NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KK9QR1QFKS2GRWX2FJNHRKSB
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
3m 3s
Cost:
$0.119873
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
92.81%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
83.23%
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)
0.00%
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)
100.00%
Em-dash & semicolon overuse
(details)
94.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
44.21%
Sentence opener variety
(details)
0.00%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
0.00%
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)
83.8086%
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
Aurora caught the falling tumbler
by its rim, and the woman at the bar said, “Still doing that, then, Rory?”
The name struck harder than
the glass.
She set the tumbler upright
on the varnished wood and looked across the slosh of whisky.
Eva Morgan leaned one elbow
on the counter as if she had left it there last week and come back for it.
The old face still lived
in the new one, in the crooked half-smile and the direct stare, but time had cut away the rest.
Her hair, once a wild
red she'd fed with chemist dye and bad judgement, sat in a blunt brown line at her jaw.
A pale scar ran from
the corner of her mouth into her cheek, thin as a paper cut and twice as sharp. Her charcoal coat cost money.
Her hands held the glass
as if it might report her.
Silas glanced up from the
far end of the bar, polishing a highball with a white cloth.
His hazel eyes moved from
Aurora to Eva and back again. He said nothing.
He rarely wasted his voice
on the opening move. “You
look
different,” Aurora said.
Eva gave the room a
quick sweep, walls hung with old maps, black-and-white faces trapped behind glass, the green neon from the sign outside staining the bottles by the mirror. “That’s kind.” “It wasn’t meant kindly.” “That sounds more like you.”
Aurora rested both palms on
the counter.
The small crescent scar on
her left wrist caught the light.
Eva’s gaze dropped to it
and lifted again with that same quickness she used to have, the same habit of seeing damage and refusing to name it first. Silas set down the glass. “Friend of yours?” Eva looked at him. “Depends who’s writing the history.” Silas gave a short nod, as if that answered more than it should have. “If you two plan to use knives,” he said, “take the back room. The regulars hate surprises.” Aurora reached for the bottle of whisky on instinct, then stopped. Her hand hovered over it. Eva watched the hesitation and smiled without
warmth
. “I’m not here for a scene.” “You’re in Soho. That’s ambitious.” Silas moved down the bar with his slight limp, silver signet ring clicking once against the wood. “Back room,” he said. “Take the bottle. I’ll put any curious ears in the street.” Aurora took the whisky. Eva lifted her glass. Neither thanked him.
They followed him past the
shelves of spirits and framed photographs into the narrow aisle beside the bookcase. Silas pressed two fingers into the spine of a fat red volume. The shelf gave with a soft clunk and swung inward. Eva let out a quiet breath. “Subtle.” “He’s old,” Aurora said. “He likes props.” The room behind the shelf held a square table, four mismatched chairs, a green banker’s lamp and a smell of dust, paper and last week’s tobacco. No windows. No music from the bar, only the muffled thud of bass through plaster and the scrape of stool legs beyond the wall. Silas left them there and closed the shelf with a soft knock. Eva set down her drink and took off her coat. Under it she wore a black
silk
blouse buttoned to the throat. Aurora remembered band T-shirts, chipped nail varnish, cigarette burns in denim, a laugh you could hear across a car park. This woman looked pressed flat and ironed sharp. “You live above a pub now?” Eva said. Aurora sat opposite her. “You say that like I’ve disappointed a committee.” “You were meant to become terrifying in court.” “You were meant to set fire to Parliament.” “I got tired.” “That never stopped you before.” Eva looked down at her hands. No rings. A pale band at the base of one finger marked where one had sat for years or for show. Silence settled between them, not awkward, not easy, full of old furniture. Aurora poured two fingers into the spare glass and slid it across. “How many years?” she said. “You’re the one who left.” “You can still count.” “Eight.” Aurora took a drink. The whisky burned clean. “You
look
smaller,” Eva said. “The city takes rent in odd ways.” “It used to be your shoulders first. You’d walk into a room like you were cross-examining it.” Aurora laughed once. “You used to walk into rooms like they owed you money.” “They often did.” For a moment the old rhythm came back, easy as breath, two girls on a Cardiff seawall with chips wrapped in paper gone translucent with grease, making plans large enough to humiliate the future. It vanished at once. Eva reached for her glass and drank half of it in one swallow. “You vanished,” she said. Aurora watched her over the rim of her own glass. “That’s one word for it.” “It’s the correct one.” “I changed jobs. Flats. Numbers.” “I noticed.” “I thought you might.” Eva’s fingers tightened around the glass. “I sent six messages.” “I know.” “No, you don’t. If you knew, you’d have answered one.” Aurora looked at the lamp. Green light washed over the tabletop and made both their hands
look
drowned. “I had Evan looking for me,” she said. “He turned up at the restaurant once, asked the wrong people the right questions. I changed everything again.” “You could have sent one line.” “I could have.” “That was all.” Aurora lifted her eyes. “You want an apology, I owe you one. Several. I don’t have a clever version. I was ashamed, and I was frightened, and after a while
silence
turned into habit.” Eva
let that sit
.
