NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXGHS62NMZ4VHE6PZQ824C
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
40.9s
Cost:
$0.088095
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
95.58%
AI-ism adverb frequency
(details)
80.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
64.63%
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)
0.63%
Name drop frequency
(details)
18.42%
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)
99.11%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
94.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
68.89%
Sentence opener variety
(details)
66.67%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
30.00%
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)
87.2642%
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
hand and
shattered
against the floorboards. "Eva?"
The woman at the end
of the bar turned. For a second her face stayed blank, the polite mask of a stranger about to apologise.
Then something cracked open behind
her eyes. "Oh my God. Rory?"
They stared at each other
across the length of The Raven's Nest, the broken glass forgotten, the low hum of the after-work crowd
suddenly
far away. Rory's first thought, absurd, irrelevant,
was that Eva
had cut her hair.
The wild copper curls she'd
worn at twenty
were gone
, replaced by something sleek and expensive that ended at a sharp line beneath her jaw. "I didn't know you were in London," Eva said. "I've been in London for two years."
Rory crouched, gathering the bigger
shards into her palm. "Because of you, actually." "Because of me?" "You told me to come. Leave Cardiff. Leave Evan."
She stood, dumped the glass
into the bin behind the bar, and wiped her hands on her apron. "You don't remember telling me that?" Eva's smile faltered. "I remember a lot of things from back then. They're a bit blurry."
The bar light caught the
rings on her fingers. Three of them, slim gold bands stacked together, and a watch that probably cost more than Rory made in a month delivering noodles.
The leather jacket draped over
the stool beside her had a designer's name stitched inside the collar.
Eva had always dressed like
a charity shop explosion, mismatched, loud, gorgeous.
Now she looked like she
belonged in the glossy windows of Bond Street. "Sit with me," Eva said. "God, sit with me. Are you working? Can you take a break?" "I'm not working here. I live upstairs."
Rory glanced toward the bar's
back corner, where Silas stood drying glasses with the slow patience of a man who heard everything and acknowledged nothing.
He met her eye, tilted
his head a fraction. *Go on.*
She came around the bar
and took the stool. Up close, the changes were sharper.
A faint puffiness under Eva's
eyes that makeup hadn't
quite buried
.
A stillness in her hands
that hadn't been there before.
The Eva she'd known had
never once sat still. "You look incredible," Rory said, and meant it, and didn't. "I look tired. You're being kind."
Eva lifted her glass
. Something amber, neat. "What are you drinking?" "Tea, mostly. I'm on at six tomorrow." "On where?" "Delivery driver. Chinese place off Gerrard Street." Rory waited for the
flicker
, the careful neutrality people wore when they were busy recalculating you. It didn't come. Eva just nodded, slow. "You were going to be a barrister." "I was going to be a lot of things." "Your dad must love that." "My dad and I don't speak much these days." Rory turned the empty stool-space between them into something to look at. "What about you? Last I heard you were temping at a recruitment firm and sleeping on
Marcus
's sofa." Eva laughed, but it came out brittle, a thing that wanted to be a laugh. "
Marcus
. Christ, there's a name I haven't said in a while." She drank. "I married James. You wouldn't know him. We met after you'd gone quiet. He's in property. Was." "Was?" "Is. Property. He's still alive, if that's what you're asking."
