NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KK9Q2E19A5FS49HAFB010KXK
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
3m 6s
Cost:
$0.113333
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
98.02%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
80.21%
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)
43.66%
Sentence opener variety
(details)
81.30%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
33.17%
Subject-first sentence starts
(details)
30.49%
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)
88.8947%
Overall
Model input
System
You are an expert and award-winning novel writer in the dark Literary Fiction genre. Your readers are hooked on your stories and can't wait to read the book you have in store. <important> - MUST: Start each chapter in medias res (in the middle of action). AVOID talking about the weather, time of day, the position of the sun, or other boring stuff. - The instructions/summary are just a that, a summary. Feel free to add details, stretch sections and add interesting transitions/descriptions/fillers. - When called for it, have fast-paced action, but otherwise take things slow. This is an experience, and not for people with short attention spans. Enjoy the wine, not slurp Red Bull. - Add descriptions when transitioning places/times/etc, or when coming by new places (e.g. a corner shop, a cafe, etc.). But remember: NOT at the start or end of a chapter. - MUST: AVOID ending in internal monologue, reminiscing or waiting for the next day. A good chapter end is when we're ending right when shit hits the fan. We want to have the reader be excited for what comes next. So no reminiscing, contemplating or summarizing the day. It's popcorn time! </important>
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <codex> <character id="4412" name="Aurora Carter" aliases="Rory, Laila, Aurora, Carter, Malphora" pronouns="she/her" species="Human" storyRole="Protagonist"> <eyeColor>bright blue</eyeColor> <hair>straight shoulder-length black</hair> <height>5'6"</height> <age>25</age> <scar>small crescent-shaped scar on her left wrist from a childhood accident</scar> <description>Aurora, referred to by her friends as Rory, is cool-headed, intelligent, and known for quick out-of-the-box thinking.</description> <backstory>Born in Cardiff to an Irish barrister father (Brendan Carter) and Welsh teacher mother (Jennifer Carter née Ellis), Rory reluctantly pursued Pre-Law at Cardiff University. She fled to London at the behest of her childhood friend Eva after leaving an abusive ex named Evan. By day, Rory works part-time as a delivery person for Yu-Fei Cheung's Golden Empress restaurant. She lives in a flat above Silas' bar.</backstory> </character> <character id="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</backstory> </character> <location id="854" name="The Raven's Nest" aliases="the Nest, Raven, Silas' bar" realm="Earth"> <signColor>distinctive green neon sign above the entrance</signColor> <secretRoom>hidden back room accessible through a bookshelf, used for clandestine meetings</secretRoom> <description>A dimly lit bar in Soho, London. The walls are covered with old maps and black-and-white photographs.</description> </location> </codex> <proseGuidelines> <styleGuide> - Write in past tense and use British English spelling and grammar - Keep a Flesch reading ease score of 60 - Respect the the Royal Order of Adjectives: The order is: opinion, size, age, shape, color, origin, material, purpose, followed by the noun itself (e.g., "a lovely little old rectangular green French silver whittling knife") - Respect the ablaut reduplication rule (e.g. tick-tock, flip-flop) - Write in active voice - Passive voice: <bad>The book was read by Sarah.</bad> - Active voice: <good>Sarah read the book.</good> - Reduce the use of passive verbs - <bad>For a moment, I was tempted to throw in the towel.</bad> - <good>For a moment, I felt tempted to throw in the towel.</good> - Avoid misplaced modifiers that can cause confusion when starting with "-ing" words: - <bad>Considering going to the store, the empty fridge reflected in Betty's eyes.</bad> - <good>Betty stared into the empty fridge. It was time to go to the store.</good> - Avoid redundant adverbs that state the obvious meaning already contained in the verb: - <bad>She whispered quietly to her mom.</bad> - <good>She whispered to her mom.</good> - Use stronger, more descriptive verbs over weak ones: - <bad>Daniel drove quickly to his mother's house.</bad> - <good>Daniel raced to his mother's house.</good> - Omit adverbs that don't add solid meaning like "extremely", "definitely", "truly", "very", "really": - <bad>The movie was extremely boring.