NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ7QRFPGHRKNXQAA49SM016
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
1m 11s
Cost:
$0.001425
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
76.00%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
44.00%
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)
80.56%
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)
100.00%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
82.83%
Em-dash & semicolon overuse
(details)
91.05%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
52.10%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
100.00%
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)
90.8847%
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 key turned in the
back door of The Raven’s Nest with a resistance that hadn’t been there two years ago.
Aurora Carter paused, the cold
iron biting through her glove. She twisted harder.
The lock gave with a
gritty *
clunk
*, like a smoker’s cough. Inside,
the air was thick with
the ghost of last night’s smoke and the faint, peppery scent of old mahogany. No lights on. Not yet. But the bar was never
truly
empty.
She stepped in, boots echoing
just once before the floorboards swallowed the noise.
The same cracked leather booth
near the back.
The same brass rail along
the partition, tarnished now
in
patches where someone—probably her—had polished it during long, slow shifts. Maps. Photos. A city that didn’t blink. But different.
The mirror behind the counter
had a new crack, spiderwebbing from the lower left.
The jukebox—out of order for
a decade—
was gone
. In its place, a single oil painting.
A raven, wings half-spread, eyes
too knowing. Footsteps. Slow. Uneven. Silas appeared from the corridor, wiping a glass with a cloth so worn it was almost transparent.
His beard was fuller, the
grey now winning.
The limp heavier, like the
knee remembered Prague more each winter. He didn’t look surprised. “You’re late,” he said. “I wasn’t expected.” “No. But you always were.”
Aurora dropped her delivery bag
by the door.
The weight of the insulated
boxes pressed into her side.
She hadn’t taken it off
since Golden Empress. Still warm. Still functional. “You cut your hair,” he said. “Grew it out, actually.” “You left it long when you left.” “I left a lot when I left.” Silas set the glass down. Placed the cloth over the counter. Precise. Like folding a flag. “You kept the ring.”
He lifted his right hand
slightly
. The silver signet caught the dim light. No crest. Just a circle. Worn smooth. “Habit.” “Or something you can’t let go?” He didn’t answer. Crossed
to
the taps, pulled two pints. Set one
in
front of her. The foam settled just above the rim. Perfect. “You still drink it flat?” “Still remember how I like it.” “Five years,” he said. “Five years, two months, six days.” “You counting?” “I stopped counting.”
She lifted the glass
. “Just remembered.” He sat opposite. The booth creaked under him. Same as always. “You look older.” “So do you.” “Different kind of older.”
He studied her
. “Yours isn’t from time. It’s from something you carry.” Aurora sipped. The ale was warm and bitter. Comfortable. “You got Eva’s message?” “No.” “She said she passed one along.” “Then she lied.” “She said you’d be here.” “She doesn’t know me anymore.” “She said you left Cardiff because of him.” “I left Cardiff because I chose.” Silas
let that hang
. Reached into his jacket. Pulled out a newspaper clipping, folded twice. Laid it on the table. Aurora didn’t touch it. “You read law, you said.” “I passed the bar.” “You never took the job.” “Didn’t want it.” “Didn’t want it, or couldn’t?” She turned the glass
slowly
. The condensation left a ring. Then another. “You trained me for more than fetching pints,” she said. “Training’s wasted if you don’t use it.” “I use it.” “Delivering dumplings?” “Delivering information.” He paused. “Who
to
?” “That’s not your concern.” “Everything
in
Soho is my concern.” “Not me.” “You walked out,” he said. “No word. No note. Just gone.” “You told me
to
go.” “I told you
to
run. Not disappear.” “I did both.” “You changed your name.” “Just the one I use.” *“Laila.”*
He tasted the name
. “Pretty. Disposable. But not yours.” Aurora flexed her left hand under the table. The scar on her wrist—pale crescent against darker skin—itched sometimes
in
the damp. “You still get it?” he asked. “Only when it rains.” “You ever see him?” “No.” “He’s looking.” Her fingers stilled. “Let him.” “He knows you’re
in
London.” “Good.” “He doesn’t know you’re here.” “Now he does.” Silas leaned back. A long
silence
, thick as
velvet
. “You used the delivery route
to
scout,” he said. “Observation’s easier on a bike.” “Cameras at the bank. The embassy. The old SOCTA building. You weren’t delivering.” “Maybe I was.” “You cycled past each three times on Tuesday. Left at different hours. Always looking up.” “Aurora Carter doesn’t exist,” she said. “But Rory does. And Rory delivers for Yu-Fei.” “And Laila? Who does she work for?” No answer. Silas exhaled. “You’re
in
deep.” “I’m not
in
anything.” “You don’t come back
to
a city like this unless you’re running *
to
* something.” “I came back for closure.” “There’s no closure here. Only unfinished business.” She looked at him then. Really looked. “You never went back either.” His jaw tightened. A
flicker
in
the hazel eyes. “Prague wasn’t my mission. It was my mistake.” “And you built a bar on top of it.” “And people come. Talk. Forget I’m listening.” “You’re still working.” “I’m retired.” “You’re still *
in
*.” A noise from the street. A car door slammed. Both of them turned. Habit. Aurora’s hand went
to
her hip. Not a weapon. Not visibly. But the angle, the
tension
—it was there. “You still carry?” “Always.” “Loaded?” “Wouldn’t make sense otherwise.” Silas watched her.
