NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEA2R6V2H335QP1AYDCJBPW
Run Details
Model:
Claude Sonnet 5 (Reasoning)
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
52.1s
Cost:
$0.048818
Provider:
Amazon Bedrock
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)
68.86%
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)
0.00%
Name drop frequency
(details)
84.21%
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)
98.10%
Passive voice overuse
(details)
88.89%
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)
75.48%
Sentence opener variety
(details)
0.00%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
0.00%
Subject-first sentence starts
(details)
100.00%
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)
87.1847%
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 glass slipped from Rory's
fingers and cracked against the copper sink. "Aurora Carter. Bloody hell, is that you?" Rory turned.
The voice belonged to a
face she hadn't catalogued in years, filed away somewhere between Pre-Law seminars and the last night she'd spent in Cardiff before the bruises made the decision for her.
Megan Pryce stood at the
end of the bar in a rain-damp coat, mouth open, eyes doing the maths. "Megan." "Christ, it is you. I nearly didn't." Megan's gaze swept over her, the black hair cut shorter than Rory used to wear it, the leather jacket, the way she stood like she owned the four feet of space around her. "You look... different." "It's been a while." "Six years, love. Six years and not a word." Megan slid onto a stool, elbows on the bar, the old easy grin trying to find its footing on her face and slipping. "One day you're in my kitchen crying over criminal law revision, next day you're gone. Your mum wouldn't even tell me where."
Rory picked up a fresh
glass, gave it a wipe it didn't need. "London happened fast." "Clearly."
Megan's eyes caught the pale
crescent scar peeking from Rory's cuff. Old wound, older story. "Still got that from the bike, then." "Still got it." "And Evan? Is he-" "Gone. Long gone." The words came out flat, final, a door shutting rather than opening.
Megan blinked, recalibrated, tried a
different angle. "I always liked him, you know. Before."
She caught herself
. "Sorry. Shouldn't have said that." "You didn't know." "None of us knew, did we."
Megan wrapped both hands round
the coaster in front of her, turning it in slow circles. "One minute you're the girl taking notes in the front row, next you've vanished into thin air and everyone's making up their own version of what happened. I always hoped you'd landed somewhere soft." Rory set the glass down. "I landed." "Doing what, exactly? Tending bar?"
Megan looked round at the
maps on the wall, the black-and-white photographs of men who'd probably never existed under the names printed beneath them. "Not exactly Pre-Law, is it." "Life rarely follows the syllabus." A short laugh escaped Megan, more surprise than humour. "God, you even talk different now. Where's the girl who used to apologise to inanimate objects when she bumped into them?" "She grew up." "Grew up, or grew a wall?"
The question landed harder than
Megan probably meant it to.
Rory busied herself lining bottles
that didn't need lining, buying half a second she didn't have. "Bit of both, I expect."
Megan studied her, the kind
of look old friends reserve for spotting the differences nobody else would notice.
A faint line at the
corner of the mouth. The stillness in the hands.
The way Rory's eyes tracked
the door every time it opened, cataloguing and dismissing each newcomer in under a second. "You used to tell me everything," Megan said. "Every rubbish date, every essay crisis, every little thing that went wrong. Now I can't get five words about the last six years." "Some things aren't worth the retelling." "Or too heavy to lift." Megan reached across, touched Rory's wrist, right over the scar. Rory didn't flinch, which somehow felt worse than if she had. "I looked for you, you know. After. Called your mum a dozen times. She kept saying you were fine, you were settled, you didn't want visitors. I thought maybe I'd done something." "You didn't do anything." "Then why leave like that? Not even a text." Rory's jaw tightened, just enough to catch the light. "Because if I'd stopped to say goodbye properly, I'm not sure I'd have made it out the door." Something in Megan's face cracked open, the old
affection
breaking through the polite distance of six lost years. "Rory-" "It's fine. It was a long time ago." "Doesn't look fine from where I'm sitting." Megan gestured vaguely at the bar, the bookshelves, the whole strange architecture of Rory's new life. "This place, this... whoever you've become. You disappear from Wales and turn up behind a bar in Soho with a scar you won't talk about and a stare that could strip paint. What happened to you, love?" Rory glanced toward the far end of the room, where Silas stood half in shadow, pretending to check a delivery invoice while his eyes
flicked
up every few seconds.
