NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-24-01KVX39Q76NM7RXCTFY9HPY9ZD
Run Details
Model:
Z.AI GLM 5.2 (Reasoning, High)
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
2m 19s
Cost:
$0.030817
Provider:
Z.AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
91.25%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
65.00%
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)
66.67%
Name drop frequency
(details)
100.00%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
100.00%
Paragraph length variance
(details)
97.55%
Passive voice overuse
(details)
50.75%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
99.73%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
57.89%
Sentence opener variety
(details)
0.00%
Adverb-first sentence starts
(details)
0.00%
Pronoun-first sentence starts
(details)
22.50%
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)
81.7115%
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 pint glass hit the
bar before I'd finished the last one.
Silas had a habit of
reading the room better than the room read itself. "Someone's staring at you." I didn't turn. "Lots of people stare. It's a bar." "Not like this."
Silas polished a glass with
the patience of a man who'd once waited in safehouses for extraction.
His hazel eyes flicked toward
the entrance, then back to me.
The silver signet ring on
his right hand caught the light as he set the glass down. I turned.
The woman stood near the
door, one hand still on the handle, the other clutching a handbag too small for London.
Her eyes swept the room
with the desperate precision of someone searching for an exit, not an entrance. She'd lost
weight
.
Her collarbones stood out like
tent poles beneath a blouse that had fit her two years ago.
The hair I remembered as
a wild copper mane had
been straightened
into submission, pulled back so tight it changed the geometry of her face. Cara Walsh.
I hadn't seen her since
the night I'd packed a single suitcase and caught the last train out of Cardiff. Three years. She'd been at the platform, actually. Standing on the opposite side of the barrier. She hadn't waved. "Cara." "Rory."
Her smile appeared and vanished
like a reflex. "I thought that was you. I almost didn't, but then I thought, no, that's, that's definitely her. God. How long has it been?" "Three years." "Three years."
She repeated it like she
was tasting
something gone off. "You look well." She didn't.
The circles under her eyes
had the particular bruise-purple of sustained sleeplessness.
Her foundation was good, expensive
probably, but it couldn't fill the hollows beneath her cheekbones.
She wore long sleeves in
a warm bar and kept her right hand curled around her left wrist. "Sit down. Drink?" "Gin and tonic. Whatever's fine." I caught Silas' eye.
He was already reaching for
the bottle.
His gaze lingered on Cara
a beat too long, cataloguing. Old habits. Cara perched on the barstool like she might need to leave in a hurry.
Her bag went on her
lap, not the bar.
She hadn't taken off her
coat. "I'm in London for a conference. Conveyancing symposium at the ExCeL. Riveting stuff." "You finished law school." "Of course I finished. Top of the year, actually."
She adjusted her bag strap
. "Got a position at Howell & Lewis. Commercial property. It's, you know, it's fine." Top of the year. The Cara I'd known would have announced it like a triumph. This Cara said it like a confession. Silas placed the gin and tonic in front of her.
