NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0GEY9G8KF2A9FARPVFVNXS
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
37.9s
Cost:
$0.107195
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
95.66%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
91.33%
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)
33.33%
Name drop frequency
(details)
89.02%
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)
89.81%
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)
69.42%
Sentence opener variety
(details)
54.64%
Adverb-first sentence starts
(details)
88.85%
Pronoun-first sentence starts
(details)
33.77%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
88.1949%
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 delivery bag still reeked
of five-spice when Rory pushed through the door of the Nest, and she wanted nothing in the world but a whisky and the stool at the far end of the bar where Silas kept her tab open.
She got halfway across the
floor before a voice stopped her. "Jesus Christ. Aurora?"
She knew the voice before
she turned. The Cardiff in it.
The upward lilt on the
second syllable, the way it went soft at the edges, like someone biting into fruit.
Mara Hughes sat at the
corner booth with a glass of house red and a coat folded over her lap. Her hair was shorter.
A proper solicitor's crop, blunt
along the jaw.
She wore a charcoal suit
that fit her too well to be off a peg. Three years, maybe four, and she looked like she'd stepped out of a different life entirely. "Mara." "Don't just stand there. Christ. Sit down."
Rory set the insulated bag
on the floor.
The grease stain on her
jumper felt
suddenly
loud.
She slid into the booth
opposite and watched Mara's eyes do the tour. Hair. Hands.
The crescent scar on her
wrist, which Mara had always found easier to look at than Rory's face. "You work here?" "I live here. Upstairs." "Upstairs."
Mara repeated it like she
was tasting
something. "Above a bar in Soho. That's. Yeah. That tracks." "What does that mean?" "Nothing. It means nothing."
She lifted her glass
.
Her nails were painted a
colour so discreet it barely existed. "You were always going to end up somewhere interesting." "And you?" "Linklaters. Corporate litigation. We're doing a thing at The Groucho tonight, some partner's leaving do. I got out early." "Linklaters." "Don't say it like that." "Like what?" "Like you're reading the word off a gravestone." Rory almost laughed.
She reached across, took Mara's
wine, sipped. Too warm. Supermarket stuff, dressed up.
Silas would lose his mind
if he knew she'd served it. "I pictured you differently," Rory said. "Funny. I pictured you at all. You didn't make that easy." There it was. Quick as a paper cut. Rory set the glass down and folded her hands in her lap, the way her mother used to when a parent-teacher evening turned sharp. "I meant to ring." "For four years." "Mara." "You left a voicemail. Do you remember what you said?" "No." "You said, 'I'm fine, don't look for me, tell the others I love them.' That was it. Forty-one seconds. I timed it. I kept it on the old phone for about a year, then I dropped the phone in the bath on purpose and watched it die." A pair of tourists came in, looked around at the maps on the walls, decided the place was too dim for them, left again. The door swung shut. Silas, behind the bar, caught Rory's eye and lifted an
eyebrow
. She shook her head. Not yet. "I couldn't tell anyone where I was going," she said. "You could have told me." "No. I couldn't." "Why?" Rory thought about Evan. About the last night in Cardiff. About the hallway, and the mirror, and the thing she'd learnt about her own face under pressure.
She thought about how Mara
had sat across from Evan at a pub quiz once and laughed at his jokes, and how that wasn't Mara's fault but it had made her impossible to trust. "Because you liked him," she said. Mara's face did something complicated. A small muscle under the eye. "Oh." "Yeah." "Oh, Rory." "Don't." "I didn't know." "Nobody did. That was sort of the point." Mara looked down at the wine.
She turned the glass a
quarter turn, a quarter turn back. A solicitor's tic. Rory had never seen her do it before. "I saw him, you know," Mara said. "Last Christmas. Queen Street. He was with a woman. She had a plaster on her cheekbone. I didn't speak to him." "Good." "I thought about you. I thought, that could have been, and then I thought, no, Rory would never have let it get that far a second time." Mara looked up. "But you did let it get that far, didn't you. The first time." "Mara." "I'm not judging. I'm saying I didn't know. I should have known. That's what I'm saying." Rory felt the thing she'd been holding for four years slip a little lower in her chest. Not all the way. Not undone. Just loosened. "You couldn't have known." "I'm your friend." "Were." "Am. Don't be a prick." She laughed.
