NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX40WEEB7RR4N4MVJNH4QWT9
Run Details
Model:
GPT-5.6 Sol
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
1m 3s
Cost:
$0.095049
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)
87.48%
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)
79.28%
Name drop frequency
(details)
77.18%
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)
45.98%
Sentence opener variety
(details)
21.37%
Adverb-first sentence starts
(details)
84.10%
Pronoun-first sentence starts
(details)
27.31%
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)
87.4232%
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
“Rory Carter. Christ alive, you do still exist.”
The bottle slipped against Aurora’s
palm.
She caught it by the
neck before it struck the floor, but lager foamed over her fingers and dripped from her wrist to the rubber mat behind the bar.
A man stood between two
vacant stools, one hand resting on the polished wood.
He wore a charcoal overcoat
over a pale shirt buttoned to the throat.
His hair, once long enough
to tuck behind his ears, had gone short at the sides and careful on top. Silver touched his temples. Not grey, not yet. A warning of it. “Evan.” The name came out clean. That surprised her.
He smiled with his mouth
closed. She
remembered that smile
. It had preceded gifts, apologies, explanations, and the small corrections with which he had once rebuilt her life to fit his hands. “Well.”
He glanced at her black
apron. “This is unexpected.” Around them, the Raven’s Nest continued its practised murmur. Ice rattled in glasses.
Someone fed coins into the
old jukebox and failed to wake it.
The green neon sign above
the entrance stained the nearest window with a sickly glow. Old maps covered the walls, their borders redrawn by dead men, while black-and-white faces watched from crooked frames.
Aurora set the bottle beside
a glass. “That’ll be six pounds eighty.” Evan looked at the lager. “I didn’t order that.” “The gentleman behind you did.”
A broad man in a
rugby shirt reached past him. “Cheers, love.”
Evan stepped aside and gave
a short laugh. “Same Rory.” “No. You’ve already said I’ve changed.” “I said this was unexpected.” “You used to call that distinction important.”
His smile loosened at one
corner. There it was, the old irritation, quick as a fish beneath dark water. Aurora wiped the beer from her wrist. The cloth snagged against the small crescent scar there. Evan’s eyes followed the movement. “You still have that.” “Skin tends to keep records.” “Fell through your dad’s greenhouse, didn’t you?” “Put my hand through a pane.” “You told everyone you were rescuing a trapped bird.” “I was nine. Perjury rules were relaxed.” A laugh escaped him, warm and
familiar
enough to disturb her. For one second, Cardiff returned in fragments: library dust, wet pavement beneath trainers, chips eaten from paper while Eva complained about vinegar, Evan leaning over a casebook he had not read.
He had laughed more easily
then. Or she had found it easier to hear.
He removed his coat and
folded it over the stool rather than sitting. “Can I buy you a drink?” “I’m working.” “Here?” “Astonishing powers of observation. They’ll make partner of you yet.” “They did.” He touched his cuff. No watch showed beneath it, though she remembered buying him one for his twenty-third birthday. A cheap silver thing, all she could afford after rent and books.
He had praised it, then
left it in a drawer. “Congratulations.” “You don’t mean that.” “I mean the word. What you do with it belongs to you.” The door opened behind him. Soho noise flooded the room, tyres hissing over greasy roads, a burst of laughter, a bicycle bell. Four office workers entered and filled the air with cold wool and expensive perfume. Aurora reached for clean tumblers. “Table or bar?” One of them pointed towards a corner booth. Aurora called their order to Mina at the far end, then lined the glasses beneath the taps. Her hands knew the work. Tilt, pour, straighten, settle. No wasted motion. Evan watched. “I heard you were in London.” “London has nine million people. Hearing I’m among them hardly counts as intelligence.” “Eva told Daniel.” “Eva hasn’t spoken to Daniel since university.” “People resume conversations.” “They do when they want something.”
He rubbed his thumb against
the inside of his forefinger. A tiny movement.
She remembered it from court
competitions, before he stood to argue a point he doubted. “Your number changed.” “Several years ago.” “You left without telling me where you’d gone.” Aurora set a pint beneath the tap and pulled the handle. Foam climbed too fast. She corrected the angle. “I left a note.” “Three lines.” “Four.” “You counted?” “I wrote them.” “Then you know they explained nothing.” The glass filled.
She placed it on a
tray, then started the next. “Some explanations turn into negotiations. I had no offer to make.” “I deserved a conversation.” The tap snapped shut in her hand. The office workers continued laughing in the booth. One slapped the table. A spoon struck the floor. Small noises, harmless noises, and beneath them came the old
silence
of a Cardiff flat where Aurora had once
measured
every cupboard door before closing it. Evan looked down at the bar. “That came out wrong.” “No. It came out polished.” “I spent months thinking you’d been hurt.” “I had.”
