NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KKACDSDQQ1B2ADDZHYZVMPGC
Run Details
Model:
GPT-5.4 (Reasoning, Low)
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
1m 28s
Cost:
$0.062723
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
100.00%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
77.16%
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)
100.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
42.86%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
50.36%
Subject-first sentence starts
(details)
30.12%
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)
90.0166%
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 nearly dropped the tray
when she heard the laugh.
It came from the far
end of the bar, cut through the clink of glasses and the low hum of Friday thirst, and struck some old wire deep in her chest. Not loud. Not theatrical.
Just a short, breathy laugh
that used to mean trouble in school corridors, railway stations, borrowed kitchens, any place where two girls with more nerve than money decided the world would have to bend.
She set the tray down
before her hands betrayed her. “Rory?”
The name landed harder than
the laugh. Aurora turned. For a blink she saw the old shape of her, all sharp cheekbones and bright dare, but time had gone at Eva with a patient knife.
Her hair, once a wild
copper cloud, hung in a sleek pale bob that stopped at her jaw.
Her face looked thinner, expensive
in a brittle way, as if somebody had paid to polish what grief had hollowed out.
A cream silk blouse vanished
beneath a dark tailored coat. The coat hung open. One cuff
was torn
. Aurora stared. Eva smiled first. It
wavered
, then held. “Well. That’s rude. I know London ruins people, but I thought you’d still recognise me.”
Aurora found her voice in
pieces. “Eva.” “There she is.”
The bar pressed on around
them. Someone called for another lager. A stool scraped. Behind Aurora, shelves glowed with amber and green glass.
The Raven’s Nest swallowed secrets
for a living. Old maps yellowed on the walls. Black-and-white faces watched from their frames. Near the till, a candle guttered in a red jar and gave the room a waxy smell beneath beer, citrus peel, and the faint medicinal sting of spilled gin.
Silas looked up from the
far end where he polished tumblers with the slow air of a priest cleaning relics.
His hazel eyes moved from
Aurora’s face to the woman at the bar and stayed there a second too long. “A friend?” he said. Eva’s gaze
flicked
to him.
She measured the limp, the
ring, the posture that said doorman, diplomat, and executioner in equal parts. Aurora nodded. “An old one.” “Those are the dangerous sort.”
Silas set the tumbler down
. “House rules still apply.” Eva smiled at him, though the smile had no softness in it. “I was hoping for a drink, not absolution.” “That costs extra.” For the first time, real amusement lit her face.
It made Aurora’s stomach turn
with memory. Cardiff station at sixteen. Eva stealing chips off her tray and talking their way out of trouble with a guard she’d nearly kicked. A summer bus ride to Barry Island with wet swimsuits in a plastic bag. A shared bedsit years later, London not yet cruel, both of them swearing they would never become women who apologised for taking up room.
Then Eva vanished from her
life in a series of missed calls, thin excuses, and one final text that read Sorry. Need to sort my head. Don’t wait up. After that, nothing. Aurora wiped her hands on a bar towel she did not need. “What are you drinking?” “Whisky.” “You used to hate whisky.” “I used to be seventeen.” Silas poured without asking which bottle.
He chose a peaty one
and set it down in front of Eva.
She lifted the glass, held
it under her nose, and drank like she had learned the cost of hesitation. Aurora watched her throat move. “When did you get back in touch with civilisation?” “Tonight, apparently.” “That’s not an answer.” Eva rolled the glass between her fingers. Her nails were short, bare, bitten at the edges. That
unsettled
Aurora more than the torn cuff. Eva had once treated her hands like a manifesto. “I’ve been in and out,” Eva said. “Mostly out.” “Of London?” “Of most things.” Silas moved closer, still drying glasses. “You want the back room for this reunion?” “No,” Aurora said too fast. Eva’s eyes slid to the bookshelf that hid the door. A brief pause. A note taken. “We’re all right here,” Aurora said. Silas gave one small nod that meant, You’re wrong, but I’ll let you prove it.