</bad> - <good>The movie was dull.</good> - Use adverbs to replace clunky phrasing when they increase clarity: - <bad>He threw the bags into the corner in a rough manner.</bad> - <good>He threw the bags into the corner roughly.</good> - Avoid making simple thoughts needlessly complex: - <bad>After I woke up in the morning the other day, I went downstairs, turned on the stove, and made myself a very good omelet.</bad> - <good>I cooked a delicious omelet for breakfast yesterday morning.</good> - Never backload sentences by putting the main idea at the end: - <bad>I decided not to wear too many layers because it's really hot outside.</bad> - <good>It's sweltering outside today, so I dressed light.</good> - Omit nonessential details that don't contribute to the core meaning: - <bad>It doesn't matter what kind of coffee I buy, where it's from, or if it's organic or not—I need to have cream because I really don't like how the bitterness makes me feel.</bad> - <good>I add cream to my coffee because the bitter taste makes me feel unwell.</good> - Always follow the "show, don't tell" principle. For instance: - Telling: <bad>Michael was terribly afraid of the dark.</bad> - Showing: <good>Michael tensed as his mother switched off the light and left the room.</good>- Telling: <bad>I walked through the forest. It was already Fall, and I was getting cold.</bad> - Showing: <good>Dry orange leaves crunched under my feet. I pulled my coat's collar up and rubbed my hands together.</good>- Add sensory details (sight, smell, taste, sound, touch) to support the "showing" (but keep an active voice) - <bad>The room was filled with the scent of copper.</bad> - <good>Copper stung my nostrils. Blood. Recent.</good> - Use descriptive language more sporadically. While vivid descriptions are engaging, human writers often use them in bursts rather than consistently throughout a piece. When adding them, make them count! Like when we transition from one location to the next, or someone is reminiscing their past, or explaining a concept/their dream... - Avoid adverbs and clichés and overused/commonly used phrases. Aim for fresh and original descriptions. - Avoid writing all sentences in the typical subject, verb, object structure. Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. Like so: <good>Locked. Seems like someone doesn't want his secrets exposed. I can work with that.</good> - Convey events and story through dialogue. It is important to keep a unique voice for every character and make it consistent. - Write dialogue that reveals characters' personalities, motivations, emotions, and attitudes in an interesting and compelling manner - Leave dialogue unattributed. If needed, only use "he/she said" dialogue tags and convey people's actions or face expressions through their speech. Dialogue always is standalone, never part of a paragraph. Like so: - <bad>"I don't know," Helena said nonchalantly, shrugging her shoulders</bad> - <good>"No idea" "Why not? It was your responsibility"</good> - Avoid boring and mushy dialog and descriptions, have dialogue always continue the action, never stall or include unnecessary fluff. Vary the descriptions to not repeat yourself. Avoid conversations that are just "Let's go" "yes, let's" or "Are you ready?" "Yes I'm ready". Those are not interesting. Think hard about every situtation and word of text before writing dialogue. If it doesn't serve a purpose and it's just people talking about their day, leave it. No one wants to have a normal dinner scene, something needs to happen for it to be in the story. Words are expensive to print, so make sure they count! - Put dialogue on its own paragraph to separate scene and action. - Use body language to reveal hidden feelings and implied accusations- Imply feelings and thoughts, never state them directly - NEVER use indicators of uncertainty like "trying" or "maybe" - NEVER use em-dashes, use commas for asides instead </styleGuide> <voiceGuide> Each character in the story needs to have distinct speech patterns: - Word choice preferences - Sentence length tendencies - Cultural/educational influences - Verbal tics and catchphrases Learn how each person talks and continue in their style, and use their Codex entries as reference. <examples> - <bad>"We need to go now." "Yes, we should leave." "I agree."</bad> <good>"Time's up." "Indeed, our departure is rather overdue." "Whatever, let's bounce."