His face changed, though not
enough. “You know what I mean.” “So do you.”
He drew in a breath
through his nose. The man before her had acquired restraint the way others acquired property. He wore it well. The younger Evan had raised his voice, punched doors, paced rooms until she apologised for standing in his path. This one pressed his fingertips to the bar and arranged his features into something fit for witnesses. Aurora lifted the tray. “I have customers.” “So serve them. I’ll wait.” “No.” “Rory.” “Don’t.” A hand
appeared beside her and took the tray
. Silver flashed on one finger. “I believe the lady has answered.” Silas carried the drinks towards the corner booth. His left leg dragged by a fraction, a flaw most people missed until they saw it twice. He wore rolled shirtsleeves and a black waistcoat. Grey streaked his auburn hair and beard, but age had not softened him. It had pared him down. Evan watched Silas cross the room. “Your boss?” “Landlord.” “Of the pub?” “Of the flat above it.” Something pinched at Evan’s mouth. “You live here.” “Upstairs. Unless property law has changed since Cardiff.” “And you work in a bar.” “I work several places.” “You finished your degree.” “I left in third year.” “I know. I called the faculty.” The words landed between them without force. That made them worse. Aurora picked up the cloth again and folded it into a narrow square. “You called them?” “You vanished during term. Nobody knew anything.” “My parents knew.” “Your father threatened to report me for harassment.” “Brendan has good instincts.” “He hated me before we met.” “He met you.” Evan pulled out the stool and sat. The old leather seat sighed beneath him. “Your father wanted you in chambers. Your mother wanted you back in Cardiff. Eva wanted you in London. Everyone had plans for you.” “And you didn’t?” “I wanted us.” “No. You wanted custody.” A glass cracked at the far end. Mina swore, swept it into a metal pan, and continued serving without looking over. Silas had returned to the centre of the room. He polished a tumbler that needed no attention. Evan lowered his voice. “I was twenty-four.” “So was I.” “I had no idea how to handle things.” “You handled me often enough.” His hand closed around the edge of the bar. “You make it sound
calculated
.” “Does impulse bruise less?” A
pulse
worked in his jaw. For an instant she saw him in their old kitchen, shirt half-buttoned, one hand flat against the fridge beside her head. Not touching. He had
liked that distinction
too. “I never hit you.” “No. You liked walls.” “That’s not fair.” “Neither was losing the deposit.” He looked towards the bottles behind her. Whisky glowed in rows of amber and brown. In the mirror, his face
seemed older and less certain
. Aurora’s own reflection stood beside his, straight black hair touching her shoulders, bright blue eyes sharpened by the low light. They
looked like strangers posed for separate
photographs. “I went to therapy,” he said. The cloth stopped between her hands. “Good.” “For two years.” “Still good.” “I didn’t come here for absolution.” “You came here for a drink. Apparently.” “I came because Daniel’s engagement party fell apart at some private club, and one of the others knew this place. I saw the sign and came in. Then you were standing there.” The coincidence sounded rehearsed. Evan heard it too. “You think I followed you.” “You called my university after I left.” “Years ago.” “People resume conversations.” His own words settled over him. He reached for the drinks list and turned it face down. “I’m married.” Aurora waited. “Her name’s Sophie. She’s a paediatric surgeon.” “Is that meant to reassure me?” “No. It’s only true.” “Those differ more often than people admit.” “We have a daughter.” His thumb moved again. Once against his finger. Twice. Aurora placed the folded cloth beside the sink. “What’s her name?” “Clara.” The answer came without his lawyer’s pause. “How old?” “Eighteen months.” A picture entered her mind without permission: Evan holding a small girl under the arms, lifting her towards a ceiling, his expression open in a way Aurora had once believed only she could summon. She pushed a stack of coasters into alignment. “Does Sophie know you’re here?” “Yes.” “Does she know who I am?” “She knows I had a serious relationship at university.” “That sounds clean.” “I told her I behaved badly.” “Also clean.” His gaze hardened. “What phrase would satisfy you?” “None. You’re not drafting a confession.” “I’m attempting to speak to someone I loved.” “You loved a version of me who said sorry before you finished hurting her.” He stood so fast the stool rocked backwards. His