NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ77EXW68HM7JF6V5MJ1G5T6
Run Details
Model:
Qwen 3.6 Flash
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
32.8s
Cost:
$0.008085
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
85.71%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
46.43%
AI-ism word frequency
(details)
100.00%
Cliché density
(details)
100.00%
Emotion telling (show vs. tell)
(details)
99.57%
Filter word density
(details)
100.00%
Gibberish response detection
(details)
100.00%
Markdown formatting overuse
(details)
100.00%
Missing dialogue indicators (quotation marks)
(details)
83.33%
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)
99.95%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
100.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
34.85%
Sentence opener variety
(details)
19.38%
Adverb-first sentence starts
(details)
26.98%
Pronoun-first sentence starts
(details)
12.33%
Subject-first sentence starts
(details)
29.07%
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)
84.5864%
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 my
fingers.
I caught it against the
damp mahogany before it hit the floor, knuckles scraping against the wood. The sound
echoed
wrong. Too sharp. Too close.
I looked up past the
green neon sign humming above the entrance.
The man stood in the
shadow of the coat rack, water dripping from a charcoal wool coat onto the scuffed parquet floor. His posture had changed. Shoulders squared like armour. Jaw set hard.
The scruffy university jumper was
gone, replaced by a tailored charcoal jacket that cost more than my monthly rent. Finn.
It had been six years
since Cardiff. Six years since we shared a cramped flat above a bakery and argued over property law until three in the morning. Six years since I packed two bags and ran south, leaving half my life dissolved in a puddle of spilled lager and broken promises. You
look
tired.
You look like you sleep
in a suit. The words hung between us, sharp and deliberate. Finn did not smile.
My eyes traced the fine
lines crowning his eyes, the grey threading through his
carefully
styled hair.
The boy who once could
quote entire sections of the Sale of Goods Act from memory now carried himself like a man weighing down a heavy coat.
Silas wiped a tumbler with
a lint-free cloth.
His silver signet ring caught
the low light,
glinting
against his knuckles before he slid behind the bar and disappeared into the shadow of the wine rack.
The spymaster did not ask
questions.
He learned long ago that
silence
made people bleed faster. You came to Soho. The door was open. I saw the light. The Raven’s Nest was
neither a shelter nor
a destination. It was a crossing point. I knew that. Finn knew it too.
We both knew why his
feet had carried him here, past the tourist traps and the damp alleyways. Why now? The question sat heavy between us. Finn reached into his jacket pocket.
His fingers brushed against the
fabric for a second before retracing the motion.
He did not pull anything
out. Dinner. I laughed. It came out flat.
We had not celebrated birthdays
or anniversaries since the third year.
We had not exchanged Christmas
cards since the day I left.
You remember how I take
my coffee. Black. Two sugars. You always ruined the cup. Finn stepped closer. His boots made a soft scuff against the floorboards. He leaned against the bar, his reflection distorting in the mirrored tiles behind my shoulders. The old maps on the walls
seemed to
shift in the peripheral vision, parchment edges curling, ink lines
tracing
routes that no longer existed. You left Cardiff, Rory. I left Evan. The name tasted like copper. Finn’s gaze dropped to my left wrist. The crescent scar caught the green light. I had hidden it under a leather bracelet since the delivery uniform arrived. The skin had healed smooth, but the nerve endings still flared when the air turned cold. He made you run. He made me stay too long. Finn pushed off the bar. His limp, barely noticeable now, betrayed the limp in his left knee. An old rugby injury healed poorly, or maybe something else. The city takes its toll. I turned the tumbler in my hands. Water condensed on the glass, cold against my palm. The restaurant delivery bag sat heavy behind me, still warm from the kitchen. Golden Empress kept the pots
simmering
past midnight. Yu-Fei did not care about law degrees or childhood fears. He cared about accurate change and timely drops. You could have called. And say what? That I found someone to live with? That I passed the coursework? That my father stopped leaving voicemails at midnight? Finn’s voice dropped, losing its polished edge. I would have
sounded like a coward
. I set the glass down. The condensation left a
perfect
ring on the wood. You
look
like a lawyer now. Circuit court. Corporate division. I draft contracts for people who never read them. I negotiate settlements for men who pay me to
look
tired and listen
carefully
. I have a corner office. I have a mortgage. I have exactly what we promised the society when we pinned our blazers and memorised the rulebooks. His hand
trembled
. Just once. A
flicker
of instability before he tucked it into his pocket. You