He drifted away, though not
far. Aurora leaned against the bar. “You look different.” “So do you.” “Do I?” “You used to wear your temper on your face. Now you tuck it away and send it out with the menus.” Aurora almost laughed. “And you used to dye your hair with supermarket box colour and call it rebellion.” “It was rebellion.” “It was auburn gone feral.” Eva
traced
the rim of the glass. “You kept the black.” “It suits my mood.” “It always did.” The line might have turned light in another mouth. In Eva’s it carried too much history. Aurora knew what she looked like now, the black shirt, black jeans, sleeves rolled to the elbows, scar pale against her left wrist when she reached for bottles. Customers liked her because she stayed calm when drunks wanted theatre. Silas liked her because she noticed exits, hands, lies. None of that had anything to do with the girl who left Cardiff with one suitcase, a split lip, and a phone number memorised in case Evan smashed the handset again. Eva had
known that girl
. Aurora set a coaster between two fresh pints and pushed them down the bar to waiting hands. When she came back, Eva still watched her. “You look well,” Eva said. Aurora arched a brow. “You’re worse at lying.” “I’m better, usually.” That word sat between them, heavy and polished. Usually. Usually where? Usually with whom? Aurora glanced at the torn cuff again. There was a rust-coloured mark near the seam. Not wine. Not lipstick. “You going to tell me why you disappeared?” Eva looked into the whisky. “Straight in, then.” “It’s been years.” “Yes.” “You don’t get to show up in my bar looking like a woman who has either inherited a fortune or buried one and expect small talk.” A customer laughed too loudly behind them. A dart hit cork with a dry thud.
Somewhere near the door, a
couple began the hushed, vicious kind of argument people mistake for manners. Eva ran a thumb over the torn cuff. “I owed people. Not money at first. Favours. Then money. Then more than money.” “You could have called.” “And said what? Hello, Rory. Sorry I missed your birthday and the rest of your twenties. I’m in trouble again. Fancy making it your problem?” “You don’t get to decide that for me.” “I already did.” Aurora looked away before the answer on her face turned raw. She reached for a bottle, realised no one had ordered, and put it back. “You were good at that,” she said. “Making choices for both of us.” Eva gave a short laugh that held no pleasure. “You remember the caravan in Tenby?” Aurora did. God, she did. A stolen weekend at nineteen. Rain drumming the roof. A hot plate that worked when kicked. Eva
dancing
barefoot on cracked linoleum, singing into a wooden spoon. They had almost no money.
They had chips wrapped in
paper, a cheap red blanket, and the obscene conviction that freedom could be assembled from scraps. “You sold my coat for train fare,” Aurora said. “You still mention that.” “It was a good coat.” “It was hideous.” “It was warm.” “It was camel.” Aurora folded her arms. “So the years have sharpened your taste and wrecked your timing.” Eva smiled. It vanished at once. “I thought if I cut clean, I might stop dragging you into the same mess.” “You didn’t cut clean. You vanished.” “Yes.” “You let me think I’d done something.” “Rory.” “What?” Eva lifted her gaze. For the first time there was no wit, no lacquer, no elegant dodge. Just fatigue laid bare. “You had done something. You had got out.” Aurora went still. The room
seemed to
pull back from them. Sound blurred at the edges. She saw, with horrible clarity, the old bedsit in Camden, the kettle furred white from hard water, Eva on the windowsill with a cigarette she never finished, staring down into the alley while Aurora packed a bag to leave Evan for good. Eva had said, Go now. Before he gets charming again. Aurora had gone. Eva had stayed behind with men she called acquaintances and jobs she called temporary and a smile she used like a lockpick. “That wasn’t your sentence,” Aurora said. Eva gave one soft shrug. “I had a talent for bad doors.” “You had a talent for walking through them and dragging the hinges behind you.” “There she is.” Eva tipped back the rest of her whisky. “I missed that.” “You missed a lot.” A line formed at the bar. Aurora served two rounds on instinct, hands steady while her
pulse
struck hard.
