NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHTX1T9YHH81PPM2V2NFMC33
Run Details
Model:
DeepSeek V3.2
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
1m 22s
Cost:
$0.002030
Provider:
Novita
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
87.48%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
62.43%
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)
50.00%
Name drop frequency
(details)
23.42%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
100.00%
Paragraph length variance
(details)
99.42%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
82.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
52.26%
Sentence opener variety
(details)
59.00%
Adverb-first sentence starts
(details)
64.25%
Pronoun-first sentence starts
(details)
0.00%
Subject-first sentence starts
(details)
88.50%
Subordinate conjunction sentence starts
(details)
91.84%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
82.0193%
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 blood on the floor
was black in the low light.
Rory wiped her damp palms
on her jeans and aimed the nozzle of the heavy-duty degreaser at the dark patch by the back door of The Raven’s Nest.
Silas had muttered something about
a supplier with poor timing and a cut forehead.
Her job, as the new
live-in tenant above the bar, was to make things disappear before the evening crowd trickled in.
The chemical smell burned her
nose, a sharp, citrusy lie that couldn’t
quite mask the copper undertone of the real mess
.
She was scrubbing the last
of it into the worn floorboards when the front bell chimed, too early for the regulars.
She didn't look up until
she heard Silas’s voice, its usual dry calm replaced by a strange, hollow note. “Christ.”
Rory straightened, the stiff brush
still in her hand.
A man stood just inside
the door, haloed by the afternoon light from the street. Tall, broad-shouldered, wearing a beautifully cut charcoal suit that screamed money, not Soho. His hair, once a sandy, sun-bleached mess, was now a neat, expensively groomed sweep of dark blonde. But the eyes were the same.
A bright, unsettling green that
had always seen too much. Evan. “Silas,”
Evan said, his voice smooth, polished
.
A different accent layered over
the Welsh valleys of their childhood. “Been a long time.”
Rory’s grip on the brush
handle tightened.
The small, crescent-shaped scar on
her left wrist itched, a phantom pain from a different lifetime.
She’d fallen from a tree
in his garden when she was nine.
He’d carried her home, his
scrawny arms shaking with the effort.
Silas moved from behind the
bar, his slight limp more pronounced.
He positioned himself between Rory
and the door, a deliberate, quiet barrier. “Evan. Didn’t expect to see you here.” “Business in town. Thought I’d look up some old ghosts.” Evan’s gaze slid past Silas, landing on Rory. The recognition was instant, but there was no
warmth
in it. Just a slow, appraising scan, from her scuffed trainers to her grease-stained t-shirt. “Aurora Carter. Scrubbing floors.” “Rory,”
she corrected, her own voice
flat.
She dropped the brush into
the bucket with a dull clunk. “And it’s a living.” “I heard you’d moved to London. Didn’t picture this.”
He took a step further
in, his Oxfords silent on the clean wood. The suit was Italian. She knew the look.
Her father had aspired to
it. “Pictures lie,”
Silas said, his tone a low warning
. “What do you want, Evan?” “A drink, for old times’ sake? You still keep that Macallan behind the map of Prague?” Silas didn’t move. The mention of Prague
hung in the air
, a shared history Rory wasn’t part of. Evan had always been Silas’s godson, a connection that had
felt like a privilege back then
.
Now it felt like a
threat. “The stock’s changed,” Silas said finally.
He walked, slowly, back behind
the bar. A dismissal, but Evan didn’t take it.
He pulled out a stool
and sat, his movements precise, controlled.
He’d learned how to occupy
space. Rory stayed by the back door, a statue in the shadows.
Her mind raced, a frantic
tick-tock of old fears and new calculations. Cardiff
was supposed
to be a closed book. Evan was a chapter she’d torn out and burned. Silas placed a glass of amber liquid in front of Evan. No ice. Evan swirled it, sniffed. A connoisseur’s gesture. He took a sip. “You’ve done well for yourself,” Silas observed, leaning on the bar. “Consulting. Private equity. Boring stuff,
really
. Pays for the suits.” Another glance at Rory. “You look well, Rory.” “You don’t,” she said. A
flicker
in those green eyes. Amusement, or annoyance?