look
like you are running out of time. My words landed soft. Too soft. Finn’s
eyes narrowed
. The hazel had faded into something duller, clouded by too many late nights and too many quiet rooms. You delivered dumplings while I built a career. You delivered dumplings while I built a fortress. The air between us grew thick. The low hum of a jazz record filled the space, bass notes crawling under the surface. Silas moved behind the bar, his limp dragging
slightly
on the right. He poured two fingers of single malt into a tumbler and set it down. No coasters. Just glass meeting wood. I came to say I am sorry. For what? For leaving. For not standing in your flat door when the police came. For letting you
think
I chose
silence
. Finn reached into his jacket again. This time, he pulled out a folded sheet of paper. The edges were worn soft. He placed it on the counter between us. The ink had bled
slightly
at the margins, dark smudges blooming like bruises. Read it. I did not touch it. The paper smelled of stale cigarettes and damp concrete. My name
was written
in bold, block letters across the top. My address below. A date. Four days from tomorrow. Who sent this? A private investigator. I hired him six months ago. He tracked your movements. Your job. Your flat. He sent receipts. Bank transactions. Security footage from your building. He showed me everything. The jazz record skipped. A scratch tore through the melody. Finn did not flinch. I stared at the paper until the letters blurred. My fingers curled under the bar, nails biting into my palms. Why show me this? Because the address is wrong. The flat number matches yours, but the postcode is for a warehouse in Woolwich. The building photos show a different entrance. Different windows. Someone changed a single digit on a delivery log. Someone wanted you to
think
you were
being followed
. Silas stopped wiping the glass. He tilted his head, listening. The back room door sat half-hidden behind the mahogany bookshelf. It remained shut. The latch was clean. Undisturbed. You tracked the investigator. I tracked everything. Finn’s voice dropped to a
whisper
. I spent three months following a shadow through Camden and Islington. I learned who visits you at two in the morning. I learned who picks up your delivery bags from the kitchen window. I learned Evan has a brother in Southwark. A brother who buys cheap locks and sells fast. My breath caught. The scar on my wrist
throbbed
. I pressed two fingers against it, feeling the raised tissue beneath the skin. Get out of this city, Rory. Pack what matters. Leave the flat tonight. Do not check your phone. Do not answer unknown numbers. Do not walk the same route twice. You sound like you are pleading. I sound like you have not learned anything. Finn stepped back. His shoes squeaked against the worn floor. The green neon sign
flickered
, buzzing like a trapped insect. I cannot just leave. You already did. The door chime rang. Sharp. Abrupt. Wind swept in, carrying the damp
chill
of a London evening. A man in a dark bomber jacket slipped through the gap, shoulders hunched, eyes
scanning
the room. He did not
look
at Finn. He did not
look
at Silas. He looked straight at me. His hand rested inside his jacket. The fabric pulled tight across his back. Finn’s voice cut through the record. Down the side steps. Now. I followed without thinking. I moved past the bar, boots sliding against the wood. Silas stopped wiping. He set the glass down. His hand moved to the drawer beneath the counter, pulling out a heavy brass flashlight. The bomber jacket man stepped fully into the light. He reached inside his coat. Metal glinted. I turned to run. My shoulder hit the bookshelf. The wood groaned. The hidden door swung inward, revealing a glimpse of concrete stairs and cold air. Finn moved first.
created_at
"2026-04-27T10:23:49.135Z"
4/27/2026, 10:23:49 AM
model
"qwen/qwen3.6-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
959
moderation_latency
(null)
generation_time
32511
tokens_prompt
4618
tokens_completion
5107
native_tokens_prompt
4477
native_tokens_completion
4644
native_tokens_completion_images
(null)
native_tokens_reasoning
2851
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00808525
router
(null)
provider_responses
0
endpoint_id
"2435bec9-c808-4f27-9fc8-12f3460d7b66"
id
"chatcmpl-6a4400b4-74d4-9e8c-8276-2f99b5d8ed3c"
is_byok
false
latency
959
model_permaslug
"qwen/qwen3.6-flash"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777285429-yo7EeIalAzKwqF3aDDan"
session_id
(null)
api_type
"completions"
id
"gen-1777285429-93Bq1UbRF6n521ROfEN2"
upstream_id
"chatcmpl-6a4400b4-74d4-9e8c-8276-2f99b5d8ed3c"
total_cost
0.00808525
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
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
0
85.71%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1400
totalAiIsmAdverbs
4
found
0
adverb
"carefully"
count
2
1
adverb
"slightly"
count
2
highlights
0
"carefully"
1
"slightly"
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)
46.43%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1400
totalAiIsms
15
found
0
word
"echoed"
count
1
1
word
"traced"