She pulled a pint, took
cash, made change, all without looking at Eva, though she felt her there like an old bruise. When she returned, Silas had replaced the empty whisky with a fresh pour. “I didn’t order that,” Eva said. “I did,” Silas said. She looked at him. “You always buy drinks for women with damaged cuffs?” “Only the ones mapping exits.” Eva held his gaze, then took the glass. “You’re not just a barman.” “No.” “What are you, then?” “Retired.” Aurora almost smiled. Eva did not. Silas rested both palms on the bar. “Who’s looking for you?” Direct. Flat. A blade, not a question. Eva exhaled through her nose. “You do run an interesting place.” “That wasn’t an answer.” Aurora turned to her. “Eva.” “No surnames in here,” Silas said. Eva nodded once, as if that confirmed something unpleasant. “Two men. Perhaps three by now. One talks too much. One doesn’t talk at all. The quiet one worries me.” “Why are they looking?” Aurora asked. “I have something.” “Money?” Eva laughed without humour. “If it were money, I’d have spent it.” Silas’s ring tapped the wood once. “What?” Eva reached inside her coat. Aurora’s body tightened before her mind caught up. Silas moved faster than his knee should have let him, one hand already below the bar where he kept things that did not go on menus. Eva froze with her hand inside the coat and lifted her brows. “Relax. If I’d meant to make a scene, I’d have chosen somewhere with better champagne.” “Hands where I can see them,” Silas said. Eva drew out a small black key wrapped in a strip of blue tape. Aurora stared. It looked ordinary. Cheap. Plastic head, metal blade, nothing to mark it except the tape. “It opens a deposit box,” Eva said. “At a bank?” Aurora asked. “Not exactly.” “Then where?” Eva slid the key across the bar. It stopped against Aurora’s fingers. “I need you to keep it.” “No.” “Rory.” “No. You don’t vanish for years, walk back in bleeding through couture, and hand me a mystery key like we’re in some third-rate thriller.” Eva’s mouth twitched. “Still snobbish.” “Still alive. Explain.” “It belongs to a locker at King’s Cross. Left luggage. The number’s on the tape.” Aurora turned the key. On the underside of the tape, written in tiny black pen, were four digits. “What’s in it?” “A ledger. A phone. Copies.” “Copies of what?” Eva looked at Silas, then back at Aurora. “Things men with clean fingernails pay to keep filthy.” Silas’s face changed by a degree, no more. Aurora had
learned that degree
mattered. It meant the room had sharpened. “Who else knows?” he asked. Eva lifted the fresh whisky but did not drink. “The men who want it. The man who sent them. And a woman who is either dead or sensible.” “That’s a short list,” Silas said. “It gets shorter.” Aurora pushed the key back. “Take it to the police.” Eva looked at her with such naked pity that Aurora wanted to slap her. “Have you met the police?” Eva said. “I’ve met enough of them.” “Then you know better.” Silas spoke before Aurora could. “Why come here?” Eva smiled at that. Not her old reckless smile, not the bright one that dared trains and rent collectors and bad men. This one
looked like surrender dressed for dinner
. “Because she still believes in doors,” Eva said. Aurora’s throat tightened. “Don’t do that.” “Do what?” “Walk in and talk like you know me.” “I do know you.” “No. You know the girl who thought a train ticket could solve anything.” “And you know the girl who thought she could set fire to the world and stay warm.” For a beat, neither moved.