She wrapped both hands around
it. "Quiet place." "It has its moments." "The kind of place you'd find in Cardiff, actually. There was one on Womanby Street, remember? The Bootlegger? They had that dog that would sleep on the bar." "I remember." "We went there after results day. You threw up in their bathroom sink." "I remember that too." She laughed. It sounded like it hurt. The
silence
that followed had
weight
. Three years of it, compressed into the space between two barstools. I picked up my pint. Took a sip. Set it down. "You're not here for a conveyancing symposium." Cara's fingers tightened around her glass. She looked at the walls, the old maps, the black-and-white photographs, everywhere but at me. "I needed to get out of Cardiff." "Why?" "Does anyone need a reason?" "Cara." Her name landed between us like something dropped from a height. She finally looked at me, and what I found in her expression made me set my pint down. "He asked about you." The clinking glasses, the murmur of conversation, the low hum of the bar, it all pulled back. Like the tide going out. "Evan." "Who else." She took a long drink. "Came to my office, actually. Last Tuesday. Walked right past reception. Sat down in my chair like he owned it. Asked if I'd heard from you." "What did you tell him?" "The truth. I haven't. Not since you left." She paused. "He didn't believe me." Cara's right hand had migrated to her left wrist again. She
was rubbing
it. Not casually. The way you'd press something that ached. I reached across and took her hand. Gently. She flinched, then let me turn her wrist over. I pushed the sleeve back. The bruise was old. Yellowed at the edges. But the shape was unmistakable. Four fingers, wrapped around the bone like a clamp. I let go of her hand. She pulled the sleeve down. "How long?" "Rory, don't." "How long have you been with him?" The question filled the space between us. Cara's mouth opened, closed. She picked up her gin and tonic, put it down without drinking. "After you left, he was... I don't know. He was different. Quiet. Lost. He kept saying he didn't understand where you'd gone. I believed him." She stared at her drink. "I was stupid." "You weren't stupid." "I was exactly that." Her voice cracked along a fault line that had been there for a while. "You left, and I thought, well, Rory had her reasons. She always had reasons. But I didn't ask. I didn't call. I just, he was there, and he looked lost, and then it just..." She pressed her palm flat against the bar, steadying herself. "It got bad, Rory. It got
really
bad." Silas materialised at the far end of the bar. He didn't speak. He didn't need to. His presence was a question aimed at me, and I answered it with the smallest shake of my head. Not yet. "Does he know you're here?" "I told him I was at the conference." "Does he know where you're staying?" "No." "Good." I pulled my phone from my pocket and slid it across the bar. "Call whoever you need to call. Tell them you're safe. Then you're staying with me." "I can't, I have the hotel, I already paid, I, Rory, I didn't come here to, I just needed to get out, I just needed one night where I didn't have to..." Her voice broke apart. She pressed her fist against her mouth. The bar noise swelled back in, filling the
silence
her words had carved. I put my hand on her shoulder. She was trembling. Fine, rapid tremors, the kind the body produces when it's been running on adrenaline for too long and finally found somewhere safe enough to stop. The door of the Raven's Nest opened. Cold air cut through the
warmth
. A man stepped inside. Heavyset, dark jacket. He
scanned
the room with the slow,
methodical
sweep of someone who'd
been taught
to look. Cara went rigid under my hand. "That's not him." Her voice dropped to almost nothing. "That's one of his."
created_at
"2026-06-24T15:17:09Z"
6/24/2026, 3:17:09 PM
model
"z-ai/glm-5.2-20260616"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5377
moderation_latency
(null)
generation_time
138200
tokens_prompt
4618
tokens_completion
7560
native_tokens_prompt
4207
native_tokens_completion
6743
native_tokens_completion_images
(null)
native_tokens_reasoning
5226
native_tokens_cached
4160
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
service_tier
(null)
usage
0.0308166
router
(null)
provider_responses
0
endpoint_id
"442ea97f-ad5e-40d5-b9a6-66e9e0417dce"
id
"202606242317093de206cf074f452a"
is_byok
false
latency
5377
model_permaslug
"z-ai/glm-5.2-20260616"
provider_name
"Z.AI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer
(null)
request_id
"req-1782314229-jJvLrT24NDMCkpV7frQ4"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782314229-DknB9XJg5UaHZqaReadu"
upstream_id
"202606242317093de206cf074f452a"
total_cost
0.0308166
cache_discount
0.0047424
upstream_inference_cost
0
provider_name
"Z.AI"
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
10