count
1
2
word
"glinting"
count
1
3
word
"silence"
count
2
4
word
"tracing"
count
1
5
word
"simmering"
count
1
6
word
"perfect"
count
1
7
word
"trembled"
count
1
8
word
"flicker"
count
1
9
word
"whisper"
count
1
10
word
"throbbed"
count
1
11
word
"flickered"
count
1
12
word
"chill"
count
1
13
word
"scanning"
count
1
highlights
0
"echoed"
1
"traced"
2
"glinting"
3
"silence"
4
"tracing"
5
"simmering"
6
"perfect"
7
"trembled"
8
"flicker"
9
"whisper"
10
"throbbed"
11
"flickered"
12
"chill"
13
"scanning"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"eyes widened/narrowed"
count
1
highlights
0
"eyes narrowed"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
198
matches
(empty)
99.57%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
5
hedgeCount
1
narrationSentences
198
filterMatches
0
"look"
1
"think"
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
198
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
27
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1400
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
0
unquotedAttributions
0
matches
(empty)
83.33%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
57
wordCount
1400
uniqueNames
20
maxNameDensity
1.14
worstName
"Finn"
maxWindowNameDensity
2.5
worstWindowName
"You"
discoveredNames
Cardiff
2
Sale
1
Goods
1
Act
1
Soho
1
Raven
1
Nest
1
Christmas
1
Rory
2
Evan
2
Empress
1
Woolwich
1
Camden
1
Islington
1
Southwark
1
London
1
Finn
16
Silas
5
You
14
Do
3
persons
0
"Raven"
1
"Christmas"
2
"Rory"
3
"Evan"
4
"Empress"
5
"Finn"
6
"Silas"
7
"You"
places
0
"Cardiff"
1
"Soho"
2
"Woolwich"
3
"Camden"
4
"Islington"
5
"Southwark"
6
"London"
globalScore
0.929
windowScore
0.833
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
102
glossingSentenceCount
1
matches
0
"sounded like a coward"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.714
wordCount
1400
matches
0
"neither a shelter nor"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
198
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
62
mean
22.58
std
19.09
cv
0.845
sampleLengths
0
31
1
64
2
1
3
52
4
3
5
8
6
56
7
51
8
4
9
8
10
40
11
2
12
31
13
1
14
28
15
7
16
8
17
51
18
4
19
3
20
48
21
4
22
6
23
32
24
55
25
4
26
37
27
20
28
53
29
16
30
9
31
27
32
8
33
8
34
54
35
7
36
2
37
20
38
42
39
2
40
34
41
3
42
31
43
34
44
4
45
46
46
28
47
4
48
59
49
22
99.95%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
3
totalSentences
198
matches
0
"was gone"
1
"was written"
2
"being followed"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
258
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
198
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1403
adjectiveStacks
0
stackExamples
(empty)
adverbCount
41
adverbRatio
0.029223093371347115
lyAdverbCount
10
lyAdverbRatio
0.007127583749109052
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
198
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
198
mean
7.07
std
5.04
cv
0.713
sampleLengths
0
6
1
17
2
4
3
2
4
2
5
12
6
22
7
4
8
4
9
3
10
19
11
1
12
7
13
21
14
24
15
3
16
8
17
8
18
4
19
17
20
27
21
8
22
27
23
6
24
10
25
4
26
4
27
4
28
10
29
5
30
3
31
4
32
18
33
2
34
6
35
6
36
13
37
6
38
1
39
2
40
4
41
11
42
11
43
7
44
1
45
2
46
5
47
3
48
9
49
15
34.85%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
30
diversityRatio
0.25757575757575757
totalSentences
198
uniqueOpeners
51
19.38%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
172
matches
0
"Just glass meeting wood."
ratio
0.006
26.98%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
83
totalSentences
172
matches
0
"I caught it against the"
1
"I looked up past the"
2
"His posture had changed."
3
"It had been six years"
4
"You look tired."
5
"You look like you sleep"
6
"My eyes traced the fine"
7
"His silver signet ring caught"
8
"He learned long ago that"
9
"You came to Soho."
10
"I saw the light."
11
"It was a crossing point."
12
"I knew that."
13
"We both knew why his"
14
"His fingers brushed against the"
15
"He did not pull anything"
16
"It came out flat."
17
"We had not celebrated birthdays"
18
"We had not exchanged Christmas"
19
"You remember how I take"
ratio
0.483
12.33%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
154
totalSentences
172
matches
0
"The glass slipped from my"
1
"I caught it against the"
2
"The sound echoed wrong."
3
"I looked up past the"
4
"The man stood in the"
5
"His posture had changed."
6
"Shoulders squared like armour."
7
"Jaw set hard."
8
"The scruffy university jumper was"
9
"It had been six years"
10
"You look tired."
11
"You look like you sleep"
12
"The words hung between us,"
13
"Finn did not smile."
14
"My eyes traced the fine"
15
"The boy who once could"
16
"Silas wiped a tumbler with"
17
"His silver signet ring caught"
18
"The spymaster did not ask"
19
"He learned long ago that"
ratio
0.895
29.07%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
172
matches
0
"Because the address is wrong."
ratio
0.006
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
47
technicalSentenceCount
1
matches
0
"I negotiate settlements for men who pay me to look tired and listen carefully."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
0
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
0
84.5864%