform. "But you already knew that when you chased a ghost into a hole that doesn't exist." Quinn stood alone. The tunnel breathed behind her. The city hummed above her. She followed the bleeding man into the fluorescent light.
created_at
"2026-04-25T13:45:29.559Z"
4/25/2026, 1:45:29 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
676
moderation_latency
(null)
generation_time
20617
tokens_prompt
4663
tokens_completion
1614
native_tokens_prompt
4220
native_tokens_completion
1353
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
"stop"
usage
0.00096964
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"9e04bc97-50b2-4e8f-8f5a-c35b772e5582"
is_byok
false
latency
373
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepSeek"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777124729-uDUY0l52uf86vXBQQsk2"
session_id
(null)
api_type
"completions"
id
"gen-1777124729-62nmwFCFC4UfyPtUMAOO"
upstream_id
"9e04bc97-50b2-4e8f-8f5a-c35b772e5582"
total_cost
0.00096964
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
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
8
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
29
tagDensity
0.276
leniency
0.552
rawRatio
0
effectiveRatio
0
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1007
totalAiIsmAdverbs
0
found
(empty)
highlights
(empty)
100.00%
AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
70.21%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1007
totalAiIsms
6
found
0
word
"footsteps"
count
1
1
word
"perfect"
count
1
2
word
"familiar"
count
1
3
word
"standard"
count
1
4
word
"shimmered"
count
1
5
word
"pulsed"
count
1
highlights
0
"footsteps"
1
"perfect"
2
"familiar"
3
"standard"
4
"shimmered"
5
"pulsed"
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
148
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
1
narrationSentences
148
filterMatches
0
"notice"
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
168
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
21
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
5
markdownWords
22
totalWords
1007
ratio
0.022
matches
0
"Perfect."
1
"Another night in London's greatest hits compilation."
2
"This is how they get you,"
3
"This is exactly how they get you."
4
"Impossible."
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
7
unquotedAttributions
0
matches
(empty)
73.08%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
31
wordCount
845
uniqueNames
14
maxNameDensity
1.54
worstName
"Quinn"
maxWindowNameDensity
2
worstWindowName
"Quinn"
discoveredNames
London
2
Oxford
1
Street
1
Tottenham
1
Court
1
Road
1
Oyster
1
Three
2
Morris
2
Quinn
13
Spanish
1
Saint
1
Christopher
1
Things
3
persons
0
"Morris"
1
"Quinn"
2
"Saint"
3
"Christopher"
places
0
"London"
1
"Oxford"
2
"Street"
3
"Tottenham"
4
"Court"
5
"Road"
6
"Three"
globalScore
0.731
windowScore
1
70.63%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
63
glossingSentenceCount
2
matches
0
"smelled like death"
1
"darkness that seemed to drink light"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1007
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
168
matches
0
"suspect that the"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
58
mean
17.36
std
12.47
cv
0.718
sampleLengths
0
18
1
30
2
3
3
8
4
39
5
16
6
1
7
13
8
36
9
25
10
40
11
25
12
3
13
30
14
8
15
26
16
23
17
5
18
30
19
20
20
43
21
5
22
36
23
8
24
33
25
3
26
42
27
1
28
7
29
26
30
34
31
7
32
15
33
4
34
27
35
4
36
16
37
3
38
18
39
16
40
19
41
4
42
31
43
3
44
10
45
12
46
14
47
10
48
19
49
16
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
2
totalSentences
148
matches
0
"was built"
1
"was gone"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
1
totalVerbs
150
matches
0
"was breathing"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
168
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
851
adjectiveStacks
0
stackExamples
(empty)
adverbCount
21
adverbRatio
0.024676850763807285
lyAdverbCount
4
lyAdverbRatio
0.004700352526439483
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
168
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
168
mean
5.99
std
3.99
cv
0.666
sampleLengths
0
3
1
3
2
2
3
4
4
6
5
13
6
12
7
5
8
3
9
5
10
3
11
11
12
8
13
12
14
2
15
6
16
4
17
12
18
1
19
6
20
7
21
4
22
10
23
1
24
1
25
9
26
4
27
7
28
6
29
2
30
5
31
5
32
7
33
11
34
3
35
6
36
20
37
5
38
8
39
5
40
1
41
6
42
3
43
3
44
4
45
7
46
4
47
3
48
9
49
4
72.82%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
11
diversityRatio
0.47619047619047616
totalSentences
168
uniqueOpeners
80
81.97%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
3
totalSentences
122
matches
0
"Definitely not your average street"
1
"Too late now."
2
"Just an alley."
ratio
0.025
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
23
totalSentences
122
matches
0
"She hit the alley at"
1
"They never did."
2
"She pressed her earpiece."
3
"She'd seen him before."
4
"They burst onto Oxford Street"
5
"Her radio crackled uselessly."
6
"Her phone showed no signal."
7
"Her late partner's voice."
8
"They found his wallet by"
9
"His badge three blocks away."
10
"His body nowhere."
11
"Her mark was getting away."
12
"She stepped forward."
13
"She followed it."
14
"Her hand reached for the"
15
"He looked down at his"
16
"He stepped closer"
17
"He pulled a cloth from"
18
"He held up his medallion."
19
"He knew her name."
ratio
0.189
87.05%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
91
totalSentences
122
matches
0
"Footsteps splashed ahead."
1
"Quinn counted them."
2
"The light one was her"
3
"She hit the alley at"
4
"The rain had stopped ten"
5
"The figure ahead didn't stop."
6
"They never did."
7
"Quinn vaulted a bin bag"
8
"The suspect cleared it with"
9
"She pressed her earpiece."
10
"The suspect glanced back."
11
"Quinn caught a flash of"
12
"Something familiar about the jawline,"
13
"She'd seen him before."
14
"The thought sat wrong in"
15
"They burst onto Oxford Street"
16
"A group of teenagers cheered."
17
"Someone filmed on their phone."
18
"*Another night in London's greatest"
19
"The suspect cut right, towards"
ratio
0.746
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
122
matches
(empty)
ratio
0
71.43%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
20
technicalSentenceCount
2
matches
0
"Something that could have been machinery or could have been screaming."
1
"Something that didn't belong in a twenty-nine-year-old face."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
8
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
3
fancyCount
0
fancyTags
(empty)
dialogueSentences
29
tagDensity
0.103
leniency
0.207
rawRatio
0
effectiveRatio
0
90.9061%