hand caught it. Several heads turned, then turned away when Silas placed both palms on the bar. “No furniture,” Silas said. “An accident.” “So was Prague, according to three governments. The knee remains unconvinced.” Evan studied him. “Do you listen to all your staff’s conversations?” “Only when men stand over them.” “I’m not threatening her.” “No. You’re merely making the room smaller.” Silas’s hazel eyes rested on Evan’s coat, his shoes, his hands. He catalogued him without shame. Aurora stepped between their lines of sight. “Si.” His silver signet ring clicked against the wood. “Aurora.” The use of her full name carried a question. “I can handle a conversation.” “I’ve no doubt.” Silas turned away, though he moved no farther than the till. Evan set the stool upright. “Si.” “He has a name. You’ve managed one yourself.” “I remember when you hated people calling you Aurora.” “I hated the way you said it.” He flinched. A small, gratifying thing. She disliked the gratification at once. “I’ve thought about that last night a thousand times.” “Then you’ve wasted a thousand nights.” “You packed while I was asleep.” “I packed while you were drunk.” “You took the blue suitcase.” “It was mine.” “You left the casebooks.” “They were heavy.” “I kept them.” “Of course you did.” His face tightened. “What does that mean?” “You never threw away evidence.” “I kept them because I thought you’d come back for them.” “I didn’t.” “No.” He looked at her apron again, but his expression had lost its first contempt. Something worse replaced it: grief shaped by an assumption that her present life
measured
the damage he had done. Aurora untied the apron and laid it on the counter. “I deliver food for a Chinese restaurant three days a week. I help here when Mina’s short. I translate legal letters for people who can’t afford your hourly rate. Last month, I stopped a landlord evicting a woman because he’d misspelt her surname on two notices and forged the third. I’m not the ruin you need me to be.” “I didn’t say you were.” “You looked.” “I looked because you should have been a barrister.” “You mean I could have been one.” “You were better than all of us.” “At pretending the rules protected people.” “They can.” “When expensive men phrase them correctly.” He leaned closer, lowering his voice again. “You sound like your father.” Aurora smiled. “That must hurt.” For the first time, Evan looked stripped of language. He gazed at his hands, smooth except for a pale mark near the knuckle. She remembered causing it. He had seized her suitcase handle, and she had slammed the bedroom door against his hand. He had cried out. She had apologised. His wedding ring caught the green light. “I’m sorry.” The words came without ornament. Aurora’s throat tightened. She reached for a glass and found none in her hand. “For which part?” “All of it.” “That isn’t an answer.” “For reading your messages. For calling Eva a parasite. For making you leave moot practice because Simon fancied you. For breaking the bathroom lock. For every time I told you that you’d misunderstood what happened.” He placed his hand flat on the bar, wedding ring down. “And for the night you left.” The Nest
seemed to
draw a breath around them. Silas stopped touching the till. Aurora studied Evan’s bowed head. She had imagined this apology in beds, on trains, in the delivery van at red lights. In each version, it unlocked something. Rage, tears, a clean indifference. The real words sat on the bar like loose coins, useful only if someone agreed on their value. “You knew, then.” “Yes.” “You knew what you were doing.” “Not while I did it. Afterwards.” “Afterwards counts.” “I know.” “Does Sophie?” His fingers curled. “She knows I had anger problems.” “That wasn’t my question.” “Rory.” “Does she know about the bathroom lock?” A bottle struck the floor in the kitchen corridor. Nobody moved. Evan’s eyes lifted to hers. “No.” “Does she know you held my phone outside the window and said you’d drop it if I rang Eva?” “No.” “Does she know you timed my walk home from university?” “That happened once.” There it was. The correction entered his voice without thought, smooth from years of use. Evan heard it after she did. Colour climbed from his collar. Aurora took one step back. He reached across the bar and caught her left wrist. His grip found the crescent scar. Silas moved. The bookshelf on the rear wall swung open before he reached them, striking the frame with a wooden crack. A woman stumbled out of the hidden room, one hand clamped to her blood-soaked side. “Lock the front door,” she gasped. “They’ve found the Nest.” The window exploded inward.