Then slowly, deliberately, opened his
coat. A small, black revolver nestled
in
a shoulder holster. Polish finish. Custom grip. “Yours,” he said. She didn’t reach for it. “Why keep it?” “Because one day, you’d come back. And one day, you’d need it.” “You thought I’d come back armed?” “I thought you’d come back unprepared. And that’s worse.”
She drained the rest of
her pint. Set the glass down hard enough
to
make it ring. “You think I ran.” “I think you survived.” “That’s generous.” “I’m not being generous. I’m stating fact.” “You didn’t come after me.” “I gave you what you needed.” “What? Silence?” “What you asked for.”
He reached into his pocket
. Pulled out a small SIM card. Not modern. Burner. Obsolete. “This arrived three weeks ago. Mailed from Belfast. No return. No stamp—hand-delivered
to
a postbox. Traced
to
a pub. The Harp. You were there
in
June.” Aurora said nothing. “It had one number on it,” he said. “Called it. Got a voicemail. Just a breath. Then a
whisper
.” He looked at her. *“Malphora.”* Her breath caught. Not much. Just a fraction. But it was there. “The name hasn’t been used
in
eight years,” he said. “Not since the safehouse burned. Not since the girl from Cardiff went off the grid.” She stood. “I should go.” “You don’t run from names, Rory. You run from what they mean.” “I’m not running.” “Then sit.” “I can’t.” “Because you’re afraid? Or because you’ve already decided?” She turned
to
the door. “Eva said you changed,” Silas said. “She was right.” “She said you don’t trust anyone.” “I trust myself.” “That enough?” She paused. Hand on the door latch. Outside, a siren wailed. Then stopped. The
silence
after was worse. “You left more than a city,” he said. “You left a family.” “I didn’t have one.” “You do.” The door opened. Wind rushed
in
. And then, a shadow
in
the corridor behind Silas. A
flicker
on the old CCTV monitor above the bar—three figures moving at the alley entrance. Too fast. Too quiet. Silas didn’t turn. But his hand moved. Under the table. Toward the revolver. Aurora stepped back inside. Locked the door. And
in
the dim green glow of the neon sign, whispered a single word: “Malphora.”
created_at
"2026-03-25T10:13:12.05Z"
3/25/2026, 10:13:12 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1669
moderation_latency
(null)
generation_time
70483
tokens_prompt
4618
tokens_completion
2313
native_tokens_prompt
4216
native_tokens_completion
1803
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00142518
router
(null)
provider_responses
0
endpoint_id
"cf186489-d252-4fb7-aca9-87ef7b557eff"
id
"c369fcabcb0c939e3503936475d47561"
is_byok
false
latency
1665
model_permaslug
"qwen/qwen3-235b-a22b-07-25"
provider_name
"Novita"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774433592-RhX5Ua15QQGmUFZQ2PoI"
upstream_id
"c369fcabcb0c939e3503936475d47561"
total_cost
0.00142518
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
17
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
121
tagDensity
0.14
leniency
0.281
rawRatio
0
effectiveRatio
0
76.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1250
totalAiIsmAdverbs
6
found
0
adverb
"truly"
count
1
1
adverb
"slightly"
count
1
2
adverb
"slowly"
count
2
3
adverb
"really"
count
1
4
adverb
"deliberately"
count
1
highlights
0
"truly"
1
"slightly"
2
"slowly"
3
"really"
4
"deliberately"
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)
44.00%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1250
totalAiIsms
14
found
0
word
"echoing"
count
1
1
word
"footsteps"
count
1
2
word
"weight"
count
1
3
word
"perfect"
count
1
4
word
"comfortable"
count
1
5
word
"silence"
count
3
6
word
"velvet"
count
1
7
word
"flicker"
count
2
8
word
"tension"
count
1
9
word
"traced"
count
1
10
word
"whisper"
count
1
highlights
0
"echoing"
1
"footsteps"
2
"weight"
3
"perfect"
4
"comfortable"
5
"silence"
6
"velvet"
7
"flicker"
8
"tension"
9
"traced"
10
"whisper"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"air was thick with"
count
1
highlights
0
"the air was thick with"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
134
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
134
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
238
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
28
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
5
markdownWords
5
totalWords
1240
ratio
0.004
matches
0
"clunk"
1
"“Laila.”"