She set the glass down
with exaggerated care. "We separated in March." The crowd behind them swelled, somebody's birthday, a cheer going up. Rory let it pass over them. "I'm sorry." "Don't be. It was a relief. Like putting down something heavy." Eva
traced
the rim of her glass. "Funny. You spend years building a life and then one morning you can't remember why you wanted any of it." "You always knew exactly what you wanted. That was the whole problem with you." Rory smiled to soften it. "You wanted everything, all at once, immediately." "I did, didn't I?" Eva's eyes shone, and for one disorienting moment the copper-haired girl
flickered
back through the polished woman, the one who'd danced barefoot on the kerb outside a club in Cardiff at three in the morning, who'd held Rory's face in both hands the night she finally left Evan and said *you're worth more than him, you're worth more than this whole grey city.* "And you wanted out. Out of everything. Out of yourself, half the time." "I got out." "Did you?" Eva looked at the apron folded on Rory's lap, at the flat-roofed ceiling above them, at the maps and dead photographs on the walls. "You crossed a country to start again and you ended up pulling pints above a bar in Soho." "I don't pull pints." "You know what I mean." "I do." Rory held her gaze. "And you flew up so high you forgot why you ever wanted wings. So which of us got out, Eva?" Silence, then. Not the
comfortable
kind. Eva's jaw tightened, and Rory watched something move behind her face, a calculation, a defence, then a surrender. "I should have called you," Eva said quietly. "When it all went wrong. You were the only person who ever told me the truth." "You stopped answering. Five years ago. I rang every birthday for two years and then I stopped too." "I know." "I thought you'd died. Or worse, that you'd just decided I wasn't worth the airtime." "It wasn't that." Eva pressed her thumb hard against one of the gold rings, twisting it. "James didn't like the people from before. Said I was reinventing myself, that I should leave the dead
weight
behind. And I let him decide what was dead
weight
."
She looked up
. "I let him decide you were." The words landed somewhere in Rory's chest, an old wound pressed without warning.
She thought of the long
nights that first winter in London, alone in the flat above with the green neon bleeding through the curtains, scrolling to Eva's name and never pressing call. "You were the reason I came here," Rory said. "You know that? You made me brave enough to run. And then you weren't here. You sent me into the dark and turned the light off behind me." Eva's eyes filled. She didn't wipe them. "I'm here now," she said. "Five years too late." "I know." A tear broke loose and tracked through the careful makeup. "But I'm here, Rory. And I don't have a single person left who knew me before I became this. Not one."
She reached across the gap
between the stools, and her manicured hand closed over Rory's, over the small crescent scar on her wrist. "Tell me it's not too late. Tell me there's still something to come back to." And the bar door swung open behind them, and a man's voice called Eva's name.
created_at
"2026-05-31T11:43:06.566Z"
5/31/2026, 11:43:06 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1098
moderation_latency
(null)
generation_time
40878
tokens_prompt
4618
tokens_completion
1666
native_tokens_prompt
6494
native_tokens_completion
2225
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"end_turn"
service_tier
"default"
usage
0.088095
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01Jp9tqT2ncg8m7uS7vx8pru"
is_byok
false
latency
1098
model_permaslug
"anthropic/claude-4.8-opus-20260528"
provider_name
"Anthropic"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer
(null)
request_id
"req-1780227786-pKNmA4orUkDYFGprSfl9"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780227786-kodOJ3HoiCFuQ1Zg2tQK"
upstream_id
"msg_01Jp9tqT2ncg8m7uS7vx8pru"
total_cost
0.088095
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
23
adverbTagCount
1
adverbTags
0
"Eva said quietly [quietly]"
dialogueSentences
56
tagDensity
0.411
leniency
0.821
rawRatio
0.043
effectiveRatio
0.036
95.58%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1131
totalAiIsmAdverbs
1
found
0
adverb
"suddenly"
count
1
highlights
0
"suddenly"
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)
64.63%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1131
totalAiIsms
8
found
0
word
"shattered"
count
1
1
word
"flicker"
count
1
2
word
"traced"
count
1
3
word
"flickered"
count
1
4
word
"silence"
count
1
5
word
"comfortable"
count
1
6
word
"weight"
count
2
highlights
0
"shattered"
1
"flicker"
2
"traced"
3
"flickered"
4
"silence"
5
"comfortable"
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
57
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
57
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
90
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
81
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
2
markdownWords
15
totalWords
1131
ratio
0.013
matches
0
"Go on."
1
"you're worth more than him, you're worth more than this whole grey city."