Then Eva put two fingers
over the key and nudged it back again. “I should have written,” she said. Aurora looked at the torn cuff, the bitten nails, the expensive coat with its faint dark stains, the bones of the friend she had loved in one fierce, shapeless way before life taught them both to mistrust
tenderness
. “You should have,” she said. A glass smashed near the door. No one screamed. The room did that strange London thing first, that quick collective pause where every head turns and every body decides whether the trouble belongs to them. Two men stood in the entrance beneath the green neon wash from the sign outside. One broad, one lean. The broad one wore a navy overcoat too fine for his face. The lean one had the stillness of a butcher behind a clean counter. Rain glistened on their shoulders, though no one else in the room had brought it in with them. The broad one
scanned
the bar, found Eva, and smiled as if he had spotted a late guest at a wedding. Silas’s hand vanished below the bar. Eva did not turn around. She had seen something in Aurora’s face. She closed her fingers over the whisky glass until her knuckles blanched. “Don’t look,” she said. Aurora ignored her and looked. The broad man started forward. The lean one locked the door behind them. The bolt snapped home with a neat, final sound. “Evening,” the broad man called. “Sorry to interrupt. We’re collecting a friend.” Silas straightened. “No collections tonight.” The broad man smiled wider. “That so?” The lean one reached inside his coat. Silas moved. Eva lunged across the bar for the key. Aurora grabbed her wrist. The whisky glass slipped from Eva’s hand, hit the floor, and burst across the boards as the lean man pulled out a gun.
created_at
"2026-03-09T22:45:30.695Z"
3/9/2026, 10:45:30 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
10309
moderation_latency
(null)
generation_time
87720
tokens_prompt
4618
tokens_completion
4053
native_tokens_prompt
4131
native_tokens_completion
3493
native_tokens_completion_images
0
native_tokens_reasoning
376
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
0.0627225
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_053db82f3db6abbe0169af4d8ac2bc8193bb0d277306c18679"
is_byok
false
latency
143
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-1773096330-e95JE2WxUjEl7dtHoYSX"
upstream_id
"resp_053db82f3db6abbe0169af4d8ac2bc8193bb0d277306c18679"
total_cost
0.0627225
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
25
adverbTagCount
2
adverbTags
0
"Aurora said too [too]"
1
"Eva tipped back [back]"
dialogueSentences
129
tagDensity
0.194
leniency
0.388
rawRatio
0.08
effectiveRatio
0.031
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2408
totalAiIsmAdverbs
0
found
(empty)
highlights
(empty)
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)
77.16%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2408
totalAiIsms
11
found
0
word
"silk"
count
1
1
word
"wavered"
count
1
2
word
"flicked"
count
1
3
word
"measured"
count
1
4
word
"stomach"
count
1
5
word
"unsettled"
count
1
6
word
"traced"
count
1
7
word
"dancing"
count
1
8
word
"pulse"
count
1
9
word
"tenderness"
count
1
10
word
"scanned"
count
1
highlights
0
"silk"
1
"wavered"
2
"flicked"
3
"measured"
4
"stomach"
5
"unsettled"
6
"traced"
7
"dancing"
8
"pulse"
9
"tenderness"
10
"scanned"
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
204
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
1
narrationSentences
204
filterMatches
(empty)
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
308
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
0
markdownWords
0
totalWords
2408
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
26
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
135
wordCount
1695
uniqueNames
16
maxNameDensity
3.01
worstName
"Eva"
maxWindowNameDensity
6.5
worstWindowName
"Eva"
discoveredNames
Friday
1
Eva
51
Aurora
46
Raven
1
Nest
1
Barry
1
Island
1
London
2
Sorry
1
Silas
20
You
1
Cardiff
2
Evan
2
Camden
1
Go
1
Usually
3
persons
0
"Eva"
1
"Aurora"
2
"Raven"
3
"Nest"
4
"Silas"
5
"You"
6
"Evan"
7
"Go"
places
0
"Barry"
1
"Island"
2
"London"
3
"Cardiff"
4
"Camden"
globalScore
0