created_at
"2026-07-09T18:05:19.705Z"
7/9/2026, 6:05:19 PM
model
"openai/gpt-5.6-sol-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
508
moderation_latency
(null)
generation_time
62730
tokens_prompt
4618
tokens_completion
4276
native_tokens_prompt
4131
native_tokens_completion
3099
native_tokens_completion_images
0
native_tokens_reasoning
0
native_tokens_cached
4128
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
service_tier
"default"
usage
0.095049
router
(null)
provider_responses
0
endpoint_id
"a54c5de0-89bf-4ad7-a212-cf977eed918a"
id
"resp_0f8eba9b890e3226016a4fe2dfcc308197aa60f3212f1ebdbe"
is_byok
false
latency
229
model_permaslug
"openai/gpt-5.6-sol-20260709"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1783620319-XInWbgO8hxhBcznKaTZM"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620319-MbsvElSje04KGhPR7oIf"
upstream_id
"resp_0f8eba9b890e3226016a4fe2dfcc308197aa60f3212f1ebdbe"
total_cost
0.095049
cache_discount
0.018576
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
4
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
185
tagDensity
0.022
leniency
0.043
rawRatio
0
effectiveRatio
0
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2396
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)
87.48%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2396
totalAiIsms
6
found
0
word
"familiar"
count
1
1
word
"silence"
count
1
2
word
"measured"
count
2
3
word
"calculated"
count
1
4
word
"pulse"
count
1
highlights
0
"familiar"
1
"silence"
2
"measured"
3
"calculated"
4
"pulse"
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
167
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
1
narrationSentences
167
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
348
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
59
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2396
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
29
unquotedAttributions
0
matches
(empty)
79.28%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
56
wordCount
1414
uniqueNames
8
maxNameDensity
1.41
worstName
"Evan"
maxWindowNameDensity
2.5
worstWindowName
"Aurora"
discoveredNames
Aurora
19
Raven
1
Nest
2
Cardiff
2
Eva
1
Evan
20
Mina
2
Silas
9
persons
0
"Aurora"
1
"Raven"
2
"Nest"
3
"Eva"
4
"Evan"
5
"Mina"
6
"Silas"
places
0
"Cardiff"
globalScore
0.793
windowScore
0.833
77.18%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
103
glossingSentenceCount
3
matches
0
"appeared beside her and took the tray"
1
"seemed older and less certain"
2
"looked like strangers posed for separate"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
2396
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
2
totalSentences
348
matches
0
"remembered that smile"
1
"liked that distinction"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
262
mean
9.15
std
11.77
cv
1.287
sampleLengths
0
8
1
35
2
59
3
1
4
8
5
32
6
10
7
58
8
7
9
5
10
5
11
4
12
5
13
10
14
2
15
8
16
2
17
6
18
5
19
7
20
19
21
21
22
4
23
5
24
7
25
6
26
9
27
7
28
56
29
13
30
6
31
2
32
1
33
10
34
2
35
41
36
1
37
4
38
12
39
36
40
5
41
3
42
37
43
2
44
6
45
13
46
3
47
7
48
3
49
6
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
167
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
255
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
348
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1419
adjectiveStacks
0
stackExamples
(empty)
adverbCount
36
adverbRatio
0.02536997885835095
lyAdverbCount
4
lyAdverbRatio
0.0028188865398167725
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
348
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
348
mean
6.89
std
6.03
cv
0.876
sampleLengths
0
8
1
6
2
29
3
14
4
13
5
20
6
4
7
4
8
4
9
1
10
5
11
3
12
6
13
4
14
22
15
7
16
3
17
9
18
4
19
12
20
15
21
18
22
7
23
5
24
5
25
4
26
5
27
10
28
2
29
8
30
2
31
6
32
5
33
7
34
6
35
13
36
7
37
9
38
5
39
4
40
5
41
7
42
6
43
9
44
7
45
11
46
31
47
6
48
8
49
13
45.98%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
14
diversityRatio
0.2672413793103448
totalSentences
348
uniqueOpeners
93
21.37%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
156
matches
0
"Once against his finger."
ratio
0.006
84.10%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
53
totalSentences
156
matches
0
"She caught it by the"
1
"He wore a charcoal overcoat"
2
"His hair, once long enough"
3
"He smiled with his mouth"
4
"She remembered that smile."
5
"It had preceded gifts, apologies,"
6
"He glanced at her black"
7
"His smile loosened at one"
8
"He had laughed more easily"
9
"He removed his coat and"
10
"He touched his cuff."
11
"He had praised it, then"
12
"Her hands knew the work."
13
"He rubbed his thumb against"
14
"She remembered it from court"
15
"She corrected the angle."
16
"She placed it on a"
17
"His face changed, though not"
18
"He drew in a breath"
19
"He wore it well."
ratio
0.34
27.31%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
135
totalSentences
156
matches
0
"The bottle slipped against Aurora’s"
1
"She caught it by the"
2
"A man stood between two"
3
"He wore a charcoal overcoat"
4
"His hair, once long enough"
5
"A warning of it."
6
"The name came out clean."
7
"That surprised her."
8
"He smiled with his mouth"
9
"She remembered that smile."
10
"It had preceded gifts, apologies,"
11
"He glanced at her black"
12
"Ice rattled in glasses."
13
"Someone fed coins into the"
14
"The green neon sign above"
15
"Aurora set the bottle beside"
16
"Evan looked at the lager."
17
"A broad man in a"
18
"Evan stepped aside and gave"
19
"His smile loosened at one"
ratio
0.865
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
156
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
52
technicalSentenceCount
0
matches
(empty)
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
4
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
3
fancyCount
1
fancyTags
0
"she gasped (gasp)"
dialogueSentences
185
tagDensity
0.016
leniency
0.032
rawRatio
0.333
effectiveRatio
0.011
87.4232%