It came out sudden and
wet and she pressed the heel of her hand against her mouth. Mara watched her, and her face
had that lawyer's
stillness now, the kind that waited for information. But her eyes weren't still.
Her eyes were the same
eyes that had sat beside Rory at nineteen in a lecture theatre and written *
kill me
* in the margin of a contracts textbook. "You went through with it," Rory said. "Pre-Law. Training contract. The whole road." "Someone had to." "That's a shitty thing to say." "I know. Sorry. I've been practising shitty things to say to you for four years. I didn't vet them all." "Keep going." "No. I think that was the only one." Silas limped over with two fresh glasses and a bottle that had no supermarket sticker on it.
He set them down without
a word, gave Mara the briefest nod, and left.
His signet ring caught the
lamp-light as he went. "Who's he?" "Landlord. Sort of." "Sort of." "It's complicated." "Everything with you is complicated." "Is it?" "Was." Mara poured for both of them. Her hand was steady. "Maybe still is. I don't know you anymore, Aurora." "Rory." "Rory, then."
She lifted the glass
. "To not knowing each other." "That's grim." "It's honest. Take it or leave it." Rory took it. They drank. The wine this time was better than either of them deserved, and for a moment the booth held the two women they had been at twenty-one, and the two women they were now, and the long silent road between, and none of it quite touched.
Then Mara's phone buzzed on
the table. She looked down.
Her face changed, the stillness
dropping into something Rory didn't recognise, a new expression Mara had grown in the years without her. "I have to take this." "Mara." "I'll come back. Don't move."
She was already standing, the
charcoal coat over her arm, the phone at her ear, and as she pushed out through the door of the Nest she said, clear enough for Rory to hear across the room, "Say that again. Say exactly what he said to you." The door swung shut behind her. Rory stared at the empty seat. On the table, Mara had left her wallet open, and a photograph, folded small, sat on top of a stack of cards. Rory reached for it.
created_at
"2026-04-24T19:46:25.717Z"
4/24/2026, 7:46:25 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3035
moderation_latency
(null)
generation_time
37833
tokens_prompt
4618
tokens_completion
1942
native_tokens_prompt
6499
native_tokens_completion
2988
native_tokens_completion_images
(null)
native_tokens_reasoning
226
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"
usage
0.107195
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"3dacbda8-2f8d-4ca2-b5c5-bbcd896ff4e1"
is_byok
false
latency
896
model_permaslug
"anthropic/claude-4.7-opus-20260416"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777059985-p3E0bHpUgBcurkCCFSzO"
session_id
(null)
api_type
"completions"
id
"gen-1777059985-q706E3hqHA6spM4UsTKE"
upstream_id
"3dacbda8-2f8d-4ca2-b5c5-bbcd896ff4e1"
total_cost
0.107195
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
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
11
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
70
tagDensity
0.157
leniency
0.314
rawRatio
0
effectiveRatio
0
95.66%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1153
totalAiIsmAdverbs
1
found
0
adverb
"suddenly"
count
1
highlights
0
"suddenly"
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)
91.33%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1153
totalAiIsms
2
found
0
word
"lilt"
count
1
1
word
"eyebrow"
count
1
highlights
0
"lilt"
1
"eyebrow"
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
74
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
74
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
133
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
48
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
1
markdownWords
2
totalWords
1153
ratio
0.002
matches
0
"kill me"
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
16
unquotedAttributions
0
matches
(empty)