</good> - Power Dynamic Example: <bad> "We need to discuss the contract." "Yes, let's talk about it." "I have concerns." </bad> <good> "A word about the contract." "Of course, Mr. Blackwood. Whatever you need." "The terms seem..." A manicured nail tapped the desk. "Inadequate." "I can explain every-" "Can you?" </good> </examples> </voiceGuide> <dialogueFlow> When writing dialogue, consider that it usually has a goal in mind, which gives it a certain flow. Make dialogue sections also quite snappy in the back and forth, and don't spread the lines out as much. It's good to have details before, after, or as a chunk in-between, but we don't want to have a trail of "dialogue breadcrumbs" spread throughout a conversation. <examples> - Pattern 1 - Question/Deflection/Revelation: <good> "Where were you last night?" "Work. The usual." "Lipstick's an interesting shade for spreadsheets." </good> - Pattern 2 - Statement/Contradiction/Escalation: <good> "Your brother's clean." "Tommy doesn't touch drugs." "I'm holding his tox screen." </good> - Pattern 3 - Observation/Denial/Truth: <good> "That's a new watch." "Birthday gift." "We both know what birthdays mean in this business." </good> - Example - A Simple Coffee Order: <bad> "I'll have a coffee." "What size?" "Large, please." </bad> <good> "Black coffee.""Size?""Large. Been a long night." "That bodega shooting?" "You watch too much news." "My brother owns that store." </good> This short exchange: - Advances plot (reveals connection to crime) - Shows character (cop working late) - Creates tension (unexpected connection) - Sets up future conflict (personal stake) - Example - Dinner Scene: <bad> "Pass the salt." "Here you go." "Thanks." </bad> <good> "Salt?" "Perfect as is. Mother's recipe." "Mother always did prefer... bland things." "Unlike your first wife?" </good> - Example - Office Small Talk: <bad> "Nice weather today." "Yes, very nice." "Good for golf." </bad> <good> "Perfect golf weather." "Shame about your membership." "Temporary suspension. Board meets next week." "I know. I called the vote." </good> </examples> </dialogueFlow> <subtextGuide> - Layer dialogue with hidden meaning: <bad>"I hate you!" she yelled angrily.</bad> <good>"I made your favorite dinner." The burnt pot sat accusingly on the stove.</good> - Create tension through indirect communication: <bad>"Are you cheating on me?"</bad> <good>"Late meeting again?" The lipstick stain on his collar caught the light.</good> <examples> - Example 1 - Unspoken Betrayal: <bad> "Did you tell them about our plans?" "No, I would never betray you." "I don't believe you." </bad> <good> "Funny. Johnson mentioned our expansion plans today." "The market's full of rumors." "Mentioned the exact numbers, actually." The pen in his hand snapped. </good> - Example 2 - Failed Marriage: <bad> "You're never home anymore." "I have to work late." "I miss you." </bad> <good> "Your dinner's in the microwave. Again." "Meetings ran long." "They always do." She folded the same shirt for the third time. </good> - Example 3 - Power Struggle: <bad> "You can't fire me." "I'm the boss." "I'll fight this." </bad> <good> "That's my father's nameplate you're sitting behind." "Was." "The board meeting's on Thursday." </good> </examples> </subtextGuide> <sceneDetail> While writing dialogue makes things more fun, sometimes we need to add detail to not have it be a full on theatre piece. <examples> - Example A (Power Dynamic Scene) <good> "Where's my money?" The ledger snapped shut. "I need more time." "Interesting." He pulled out a familiar gold pocket watch. My mother's. "Time is exactly what you bargained with last month." "That was different-" "Was it?" The watch dangled between us. "Four generations of O'Reillys have wound this every night. Your mother. Your grandmother. Your great-grandmother.Shall we see who winds it next?" </good> - Example B (Action Chase) It's much better to be in the head of the character experiencing it, showing a bit of their though-process, mannerisms and personality: <good> Three rules for surviving a goblin chase in Covent Garden: Don't run straight. Don't look back. Don't let them herd you underground. I broke the first rule at Drury Lane. Rookie mistake. The fruit cart I dodged sailed into the wall behind me. Glass shattered. Someone screamed about insurance. *Tourist season's getting rough*, the scream seemed to say. Londoners adapt fast. "Oi! Market's closed!" The goblin's accent was pure East End. They're evolving. Learning. I spotted the Warren Street tube station sign ahead. *Shit.* There went rule three. </good> - Example C (Crime Scene Investigation) <good> "Greek." Davies snapped photos of the symbols. "No, wait. Reverse Greek." "Someone's been watching too many horror films." I picked up a receipt from the floor. Occult supply shop in Camden. Paid by credit card. *Amateur hour*. "Could be dangerous though," Davies said. "Remember Bristol?" "Bristol was Sanskrit. And actual cultists." I pointed to the nearest symbol. "This genius wrote 'darkness' backwards but used a Sigma instead of an S. It's summoning Instagram followers at best." "Speaking of followers..." Davies pointed to heavy foot traffic in the dust. Multiple sets. All new trainers. *Ah.