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
51
tagDensity
0.196
leniency
0.392
rawRatio
0
effectiveRatio
0
91.25%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1143
totalAiIsmAdverbs
2
found
0
adverb
"gently"
count
1
1
adverb
"really"
count
1
highlights
0
"gently"
1
"really"
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)
65.00%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1143
totalAiIsms
8
found
0
word
"flicked"
count
1
1
word
"weight"
count
2
2
word
"silence"
count
2
3
word
"warmth"
count
1
4
word
"scanned"
count
1
5
word
"methodical"
count
1
highlights
0
"flicked"
1
"weight"
2
"silence"
3
"warmth"
4
"scanned"
5
"methodical"
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
91
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
91
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
34
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1143
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
11
unquotedAttributions
0
matches
(empty)
66.67%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
19
wordCount
760
uniqueNames
8
maxNameDensity
1.18
worstName
"Cara"
maxWindowNameDensity
3
worstWindowName
"Cara"
discoveredNames
London
1
Walsh
1
Cardiff
1
Cara
9
Top
1
Raven
1
Nest
1
Silas
4
persons
0
"Walsh"
1
"Cara"
2
"Raven"
3
"Nest"
4
"Silas"
places
0
"London"
1
"Cardiff"
globalScore
0.908
windowScore
0.667
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
55
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1143
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
133
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
69
mean
16.57
std
15.66
cv
0.946
sampleLengths
0
26
1
4
2
10
3
3
4
45
5
2
6
84
7
2
8
39
9
1
10
32
11
2
12
15
13
47
14
3
15
5
16
23
17
29
18
13
19
4
20
28
21
22
22
16
23
2
24
4
25
28
26
2
27
13
28
4
29
7
30
28
31
7
32
21
33
7
34
1
35
5
36
1
37
29
38
4
39
22
40
1
41
33
42
5
43
14
44
23
45
22
46
22
47
11
48
2
49
2
97.55%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
2
totalSentences
91
matches
0
"been straightened"
1
"been taught"
50.75%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
3
totalVerbs
134
matches
0
"was tasting"
1
"was already reaching"
2
"was rubbing"
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)
99.73%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
521
adjectiveStacks
0
stackExamples
(empty)
adverbCount
21
adverbRatio
0.04030710172744722
lyAdverbCount
6
lyAdverbRatio
0.011516314779270634
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
8.59
std
6.96
cv
0.81
sampleLengths
0
12
1
14
2
4
3
3
4
7
5
3
6
17
7
11
8
17
9
2
10
21
11
18
12
3
13
17
14
25
15
2
16
20
17
2
18
6
19
8
20
3
21
1
22
9
23
23
24
2
25
12
26
3
27
2
28
12
29
15
30
18
31
3
32
5
33
4
34
7
35
10
36
2
37
14
38
9
39
6
40
13
41
4
42
14
43
14
44
4
45
11
46
7
47
10
48
6
49
2
57.89%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
3
diversityRatio
0.3609022556390977
totalSentences
133
uniqueOpeners
48
0.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
0
totalSentences
80
matches
(empty)
ratio
0
0.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
44
totalSentences
80
matches
0
"I didn't turn."
1
"His hazel eyes flicked toward"
2
"Her eyes swept the room"
3
"She'd lost weight."
4
"Her collarbones stood out like"
5
"I hadn't seen her since"
6
"She'd been at the platform,"
7
"She hadn't waved."
8
"Her smile appeared and vanished"
9
"She repeated it like she"
10
"Her foundation was good, expensive"
11
"She wore long sleeves in"
12
"He was already reaching for"
13
"His gaze lingered on Cara"
14
"Her bag went on her"
15
"She hadn't taken off her"
16
"She adjusted her bag strap"
17
"She wrapped both hands around"
18
"It sounded like it hurt."
19
"I picked up my pint."
ratio
0.55
22.50%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
70
totalSentences
80
matches
0
"The pint glass hit the"
1
"Silas had a habit of"
2
"I didn't turn."
3
"Silas polished a glass with"
4
"His hazel eyes flicked toward"
5
"The silver signet ring on"
6
"The woman stood near the"
7
"Her eyes swept the room"
8
"She'd lost weight."
9
"Her collarbones stood out like"
10
"The hair I remembered as"
11
"I hadn't seen her since"
12
"She'd been at the platform,"
13
"She hadn't waved."
14
"Her smile appeared and vanished"
15
"She repeated it like she"
16
"The circles under her eyes"
17
"Her foundation was good, expensive"
18
"She wore long sleeves in"
19
"He was already reaching for"
ratio
0.875
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
80
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
29
technicalSentenceCount
1
matches
0
"Her collarbones stood out like tent poles beneath a blouse that had fit her two years ago."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
10
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
1
fancyCount
1
fancyTags
0
"She repeated (repeat)"
dialogueSentences
51
tagDensity
0.02
leniency
0.039
rawRatio
1
effectiveRatio
0.039
81.7115%