33.33%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
45
wordCount
742
uniqueNames
7
maxNameDensity
2.29
worstName
"Rory"
maxWindowNameDensity
4
worstWindowName
"Mara"
discoveredNames
Rory
17
Nest
2
Silas
4
Cardiff
2
Hughes
1
Mara
17
Evan
2
persons
0
"Rory"
1
"Silas"
2
"Hughes"
3
"Mara"
4
"Evan"
places
0
"Cardiff"
globalScore
0.354
windowScore
0.333
89.02%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
41
glossingSentenceCount
1
matches
0
"looked like she'd stepped out of a differ"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1153
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
133
matches
0
"had that lawyer's"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
81
mean
14.23
std
17.18
cv
1.207
sampleLengths
0
42
1
11
2
3
3
31
4
63
5
1
6
7
7
50
8
3
9
4
10
18
11
4
12
28
13
2
14
19
15
1
16
5
17
2
18
8
19
27
20
6
21
11
22
32
23
4
24
3
25
1
26
10
27
1
28
47
29
45
30
10
31
5
32
3
33
1
34
61
35
6
36
11
37
1
38
1
39
2
40
1
41
3
42
8
43
28
44
28
45
1
46
43
47
1
48
16
49
25
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
74
matches
0
"were painted"
89.81%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
2
totalVerbs
121
matches
0
"was tasting"
1
"was already standing"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
133
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
746
adjectiveStacks
0
stackExamples
(empty)
adverbCount
22
adverbRatio
0.029490616621983913
lyAdverbCount
3
lyAdverbRatio
0.004021447721179625
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
133
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
133
mean
8.67
std
9.29
cv
1.071
sampleLengths
0
42
1
11
2
3
3
7
4
4
5
20
6
20
7
4
8
8
9
15
10
16
11
1
12
7
13
8
14
9
15
13
16
1
17
1
18
18
19
3
20
4
21
9
22
9
23
4
24
8
25
11
26
9
27
2
28
19
29
1
30
5
31
2
32
8
33
3
34
7
35
2
36
4
37
11
38
6
39
11
40
3
41
5
42
24
43
4
44
3
45
1
46
10
47
1
48
47
49
24
69.42%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
6
diversityRatio
0.44360902255639095
totalSentences
133
uniqueOpeners
59
54.64%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
61
matches
0
"Then Mara's phone buzzed on"
ratio
0.016
88.85%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
20
totalSentences
61
matches
0
"She got halfway across the"
1
"She knew the voice before"
2
"Her hair was shorter."
3
"She wore a charcoal suit"
4
"She slid into the booth"
5
"She lifted her glass"
6
"Her nails were painted a"
7
"She reached across, took Mara's"
8
"She shook her head."
9
"She thought about how Mara"
10
"She turned the glass a"
11
"It came out sudden and"
12
"Her eyes were the same"
13
"He set them down without"
14
"His signet ring caught the"
15
"Her hand was steady."
16
"She lifted the glass"
17
"She looked down."
18
"Her face changed, the stillness"
19
"She was already standing, the"
ratio
0.328
33.77%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
52
totalSentences
61
matches
0
"The delivery bag still reeked"
1
"She got halfway across the"
2
"She knew the voice before"
3
"The Cardiff in it."
4
"The upward lilt on the"
5
"Mara Hughes sat at the"
6
"Her hair was shorter."
7
"A proper solicitor's crop, blunt"
8
"She wore a charcoal suit"
9
"Rory set the insulated bag"
10
"The grease stain on her"
11
"She slid into the booth"
12
"The crescent scar on her"
13
"Mara repeated it like she"
14
"She lifted her glass"
15
"Her nails were painted a"
16
"Rory almost laughed."
17
"She reached across, took Mara's"
18
"Supermarket stuff, dressed up."
19
"Silas would lose his mind"
ratio
0.852
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
61
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
26
technicalSentenceCount
1
matches
0
"Mara watched her, and her face had that lawyer's stillness now, the kind that waited for information."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
11
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
6
fancyCount
1
fancyTags
0
"Mara repeated (repeat)"
dialogueSentences
70
tagDensity
0.086
leniency
0.171
rawRatio
0.167
effectiveRatio
0.029
88.1949%