* "Anyone check local uni paranormal societies?" </good> - Example D (Dialogue-heavy) <good> "Found your card in her wallet." The detective slid it across the table. Worn edges. Folded corner. Three years old at least. "Standard practice. I work missing persons." "Funny thing about missing persons.Eventually they stop being missing. Turn up in the Thames. Under motorways. In pieces." "I don't-" "You found four last year. All breathing." She opened a file. "This would've been your first dead one. If we hadn't found her first." The card felt heavier somehow. </good> </examples> </sceneDetail> <sceneOpenings> KEY RULE: Never open with more than one paragraph of description, no matter how beautiful. Description should be earned through action and dialogue. Instead of opening with setting description, open with: - A character doing something specific - A line of dialogue that raises questions - An unexpected observation - A moment of tension or conflict - Start with a hook that's 1-2 sentences maximum - Follow with a smaller paragraph that provides immediate context - Vary paragraph size from the start to create visual interest </sceneOpenings> </proseGuidelines> Write a chapter based on the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the literary fiction genre. Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret. Use the codex entries above as your world reference for characters and setting. Only include the prose of the scene without any markdown or commentary. </instructions>
Model response
Messages
Meta
AI
The glass slipped in Aurora’s
hand when she heard her old name. “Rory?”
Gin splashed over her knuckles
and across the bar top.
She caught the tumbler before
it hit the floor, set it down, and looked up with the sort of stillness that came after impact.
The woman by the green-lit
entrance stood half in shadow, one hand still on the door as if she had not decided whether to enter or flee.
The neon from the sign
outside washed her cheekbone the colour of old bruise. For a beat Aurora saw only the outline, the lift of the chin she knew, the pause before a smile that did not arrive.
Then the face settled into
focus. “Eva.”
Silas glanced up from the
till.
His silver signet ring flashed
once as he shut the drawer.
He followed Aurora’s stare to
the door and said nothing.
That was one of his
better qualities.
He saved words the way
other men saved cash.
Eva came in and let
the door fall shut behind her.
The Raven’s Nest took her
in by inches, smoke-dark timber, old maps, black-and-white photographs with corners curled by years of heat, a low hum from the speakers, the smell of citrus peel and spilled beer sunk deep into the grain. She looked wrong inside it, too clean at first glance, too narrow, like she had been cut from a harder cloth and folded into a shape that left no room for softness. Aurora remembered a different Eva. Copper hair. Smudged eyeliner. Rings on half her fingers.
A laugh that entered a
room before she did and left after everyone else.
This Eva wore a black
coat with sharp seams and no jewellery at all.
Her hair sat in a
blunt dark bob that showed the pale nick in her left ear where a hoop used to hang.
She had lost flesh from
her face.
Her mouth had thinned with
discipline or damage. “You vanished,” Eva said. “You told me to.” “That was London, not the
grave
.” Aurora picked up the bar towel and wiped the gin from the wood.
Her hand moved in neat
circles.
Only her wrist gave her
away, the small crescent scar on the left catching light each time she turned it. Silas dried a glass that did not need drying. “Friend of yours?” “Used to be.” Eva gave him a quick, measuring
look
.
He had that effect on
people. Some straightened. Some lied at once. She did neither. “You run a proper speakeasy now, Rory?” “It’s a bar.” “A bar with maps from dead empires.” “People drink more when they feel history watching.” One corner of Eva’s mouth lifted. There it was, a shard of the old face. Silas set the glass down. “If this reunion ends in tears, take it away from the whisky.” Aurora nodded towards the far booth under the framed map of Prague. “Sit.” Eva crossed the room with a care Aurora did not remember.
She used to move as
if the world would shift round her.
Now she checked sightlines in
mirrors, doors, hands, exits. Silas saw it too.
He watched her long enough
to file the habit, then limped down the bar to serve a man in a flat cap at the far end. Aurora poured herself water.