He hadn't said a word
since Megan arrived. He didn't need to.
His silence carried its own
weight
, a
reminder
that certain doors in this building only opened one way, and certain stories weren't hers to hand out over the bar top to old university friends with kind eyes and too many questions. "Different life," Rory said finally. "That's all it is." "That's not an answer." "It's the one I've got." Megan sat back, arms crossing, the
warmth
in her expression cooling by a few careful degrees.
She'd known Rory long enough
to recognise a locked door when she ran into one, even dressed up in old fondness and a
familiar
face. "Fine. Keep your secrets."
She managed something close to
a smile. "But for what it's worth, whoever did this to you, whatever this is, I hope it was worth losing the girl I used to know." "She's still in here somewhere." "Doesn't look it from the outside." Rory poured two whiskies without
being asked
, set one in front of Megan, kept the other for herself. A peace offering dressed as habit. "To old times," she said. Megan lifted the glass, studied the amber liquid like it might explain the six missing years better than Rory had. "To old times." A pause, then, quieter: "Try not to disappear again without telling me, yeah? Some of us worry."
Before Rory could answer, the
side door creaked, the one that led to the back room behind the bookshelf, the one that only ever opened for people who mattered to Silas's other business.
His voice cut low across
the room, all pleasant surface and buried steel. "Rory. A word, if you don't mind." Megan's eyebrows lifted at the tone, the way even a simple request
seemed to
carry the shape of an order. "Duty calls?" "Something like that." Rory set down her glass, the whisky barely touched, and felt Megan's eyes follow her the whole way across the room, cataloguing the same details Rory had spent years learning to hide.
She reached the bookshelf, fingers
brushing the spine of an old atlas that hadn't moved in a decade, and glanced back once. Megan hadn't picked up her drink.
She was still watching, still
waiting for the friend she remembered to reappear from wherever she'd gone. She
wasn't coming
back tonight.
created_at
"2026-07-01T07:42:46.007Z"
7/1/2026, 7:42:46 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4289
moderation_latency
(null)
generation_time
51996
tokens_prompt
4618
tokens_completion
2069
native_tokens_prompt
6494
native_tokens_completion
3583
native_tokens_completion_images
(null)
native_tokens_reasoning
361
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
0.048818
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01Ds7r49N7WrtXRoEYbsgDsj"
is_byok
false
latency
1925
model_permaslug
"anthropic/claude-sonnet-5-20260630"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.17.0; linux; x64))"
http_referer
(null)
request_id
"req-1782891766-fvnqOoIkSFUxs2r5IwbJ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891766-7mZRbuhcyOzsO2IHWSWR"
upstream_id
"msg_01Ds7r49N7WrtXRoEYbsgDsj"
total_cost
0.048818
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
12
adverbTagCount
2
adverbTags
0
"Megan gestured vaguely [vaguely]"
1
"Rory said finally [finally]"
dialogueSentences
51
tagDensity
0.235
leniency
0.471
rawRatio
0.167
effectiveRatio
0.078
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1124
totalAiIsmAdverbs
0
found
(empty)
highlights
(empty)
100.00%
AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0
"Blackwood"
found
(empty)
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
68.86%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1124
totalAiIsms
7
found
0
word
"affection"
count
1
1
word
"flicked"
count
1
2
word
"silence"
count
1
3
word
"weight"
count
1
4
word
"reminder"
count
1
5
word
"warmth"
count
1
6
word
"familiar"
count
1
highlights
0
"affection"
1
"flicked"
2
"silence"
3
"weight"
4
"reminder"
5
"warmth"
6
"familiar"
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
49