It was hard to tell
now. The boy who’d laughed until he cried
was buried
under this veneer. “London’s taught you bluntness.” “Cardiff taught me that. I just forgot for a while.” The
silence
stretched. The neon from the sign outside bled a sickly green through the window, painting Evan’s profile in an alien glow. “How’s your father?” Evan asked, too casually. “Fine.” “Still fighting the good fight in court?” “Someone has to.” “And your mother? Still teaching the brats of Roath how to spell?” “Retired.” “Ah.”
He took another sip
. “Time marches on.” “It marches right over some people,” Rory said.
She finally moved, walking to
the bar but keeping a stool between them. She could smell his cologne. Something woody, expensive. It made her
think
of boardrooms and lies. “Why are you
really
here, Evan? This isn’t a social call. You don’t do social.” He smiled, a thin, practised stretch of lips. “Can’t a man visit his old haunts? See old friends?” “We weren’t friends.” The smile didn’t falter. “Weren’t we? Felt like it once. Felt like a lot of things once.” His gaze dropped to her left hand, resting on the bar. To the bare finger. “I heard about the engagement. Or the lack of one.” Her
stomach
twisted. He’d heard. Of course he’d heard. The Carter family gossip network was a relentless, one-way river flowing straight to anyone who’d ever known them. “News travels.” “To those who listen.” He set his glass down, the
crystal
tapping a sharp note on the wood. “He wasn’t right for you. A barrister’s son with a gambling problem. Predictable.” “And what’s the alternative? A consultant in a five-thousand-pound suit who thinks a visit constitutes an ambush?” Silas cleared his throat. A low sound, like stone grinding on stone. “Evan. Enough.” Evan held up a placating hand, the silver of a watch
glinting
at his cuff. A Patek Philippe. Her father had a poster of one in his study. “I’m just catching up, Silas. It’s been, what, five years? Six?” “Seven,” Rory said. “Since the summer before I left for university. You came to the house. You borrowed fifty pounds from my dad and never paid it back.” “I sent a cheque.” “It bounced.” He had the grace to look faintly embarrassed, a ghost of the boy he’d been breaking through. “Cash flow was tight. I’ve since made rather more substantial reparations to your family. Quiet investments. Your father’s never been good with risk.” The air left the room. Rory stared at him. “You did what?” “The firm needed shoring up. Brendan was too proud to ask. I had the means. Consider it… an apology. For a lot of things.” An apology. Wired into a bank account. The
weight
of it, the sheer, arrogant presumption, pressed down on her. He’d bought his way back into the narrative of her life without even being in the room. Her father had never mentioned it. The shame of it would have choked him. “You had no right,”
she whispered, the words scraped raw
. “I had every right,” he said, and for the first time, the polish cracked. Something harder, colder, showed through. “You left. You cut everyone off. You changed your number, you moved here, you started scrubbing floors. Someone had to look out for them.” “I didn’t ask you to.” “You never asked for anything. That was always the problem.” He finished his drink, pushed the glass away. “You just endured. Until you couldn’t, and then you ran.” The truth of it was a physical blow. She had run. From Cardiff, from the law degree, from the suffocating expectation, from the ghost of him that still lingered in every
familiar
street. She’d run to London and buried herself in anonymous work and the dusty flat above a spy’s bar. “What do you want?”
she asked again, her voice steadier now, forged in a sudden, clear anger
. Evan stood, straightening his suit jacket. He looked at Silas, then back at her. “There’s a position. At my firm. Research analyst. It’s beneath you, frankly, but it’s a start. It pays ten times what you make delivering noodles and cleaning blood off floors.” Silas went
very
still. “How did you know about the blood, Evan?” Evan’s eyes
flicked
to the damp patch by the back door, then back to Silas. A slow, knowing smile. “Lucky guess. This is Soho, after all.” He pulled a crisp, white business card from his breast pocket and placed it on the bar. It sat there, a tiny,
perfect
rectangle of condemnation. “Think about it, Rory. Your brain was always your best feature. Wasting it here is a tragedy.” He nodded to Silas. “Always a pleasure, godfather. We should do this more often.” He turned and walked out, the door swinging shut behind him with a soft sigh. The green neon buzzed. Rory looked at the card. *
Evan Rhys, Managing Director, Rhys & Locke Advisory
*. An address in Mayfair. Silas picked up the empty glass, his knuckles white around it. “He’s been watching you.” “I know.” “The money for your father… that wasn’t an apology. It was a down payment.” She picked up the card. The stock was thick, creamy. It would tear cleanly. “What do I do?” Silas looked at her, his hazel eyes old and tired. “That’s the question, isn’t it? You can take his offer and walk into a gilded cage. Or you can stay here and keep scrubbing away the messes other people make.”