She set a tumbler of
soda in front of Eva without asking. Eva looked at it. “You remember.” “You hated tonic.” “I hate lots of things. It never stopped me.” Aurora slid into the booth opposite her. The leather seat sighed under her
weight
. Up close, the changes showed better. Fine lines cut the skin round Eva’s mouth. A tiny white seam nicked her
eyebrow
.
Her nails were short and
bare. No smell of perfume, only cold city air and the faint medicinal trace of hand sanitiser. “You
look
different,” Aurora said. “So do you.” “That wasn’t an answer.” Eva ran one finger round the rim of the glass but did not lift it. “You used to wear your hair like a threat. Red lipstick, leather jacket, all that theatre. Now you
look
like someone who gives bad news in a private room.” Eva laughed once.
It held no joy and
no bitterness either. Just recognition. “I work in probation.” Aurora blinked. “You’re joking.” “No.” “You used to steal traffic cones.” “I still could, if the nation called.” Silence opened between them, not empty, not peaceful. It had
weight
. The old kind. The sort that remembered things both people had locked away in different cities. Aurora leaned back. “How many years?” “Six.” “Five and a half.” “You always were pedantic.” “You always were late.” Eva’s fingers stopped moving on the glass. A tiny thing, easy to miss. “Still are,” Aurora said. “That sounded earned.” “It was.” Eva looked past her for a second, to the shelves behind the bar, to Silas speaking low to a man with a newspaper folded under his arm. When she looked back, the old quick silver in her had gone. What remained was steadier and harder. “I wrote to you.” “I moved.” “I called.” “I changed my number.” “I noticed.” Aurora folded her hands on the table. She kept them flat. It stopped them from fidgeting. “So why are you here?” “To see you.” “Don’t insult me in a bar run by a former spy.” Silas, all the way at the counter, did not turn his head. One side of his mouth twitched. Eva
let out a breath
through her nose. “You used to be easier.” “I used to be twenty.” “Fair.” A couple near the door got up with their coats. Someone fed coins into the old jukebox, then thought better of it. The room kept its low
pulse
, glass against wood, soft shoes on boards, the mutter of conversations no one would repeat outside. Aurora watched Eva’s face the way she once watched exam invigilators, alert for weakness, alert for fraud. “I thought you’d gone back to Cardiff,” Aurora said. “I did.” “How long?” “Long enough to know I couldn’t stay.” “And now you save men from themselves.” “I process them. The saving is above my pay grade.” “That sounds more like you.” Eva took her first sip of soda. Her throat worked. Aurora saw, with a small ugly shock, that her hand did not shake. Old Eva would have ordered gin in the first minute and finished it before the second. “No alcohol?” Aurora said. “Three years.” “You quit.” “I stopped waking up in strangers’ kitchens with one shoe and a police caution.” “That does sound mature.” “It bored me.” Aurora looked at her then, properly. Not the coat. Not the haircut. The face beneath. The old mischief had not died. It had
been mined
out and packed away under work, under sleep, under whatever pain had taught Eva to sit so still. Aurora felt a flash of something mean and hot, not anger, not pity, something less noble than both. “You
look
tired,” she said. Eva gave a short smile. “You
look
defended.” “That’s not the same thing.” “No.” Silas
appeared beside the table as if the room had carried him there
. He placed a fresh water for Aurora and set a small dish of salted almonds between them. “On the house,” he said. “We didn’t ask.” “You both looked hungry enough to bite the furniture.” Eva tipped her head. “You always keep the peace like this?” “I keep options open.” His hazel eyes settled on Aurora for half a second, then on Eva. “If she throws the glass, duck left. The booth’s fixed.” He left them with that. Eva watched him go. “He likes you.” “He likes useful people.” “That counts.” Aurora drank. “You still haven’t answered.” Eva looked down at the bubbles breaking in her glass. “No. I haven’t.” Aurora waited. She had learnt patience in the worst places, in solicitor waiting rooms with cheap carpet and in kitchens where men turned kind by degrees and cruel in a snap. Silence made people clumsy. Eva had known that once. She knew it now too. It showed in the way her jaw tightened. “You remember that night at Cathays,” Eva said. Aurora did not move. “The red house. Mould in the bathroom. Your awful landlady.” “I remember.” “You came round with that overnight bag and