windowScore
0
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
105
glossingSentenceCount
2
matches
0
"looked like now, the black shirt, black j"
1
"looked like surrender dressed for dinner"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
2408
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
2
totalSentences
308
matches
0
"known that girl"
1
"learned that degree"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
175
mean
13.76
std
17.24
cv
1.253
sampleLengths
0
10
1
69
2
10
3
1
4
7
5
85
6
2
7
22
8
7
9
3
10
72
11
40
12
4
13
22
14
5
15
14
16
20
17
3
18
77
19
32
20
16
21
1
22
5
23
5
24
38
25
14
26
2
27
4
28
33
29
9
30
2
31
3
32
14
33
5
34
16
35
6
36
21
37
8
38
3
39
2
40
21
41
18
42
3
43
5
44
11
45
4
46
3
47
95
48
5
49
25
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
204
matches
0
"was torn"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
302
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
308
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1698
adjectiveStacks
0
stackExamples
(empty)
adverbCount
52
adverbRatio
0.030624263839811542
lyAdverbCount
6
lyAdverbRatio
0.0035335689045936395
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
308
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
308
mean
7.82
std
6.8
cv
0.87
sampleLengths
0
10
1
31
2
2
3
2
4
34
5
10
6
1
7
7
8
2
9
26
10
18
11
21
12
10
13
4
14
4
15
2
16
3
17
4
18
15
19
6
20
1
21
3
22
6
23
5
24
3
25
9
26
8
27
6
28
6
29
29
30
20
31
20
32
4
33
5
34
17
35
2
36
3
37
10
38
4
39
12
40
8
41
3
42
9
43
7
44
4
45
19
46
14
47
24
48
21
49
5
42.86%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
22
diversityRatio
0.2662337662337662
totalSentences
308
uniqueOpeners
82
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
6
totalSentences
166
matches
0
"Just a short, breathy laugh"
1
"Then Eva vanished from her"
2
"Usually with whom?"
3
"Somewhere near the door, a"
4
"Just fatigue laid bare."
5
"Then Eva put two fingers"
ratio
0.036
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
24
totalSentences
166
matches
0
"It came from the far"
1
"She set the tray down"
2
"Her hair, once a wild"
3
"Her face looked thinner, expensive"
4
"It wavered, then held."
5
"His hazel eyes moved from"
6
"She measured the limp, the"
7
"It made Aurora’s stomach turn"
8
"He chose a peaty one"
9
"She lifted the glass, held"
10
"Her nails were short, bare,"
11
"He drifted away, though not"
12
"She reached for a bottle,"
13
"They had almost no money."
14
"They had chips wrapped in"
15
"It vanished at once."
16
"She saw, with horrible clarity,"
17
"She pulled a pint, took"
18
"She looked at him."
19
"It looked ordinary."
ratio
0.145
50.36%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
136
totalSentences
166
matches
0
"Aurora nearly dropped the tray"
1
"It came from the far"
2
"She set the tray down"
3
"The name landed harder than"
4
"Her hair, once a wild"
5
"Her face looked thinner, expensive"
6
"A cream silk blouse vanished"
7
"The coat hung open."
8
"Eva smiled first."
9
"It wavered, then held."
10
"Aurora found her voice in"
11
"The bar pressed on around"
12
"Someone called for another lager."
13
"A stool scraped."
14
"The Raven’s Nest swallowed secrets"
15
"Silas looked up from the"
16
"His hazel eyes moved from"
17
"Eva’s gaze flicked to him."
18
"She measured the limp, the"
19
"Silas set the tumbler down"
ratio
0.819
30.12%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
166
matches
0
"Before he gets charming again."
ratio
0.006
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
54
technicalSentenceCount
3
matches
0
"She measured the limp, the ring, the posture that said doorman, diplomat, and executioner in equal parts."
1
"A shared bedsit years later, London not yet cruel, both of them swearing they would never become women who apologised for taking up room."
2
"Then Eva vanished from her life in a series of missed calls, thin excuses, and one final text that read Sorry."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
25
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
23
fancyCount
0
fancyTags
(empty)
dialogueSentences
129
tagDensity
0.178
leniency
0.357
rawRatio
0
effectiveRatio
0
90.0166%