He paused, his gaze drifting to the hidden door behind the bookshelf
. “But know this, Rory. Men like Evan… they don’t make offers. They make acquisitions.” Outside, a black sedan she hadn’t noticed before pulled away from the kerb. The card in her hand
felt like a trigger
.
created_at
"2026-02-19T12:12:31.654Z"
2/19/2026, 12:12:31 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1539
moderation_latency
(null)
generation_time
81786
tokens_prompt
4618
tokens_completion
2510
native_tokens_prompt
4209
native_tokens_completion
2245
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
0.002030221
router
(null)
provider_responses
0
endpoint_id
"8a5fb6d3-ef71-4958-af54-269ffa3a3c6e"
id
"0e7d7c046dc420202009fc7dc104b3a4"
is_byok
false
latency
1539
model_permaslug
"deepseek/deepseek-v3.2-20251201"
provider_name
"Novita"
status
200
api_type
"completions"
id
"gen-1771503151-mBCiHLcrNhQ1xmEMwfeo"
upstream_id
"0e7d7c046dc420202009fc7dc104b3a4"
total_cost
0.002030221
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
21
adverbTagCount
2
adverbTags
0
"Silas said finally [finally]"
1
"she asked again [again]"
dialogueSentences
64
tagDensity
0.328
leniency
0.656
rawRatio
0.095
effectiveRatio
0.063
87.48%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1597
totalAiIsmAdverbs
4
found
0
adverb
"slowly"
count
1
1
adverb
"really"
count
2
2
adverb
"very"
count
1
highlights
0
"slowly"
1
"really"
2
"very"
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)
62.43%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1597
totalAiIsms
12
found
0
word
"warmth"
count
1
1
word
"raced"
count
1
2
word
"flicker"
count
1
3
word
"silence"
count
1
4
word
"stomach"
count
1
5
word
"crystal"
count
1
6
word
"predictable"
count
1
7
word
"glinting"
count
1
8
word
"weight"
count
1
9
word
"familiar"
count
1
10
word
"flicked"
count
1
11
word
"perfect"
count
1
highlights
0
"warmth"
1
"raced"
2
"flicker"
3
"silence"
4
"stomach"
5
"crystal"
6
"predictable"
7
"glinting"
8
"weight"
9
"familiar"
10
"flicked"
11
"perfect"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"hung in the air"
count
1
highlights
0
"hung in the air"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
120
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
0
narrationSentences
120
filterMatches
0
"think"
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
162
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
42
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
1
markdownWords
8
totalWords
1587
ratio
0.005
matches
0
"Evan Rhys, Managing Director, Rhys & Locke Advisory"
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
16
unquotedAttributions
0
matches
(empty)
50.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
62
wordCount
1065
uniqueNames
20
maxNameDensity
1.6
worstName
"Silas"
maxWindowNameDensity
3.5
worstWindowName
"Evan"
discoveredNames
Raven
1
Nest
1
Silas
17
Soho
1
Welsh
1
Rory
12
Oxfords
1
Italian
1
Prague
1
Evan
14
Carter
1
Patek
1
Philippe
1
Cardiff
2
London
1
Rhys
2
Managing
1
Director
1
Locke
1
Mayfair
1
persons
0
"Raven"
1
"Silas"
2
"Rory"
3
"Evan"
4
"Carter"
5
"Patek"
6
"Philippe"
7
"Rhys"
places
0
"Soho"
1
"Prague"
2
"Cardiff"
3
"London"
4
"Mayfair"
globalScore
0.702
windowScore
0.5
23.42%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
79
glossingSentenceCount
4
matches
0
"quite mask the copper undertone of the real mess"
1
"felt like a privilege back then"
2
"felt like a threat"
3
"felt like a trigger"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1587
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
162
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
65
mean
24.42
std
18.05
cv
0.739
sampleLengths
0
11
1
84
2
40
3
1
4
9
5
62
6
22
7
46
8
30
9
46
10
22
11
36
12
14
13
16
14
40
15
37
16
40
17
24
18
11
19
18
20
4
21
31
22
10
23
23
24
7
25
1
26
7
27
3
28
12
29
1
30
8
31
52
32
18
33
3
34
42
35
29
36
31
37
17
38
14
39
39
40
28
41
4
42
2
43
40
44
12
45
24
46
50
47
10
48
43
49
5
99.42%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
2
totalSentences