Her mouth twitched at one
corner, not a smile, not contempt, something tired and old. “There she is,”
she said softly
. “The honest bit.” “You dragged me onto a train with one suitcase and a split lip. I thought honesty had earned a holiday.” “I dragged you because you rang me crying from a station toilet and said if I didn’t come you’d go back to him.” Aurora kept still. Eva leaned back. The chair creaked under her. “I told my mother I’d met a girl in London who had nowhere to go. She sent cash in an envelope and knitted you a scarf in a colour no human ought to wear. You slept on my sofa for three months. Then one morning I got up for work and found your key on the table.” “I remember.” “That made one of us.” Aurora held her stare. “I remember your sink full of plates. I remember the mould in the bathroom grout. I remember you stealing basil from the neighbour’s window box because you said pasta deserved effort. I remember you cutting my hair in your kitchen with fabric scissors.” Eva’s jaw loosened by a fraction. “I ruined it.” “It was already ruined.” “That was kind.” “It wasn’t meant kindly.” This time Eva smiled for real, and the scar in her cheek bent with it, turning the smile into something cut and stitched. Aurora saw the girl she had known, the one who once climbed the locked bell tower at St Mary Street on a dare and shouted down at traffic that God needed better security.
She had broken her ankle
on the way down.
She had laughed all through
casualty. That girl had not sat with her back to the wall and checked the door each time a floorboard shifted. “What happened to you?” Aurora asked. Eva swirled the whisky once and set it still. “I got
efficient
.” “That’s not an answer.” “It is where I work.” “And where’s that?” “An advisory firm.” Aurora stared. Eva gave a brief, dead sound. “There. That expression. I missed that expression.” “Advisory for whom?” “Men with newspapers at their throats. Companies with bodies under the carpet. Councillors with receipts. Wealthy husbands with regrettable appetites.” “You tidy up.” “I manage outcomes.” “That sounds expensive.” “It is.” Aurora sat back. “You used to throw paint at fur shops.” “I upgraded.” “To bleach.” Eva’s gaze did not shift. “You think I don’t hear it when I talk? I hear every polished little coffin nail. I know what I sound like.” “Then why do it?” “Because rent arrives every month. Because dignity does not pay tax. Because after Mam got ill, the bills came faster than principles.” That landed between them with a dull
weight
. Aurora put down her glass. “Your mother was ill?” Eva looked at her for the first time as if she might
truly
not know. “Yes.” “When?” “Three years after you left.” Aurora felt her face change. Eva watched it happen. “I sent those messages from hospital.” The room shrank. Aurora’s fingers curled against the table edge. “What was it?” “Ovarian. Ugly. Quick at the end. Slow until then, just to keep things tasteful.” “Eva.” “She died on a Tuesday. You used to hate Tuesdays.” Aurora closed her eyes once, opened them. “I’m sorry.” “I know.” “No, I mean it.” “I know that as well.” The kindness in it hurt more than anger would have. Eva stood, crossed to the shelf-lined wall and ran one finger over the spine of a book without seeing it. “You weren’t the only one who changed numbers,” she said. “After the funeral I stopped speaking to half the city. Cardiff shrank. Everyone knew what flowers were sent, who cried, who didn’t. Grief turns people into accountants.” “You should have told me.” Eva turned. “I did.” Aurora had no answer. The green lamp hummed. From the other side of the shelf came a burst of laughter, then the muted clink of bottles. Life went on out there, bright and stupid and thirsty. In here, the air thickened. Aurora rose and moved to the table again. “And the scar?” Eva touched her cheek, almost absent. “Broken glass.” Aurora waited. Eva let out a slow breath. “A client’s wife threw a tumbler. She had excellent aim.” “You stayed?” “It was my flat.” Aurora looked at the pale ring mark on her finger, the precise blouse, the careful hair, the way she stood with her
weight
balanced for a blow. “He was yours.” Eva’s mouth flattened. “For four years.” Aurora felt something old and ugly stir, not jealousy, not judgement, something closer to recognition. “And now?” “Now he’s somebody else’s cautionary tale.” “You left.” “He left first, in all the ways that matter.” Aurora pulled the bottle closer and poured again. “You’ve got a talent,” she said. “For rescuing wrecks and moving into their ruins.” Eva barked a laugh and took the fresh glass. “That’s rich, coming from the woman who lives above a spy’s pub and calls it stability.” They drank. The whisky softened nothing. After a while Eva said, “I saw him.” Aurora looked up. “Who?” “Evan.”