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
19
unquotedAttributions
0
matches
(empty)
0.63%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
45
wordCount
636
uniqueNames
11
maxNameDensity
2.99
worstName
"Eva"
maxWindowNameDensity
4
worstWindowName
"Rory"
discoveredNames
Rory
17
Raven
1
Nest
1
Eva
19
Bond
1
Street
1
Silas
1
Cardiff
1
Evan
1
Silence
1
London
1
persons
0
"Rory"
1
"Raven"
2
"Eva"
3
"Silas"
4
"Evan"
places
0
"Bond"
1
"Street"
2
"Cardiff"
3
"London"
globalScore
0.006
windowScore
0.333
18.42%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
38
glossingSentenceCount
2
matches
0
"looked like she belonged in the glossy wi"
1
"quite buried"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1131
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
90
matches
0
"was that Eva"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
49
mean
23.08
std
20.64
cv
0.894
sampleLengths
0
11
1
1
2
32
3
4
4
63
5
9
6
20
7
3
8
33
9
16
10
74
11
17
12
43
13
45
14
10
15
17
16
7
17
2
18
30
19
7
20
9
21
5
22
39
23
45
24
1
25
22
26
17
27
2
28
38
29
26
30
80
31
3
32
44
33
4
34
5
35
26
36
24
37
24
38
18
39
2
40
15
41
54
42
45
43
37
44
7
45
5
46
4
47
71
48
15
99.11%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
57
matches
0
"were gone"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
106
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
90
ratio
0
matches
(empty)
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
640
adjectiveStacks
1
stackExamples
0
"cracked open behind her"
adverbCount
20
adverbRatio
0.03125
lyAdverbCount
4
lyAdverbRatio
0.00625
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
90
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
90
mean
12.57
std
11.11
cv
0.884
sampleLengths
0
11
1
1
2
9
3
16
4
7
5
4
6
26
7
12
8
25
9
9
10
16
11
4
12
3
13
27
14
6
15
3
16
13
17
9
18
23
19
17
20
12
21
13
22
5
23
12
24
32
25
9
26
2
27
9
28
6
29
11
30
10
31
9
32
10
33
10
34
3
35
4
36
7
37
2
38
23
39
3
40
4
41
7
42
9
43
5
44
21
45
18
46
15
47
13
48
17
49
1
68.89%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
8
diversityRatio
0.4666666666666667
totalSentences
90
uniqueOpeners
42
66.67%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
50
matches
0
"Then something cracked open behind"
ratio
0.02
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
10
totalSentences
50
matches
0
"They stared at each other"
1
"She stood, dumped the glass"
2
"He met her eye, tilted"
3
"She came around the bar"
4
"It didn't come."
5
"She set the glass down"
6
"She looked up"
7
"She thought of the long"
8
"She didn't wipe them."
9
"She reached across the gap"
ratio
0.2
30.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
43
totalSentences
50
matches
0
"The glass slipped from Rory's"
1
"The woman at the end"
2
"They stared at each other"
3
"Rory's first thought, absurd, irrelevant,"
4
"The wild copper curls she'd"
5
"Rory crouched, gathering the bigger"
6
"She stood, dumped the glass"
7
"Eva's smile faltered."
8
"The bar light caught the"
9
"The leather jacket draped over"
10
"Eva had always dressed like"
11
"Rory glanced toward the bar's"
12
"He met her eye, tilted"
13
"She came around the bar"
14
"A faint puffiness under Eva's"
15
"A stillness in her hands"
16
"The Eva she'd known had"
17
"Rory said, and meant it,"
18
"Eva lifted her glass"
19
"Something amber, neat."
ratio
0.86
100.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
50
matches
0
"Now she looked like she"
ratio
0.02
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
17
technicalSentenceCount
0
matches
(empty)
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
23
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
7
fancyCount
1
fancyTags
0
"Eva pressed (press)"
dialogueSentences
56
tagDensity
0.125
leniency
0.25
rawRatio
0.143
effectiveRatio
0.036
87.2642%