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
1
narrationSentences
49
filterMatches
(empty)
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
87
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
41
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1124
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
11
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
47
wordCount
701
uniqueNames
7
maxNameDensity
3
worstName
"Megan"
maxWindowNameDensity
5
worstWindowName
"Megan"
discoveredNames
Rory
20
Pre-Law
1
Cardiff
1
Pryce
1
Megan
21
Old
1
Silas
2
persons
0
"Rory"
1
"Pryce"
2
"Megan"
3
"Silas"
places
0
"Cardiff"
1
"Old"
globalScore
0.002
windowScore
0
84.21%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
38
glossingSentenceCount
1
matches
0
"something close to a smile"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1124
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
87
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
59
mean
19.05
std
19.45
cv
1.021
sampleLengths
0
12
1
7
2
54
3
1
4
43
5
4
6
54
7
13
8
3
9
23
10
3
11
4
12
3
13
19
14
15
15
3
16
56
17
5
18
2
19
34
20
5
21
9
22
21
23
3
24
6
25
26
26
5
27
52
28
31
29
6
30
58
31
4
32
9
33
9
34
18
35
18
36
1
37
8
38
60
39
82
40
9
41
4
42
5
43
41
44
36
45
5
46
6
47
24
48
5
49
20
98.10%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
49
matches
0
"being asked"
88.89%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
2
totalVerbs
120
matches
0
"was still watching"
1
"wasn't coming"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
87
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
705
adjectiveStacks
0
stackExamples
(empty)
adverbCount
24
adverbRatio
0.03404255319148936
lyAdverbCount
7
lyAdverbRatio
0.009929078014184398
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
87
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
87
mean
12.92
std
10.32
cv
0.799
sampleLengths
0
12
1
7
2
2
3
33
4
19
5
1
6
40
7
3
8
4
9
32
10
22
11
13
12
3
13
12
14
4
15
7
16
3
17
4
18
3
19
12
20
7
21
10
22
5
23
3
24
22
25
34
26
5
27
2
28
29
29
5
30
5
31
9
32
21
33
3
34
6
35
10
36
16
37
5
38
18
39
9
40
5
41
20
42
8
43
23
44
6
45
15
46
11
47
32
48
4
49
9
75.48%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
6
diversityRatio
0.4942528735632184
totalSentences
87
uniqueOpeners
43
0.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
0
totalSentences
46
matches
(empty)
ratio
0
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
10
totalSentences
46
matches
0
"She caught herself"
1
"He hadn't said a word"
2
"He didn't need to."
3
"His silence carried its own"
4
"She'd known Rory long enough"
5
"She managed something close to"
6
"His voice cut low across"
7
"She reached the bookshelf, fingers"
8
"She was still watching, still"
9
"She wasn't coming back tonight."
ratio
0.217
0.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
44
totalSentences
46
matches
0
"The glass slipped from Rory's"
1
"The voice belonged to a"
2
"Megan Pryce stood at the"
3
"Megan's gaze swept over her,"
4
"Megan slid onto a stool,"
5
"Rory picked up a fresh"
6
"Megan's eyes caught the pale"
7
"The words came out flat,"
8
"Megan blinked, recalibrated, tried a"
9
"She caught herself"
10
"Megan wrapped both hands round"
11
"Rory set the glass down."
12
"Megan looked round at the"
13
"A short laugh escaped Megan,"
14
"The question landed harder than"
15
"Rory busied herself lining bottles"
16
"Megan studied her, the kind"
17
"A faint line at the"
18
"The stillness in the hands."
19
"The way Rory's eyes tracked"
ratio
0.957
100.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
46
matches
0
"Before Rory could answer, the"
ratio
0.022
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
23
technicalSentenceCount
0
matches
(empty)
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
12
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
3
fancyCount
0
fancyTags
(empty)
dialogueSentences
51
tagDensity
0.059
leniency
0.118
rawRatio
0
effectiveRatio
0
87.1847%