Her fingers tightened around the
glass so fast the base clicked against the wood. “When?” “Last week.” The room lost its edges. Aurora kept her voice flat. “Where?” “In a conference room in Mayfair. He came in with a solicitor and a watch that cost more than my first car. He’d aged well. Men like that often do. Somebody else carries the damage for them.” Aurora heard the blood in her ears. “What was he doing there?” Eva held her stare. “He hired the firm.” “For what?” “For what men like him always want. Restraint. Discretion. Narrative. A woman in Bristol said his name in print. Another one in Leeds spoke to the police. He wanted us to make the word allegation feel dirty.” Aurora did not move. “He recognised me after ten minutes,” Eva said. “Not my name. My face. Cardiff wasn’t a large world. He asked if I still knew you.” “And?” “I said no.” Aurora gave one hard nod. “He didn’t believe me.” The shelf door opened. Silas slipped into the room and shut it behind him.
He did not waste time
on apology or preamble.
His limp showed more when
he moved
quickly
. The silver ring on his right hand flashed once in the green light. “You’ve got company,” he said. Eva went still. “One blond man,” Silas said. “Expensive coat, provincial shoes. Two others outside under the sign. The blond one asked for a woman in charcoal and called her Eva. Then he asked if Aurora Carter worked here.” Aurora was already on her feet. Silas looked at the bottle, then at the two untouched chairs, then back at them. “If either of you intends to lie to me,” he said, “do it while walking.”
created_at
"2026-03-09T16:44:06.784Z"
3/9/2026, 4:44:06 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
115281
moderation_latency
(null)
generation_time
182645
tokens_prompt
4618
tokens_completion
3559
native_tokens_prompt
4131
native_tokens_completion
7303
native_tokens_completion_images
0
native_tokens_reasoning
4641
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
"completed"
usage
0.1198725
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0fc7382ecf1cbaee0169aef8d6e9188193a2184dd32c8d4545"
is_byok
false
latency
279
model_permaslug
"openai/gpt-5.4-20260305"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773074646-S7j80XFb1W18JDga4TnF"
upstream_id
"resp_0fc7382ecf1cbaee0169aef8d6e9188193a2184dd32c8d4545"
total_cost
0.1198725
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
19
adverbTagCount
1
adverbTags
0
"she said softly [softly]"
dialogueSentences
127
tagDensity
0.15
leniency
0.299
rawRatio
0.053
effectiveRatio
0.016
92.81%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2087
totalAiIsmAdverbs
3
found
0
adverb
"softly"
count
1
1
adverb
"truly"
count
1
2
adverb
"quickly"
count
1
highlights
0
"softly"
1
"truly"
2
"quickly"
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)
83.23%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2087
totalAiIsms
7
found
0
word
"warmth"
count
1
1
word
"silk"
count
1
2
word
"silence"
count
2
3
word
"efficient"
count
1
4
word
"weight"
count
2
highlights
0
"warmth"
1
"silk"
2
"silence"
3
"efficient"
4
"weight"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
0
maxInWindow
0
found
(empty)
highlights
(empty)
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
134
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
0
narrationSentences
134
filterMatches
0
"look"
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
242
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
57
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2087
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
32
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
85
wordCount
1177
uniqueNames
9