2
"to"
3
"in"
4
"“Malphora.”"
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
25
unquotedAttributions
0
matches
(empty)
80.56%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
25
wordCount
648
uniqueNames
9
maxNameDensity
1.39
worstName
"Silas"
maxWindowNameDensity
2.5
worstWindowName
"Silas"
discoveredNames
Raven
1
Nest
1
Carter
1
Prague
1
Aurora
8
Golden
1
Empress
1
Silas
9
Pulled
2
persons
0
"Raven"
1
"Carter"
2
"Aurora"
3
"Silas"
4
"Pulled"
places
0
"Prague"
globalScore
0.806
windowScore
0.833
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
40
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
1240
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
238
matches
0
"let that hang"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
160
mean
7.75
std
7.79
cv
1.005
sampleLengths
0
21
1
24
2
32
3
48
4
2
5
36
6
3
7
36
8
4
9
4
10
3
11
5
12
30
13
6
14
4
15
7
16
7
17
16
18
4
19
20
20
1
21
6
22
24
23
5
24
6
25
4
26
6
27
2
28
9
29
11
30
3
31
3
32
16
33
9
34
4
35
1
36
6
37
3
38
5
39
5
40
8
41
6
42
20
43
4
44
5
45
4
46
5
47
3
48
5
49
12
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
134
matches
0
"was gone"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
117
matches
(empty)
82.83%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
8
semicolonCount
0
flaggedSentences
5
totalSentences
238
ratio
0.021
matches
0
"The same brass rail along the partition, tarnished now in patches where someone—probably her—had polished it during long, slow shifts."
1
"The jukebox—out of order for a decade—was gone."
2
"The scar on her wrist—pale crescent against darker skin—itched sometimes in the damp."
3
"But the angle, the tension—it was there."
4
"A flicker on the old CCTV monitor above the bar—three figures moving at the alley entrance."
91.05%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
657
adjectiveStacks
0
stackExamples
(empty)
adverbCount
33
adverbRatio
0.0502283105022831
lyAdverbCount
8
lyAdverbRatio
0.0121765601217656
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
238
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
238
mean
5.21
std
3.84
cv
0.737
sampleLengths
0
21
1
10
2
3
3
11
4
20
5
3
6
2
7
7
8
13
9
8
10
20
11
1
12
1
13
5
14
2
15
14
16
8
17
7
18
7
19
1
20
1
21
1
22
17
23
8
24
11
25
4
26
4
27
3
28
5
29
8
30
10
31
8
32
2
33
2
34
6
35
4
36
7
37
7
38
5
39
6
40
1
41
4
42
4
43
6
44
7
45
2
46
3
47
2
48
1
49
6
52.10%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
16
diversityRatio
0.35294117647058826
totalSentences
238
uniqueOpeners
84
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
3
totalSentences
88
matches
0
"Just a circle."
1
"Then slowly, deliberately, opened his"
2
"Just a fraction."
ratio
0.034
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
21
totalSentences
88
matches
0
"She twisted harder."
1
"She stepped in, boots echoing"
2
"His beard was fuller, the"
3
"He didn’t look surprised."
4
"She hadn’t taken it off"
5
"He lifted his right hand"
6
"He didn’t answer."
7
"She lifted the glass"
8
"He sat opposite."
9
"He studied her"
10
"She turned the glass slowly."
11
"He tasted the name"
12
"Her fingers stilled."
13
"She looked at him then."
14
"His jaw tightened."
15
"She didn’t reach for it."
16
"She drained the rest of"
17
"He reached into his pocket"
18
"He looked at her."
19
"Her breath caught."
ratio
0.239
100.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
60
totalSentences
88
matches
0
"The key turned in the"
1
"Aurora Carter paused, the cold"
2
"She twisted harder."
3
"The lock gave with a"
4
"She stepped in, boots echoing"
5
"The same cracked leather booth"
6
"The same brass rail along"
7
"A city that didn’t blink."
8
"The mirror behind the counter"
9
"The jukebox—out of order for"
10
"A raven, wings half-spread, eyes"
11
"Silas appeared from the corridor,"
12
"His beard was fuller, the"
13
"The limp heavier, like the"
14
"He didn’t look surprised."
15
"Aurora dropped her delivery bag"
16
"The weight of the insulated"
17
"She hadn’t taken it off"
18
"Silas set the glass down."
19
"He lifted his right hand"
ratio
0.682
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
88
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
15
technicalSentenceCount
0
matches
(empty)
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
17
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
13
fancyCount
0
fancyTags
(empty)
dialogueSentences
121
tagDensity
0.107
leniency
0.215
rawRatio
0
effectiveRatio
0
90.8847%