120
matches
0
"was supposed"
1
"was buried"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
1
totalVerbs
165
matches
0
"was scrubbing"
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
162
ratio
0
matches
(empty)
82.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1073
adjectiveStacks
3
stackExamples
0
"new live-in tenant"
1
"sandy, sun-bleached mess,"
2
"small, crescent-shaped scar"
adverbCount
37
adverbRatio
0.034482758620689655
lyAdverbCount
11
lyAdverbRatio
0.010251630941286114
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
162
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
162
mean
9.8
std
6.85
cv
0.699
sampleLengths
0
11
1
28
2
14
3
21
4
21
5
21
6
19
7
1
8
9
9
15
10
13
11
17
12
6
13
10
14
1
15
7
16
11
17
4
18
7
19
16
20
12
21
11
22
11
23
12
24
7
25
18
26
11
27
13
28
4
29
7
30
11
31
4
32
22
33
4
34
4
35
6
36
9
37
5
38
16
39
3
40
15
41
16
42
6
43
6
44
7
45
7
46
11
47
6
48
11
49
12
52.26%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
7
diversityRatio
0.3395061728395062
totalSentences
162
uniqueOpeners
55
59.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
2
totalSentences
113
matches
0
"Just a slow, appraising scan,"
1
"Of course he’d heard."
ratio
0.018
64.25%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
44
totalSentences
113
matches
0
"Her job, as the new"
1
"She was scrubbing the last"
2
"She didn't look up until"
3
"His hair, once a sandy,"
4
"She’d fallen from a tree"
5
"He’d carried her home, his"
6
"He positioned himself between Rory"
7
"she corrected, her own voice"
8
"She dropped the brush into"
9
"He took a step further"
10
"She knew the look."
11
"Her father had aspired to"
12
"He walked, slowly, back behind"
13
"He pulled out a stool"
14
"He’d learned how to occupy"
15
"Her mind raced, a frantic"
16
"He took a sip."
17
"It was hard to tell"
18
"He took another sip"
19
"She finally moved, walking to"
ratio
0.389
0.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
104
totalSentences
113
matches
0
"The blood on the floor"
1
"Rory wiped her damp palms"
2
"Silas had muttered something about"
3
"Her job, as the new"
4
"The chemical smell burned her"
5
"She was scrubbing the last"
6
"She didn't look up until"
7
"Rory straightened, the stiff brush"
8
"A man stood just inside"
9
"His hair, once a sandy,"
10
"A bright, unsettling green that"
11
"Evan said, his voice smooth,"
12
"A different accent layered over"
13
"Rory’s grip on the brush"
14
"The small, crescent-shaped scar on"
15
"She’d fallen from a tree"
16
"He’d carried her home, his"
17
"Silas moved from behind the"
18
"He positioned himself between Rory"
19
"Evan’s gaze slid past Silas,"
ratio
0.92
88.50%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
2
totalSentences
113
matches
0
"Now it felt like a"
1
"To the bare finger."
ratio
0.018
91.84%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
42
technicalSentenceCount
3
matches
0
"The chemical smell burned her nose, a sharp, citrusy lie that couldn’t quite mask the copper undertone of the real mess."
1
"Tall, broad-shouldered, wearing a beautifully cut charcoal suit that screamed money, not Soho."
2
"The Carter family gossip network was a relentless, one-way river flowing straight to anyone who’d ever known them."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
21
uselessAdditionCount
8
matches
0
"Evan said, his voice smooth, polished"
1
"she corrected, her own voice flat"
2
"He took, his Oxfords silent on the clean wood"
3
"Silas said, his tone a low warning"
4
"He set, the crystal tapping a sharp note on the wood"
5
"she whispered, the words scraped raw"
6
"she asked again, her voice steadier now, forged in a sudden, clear anger"
7
"He paused, his gaze drifting to the hidden door behind the bookshelf"
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
12
fancyCount
3
fancyTags
0
"she corrected (correct)"
1
"Silas observed (observe)"
2
"she whispered (whisper)"
dialogueSentences
64
tagDensity
0.188
leniency
0.375
rawRatio
0.25
effectiveRatio
0.094
82.0193%