maxNameDensity
3.14
worstName
"Aurora"
maxWindowNameDensity
5.5
worstWindowName
"Aurora"
discoveredNames
Morgan
1
Aurora
37
Eva
33
Cardiff
1
St
1
Mary
1
Street
1
God
1
Silas
9
persons
0
"Morgan"
1
"Aurora"
2
"Eva"
3
"God"
4
"Silas"
places
0
"Cardiff"
1
"St"
2
"Mary"
3
"Street"
globalScore
0
windowScore
0
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
71
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
2087
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
242
matches
0
"let that sit"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
170
mean
12.28
std
15.66
cv
1.276
sampleLengths
0
20
1
23
2
107
3
40
4
5
5
30
6
2
7
4
8
5
9
46
10
5
11
3
12
4
13
5
14
14
15
17
16
24
17
6
18
5
19
17
20
15
21
51
22
6
23
1
24
7
25
62
26
50
27
8
28
12
29
8
30
8
31
3
32
5
33
27
34
24
35
5
36
5
37
4
38
1
39
8
40
5
41
7
42
17
43
14
44
3
45
51
46
4
47
15
48
4
49
5
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
134
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
206
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
242
ratio
0
matches
(empty)
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1181
adjectiveStacks
1
stackExamples
0
"slight limp, silver signet"
adverbCount
34
adverbRatio
0.028789161727349702
lyAdverbCount
6
lyAdverbRatio
0.005080440304826418
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
242
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
242
mean
8.62
std
8.32
cv
0.964
sampleLengths
0
20
1
7
2
16
3
22
4
24
5
23
6
22
7
5
8
11
9
17
10
11
11
3
12
9
13
5
14
30
15
2
16
4
17
5
18
7
19
11
20
28
21
5
22
3
23
4
24
5
25
14
26
17
27
11
28
5
29
8
30
6
31
5
32
17
33
4
34
11
35
4
36
4
37
3
38
18
39
12
40
10
41
6
42
1
43
4
44
3
45
26
46
2
47
22
48
12
49
10
44.21%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
14
diversityRatio
0.23140495867768596
totalSentences
242
uniqueOpeners
56
0.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
0
totalSentences
112
matches
(empty)
ratio
0
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
17
totalSentences
112
matches
0
"She set the tumbler upright"
1
"Her hair, once a wild"
2
"Her charcoal coat cost money."
3
"Her hands held the glass"
4
"His hazel eyes moved from"
5
"He said nothing."
6
"He rarely wasted his voice"
7
"Her hand hovered over it."
8
"They followed him past the"
9
"It vanished at once."
10
"Her mouth twitched at one"
11
"she said softly"
12
"She had broken her ankle"
13
"She had laughed all through"
14
"Her fingers tightened around the"
15
"He did not waste time"
16
"His limp showed more when"
ratio
0.152
0.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
104
totalSentences
112
matches
0
"Aurora caught the falling tumbler"
1
"The name struck harder than"
2
"She set the tumbler upright"
3
"Eva Morgan leaned one elbow"
4
"The old face still lived"
5
"Her hair, once a wild"
6
"A pale scar ran from"
7
"Her charcoal coat cost money."
8
"Her hands held the glass"
9
"Silas glanced up from the"
10
"His hazel eyes moved from"
11
"He said nothing."
12
"He rarely wasted his voice"
13
"Eva gave the room a"
14
"Aurora rested both palms on"
15
"The small crescent scar on"
16
"Eva’s gaze dropped to it"
17
"Silas set down the glass."
18
"Eva looked at him."
19
"Silas gave a short nod,"
ratio
0.929
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
112
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
45
technicalSentenceCount
1
matches
0
"Her hands held the glass as if it might report her."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
19
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
18
fancyCount
0
fancyTags
(empty)
dialogueSentences
127
tagDensity
0.142
leniency
0.283
rawRatio
0
effectiveRatio
0
83.8086%