that split lip you said came from a cupboard door.” “Eva.” “He rang me after you left.” The room did not change. No chair scraped. No glass broke. Yet everything drew thin at the edges. Aurora’s voice came flat. “When?” “That same night.” “And?” Eva pressed her thumb into the side of the glass. “He was frantic. Crying. Said you’d taken tablets before, said you weren’t well, said he needed to find you before you hurt yourself.” Aurora said nothing. “I knew he was lying about half of it. I knew enough for that. But he had blood on his shirt and panic all over him, and I was drunk, and he kept saying your name like a prayer and a threat in the same breath.” Aurora’s eyes did not leave her face. “What did you tell him?” Eva lifted her gaze. She did not hide. “I told him London.” “That’s all?” “I said your friend had a sofa in Bethnal Green.” Aurora laughed once. A small clean sound, like a blade lifted from water. “That was enough.” “I know.” “He found me in Camden three weeks later.” Eva flinched, small but real. “I know.” “No, you don’t.” “He told me afterwards.” Aurora leaned in. “Afterwards?” Eva swallowed. “He came back. Sober. Calm. Worse, somehow. He said he’d seen you. Said you’d gone all cold and strange in the city. He wanted me to agree with him. He wanted a witness to the version of you he’d made.” Aurora’s fingers curled against the wood. “And what did you say?” “I told him to go to hell.” “That must have stung.” “He broke my jaw.” The words sat between them with awful composure. Aurora stared. Eva touched the left side of her face, not as a flourish, only habit. There it was then, in the changed line of her smile, in the slight hitch when certain consonants caught. “He did that?” Eva nodded. “I testified when they
charged
him for the girl after me.” Aurora went still. “What girl?” Eva shut her eyes for one beat. Opened them. “Nineteen. First year at the uni. He moved on fast.” The jukebox clicked and failed to start.
Somewhere a man laughed too
loud and
got shushed
. Aurora’s mouth had gone dry. “He went away?” “For a while.” “For a while,” Aurora repeated. “That’s the problem with terms like justice. They have calendar dates.” Aurora sat back. The booth leather creaked under her spine. She looked towards the bar. Silas had not once looked at them, which meant he had heard enough to know it mattered. “You should have told me,” Aurora said. “I wrote three letters.” “I never got them.” “I sent them to the flat above the off-licence in Whitechapel.” Aurora frowned. “I never lived there.” Eva’s face changed then, a tiny collapse. Not surprise, not quite. Confirmation. “He said that was where you were.” Aurora saw it come together in both of them at once, ugly and late. Evan feeding one lie into another, building his little kingdom out of people’s good intentions and fear. “You believed him twice,” Aurora said. “Yes.” “You never used to be stupid.” Eva took that without defence. She had earned worse from herself. “No,” she said. “I used to be loud. It looked similar from a distance.” Aurora looked at her hands. Bare knuckles. No rings. A thin pale scar across the base of the thumb. Work or violence, hard to tell. Time had worked over them both. It had shaved one down to nerve and caution. It had set the other in place like cooling metal. “You were the only person I missed,” Eva said. Aurora’s eyes
flicked
up. “That line used to work on bartenders.” “I’m not flirting. Christ.” “You sound offended.” “I am. You were impossible. You corrected my essays in green ink. You stole my jumpers. You threw up on my brother’s trainers. You were still the only person who knew me before I started performing.” Aurora’s mouth tightened despite herself. “You once told a philosophy tutor that Derrida was just gossip for men with scarves.” “He deserved worse.” “You also slept with him.” “One follows the other.” The laugh that escaped Aurora came before she could stop it. It surprised them both. Eva smiled then, and for a breath the old years rose through the silt, student kitchens, cheap vodka, bus fares counted in coins, the strange bright arrogance of youth, how people loved each other badly and called it loyalty. Then Eva’s smile died. “I didn’t come for nostalgia.” “There it is.” “He’s out.” Aurora’s face emptied. “When?” “Two months.” “Why am I hearing this now?” “Because he breached his licence in Bristol, vanished for nine days, and yesterday he walked into my office asking for a copy of his victim contact conditions.” Cold moved through Aurora, clean and immediate. “Is that legal?” “Nothing about him ever cared much for legal.” “You work there. You saw him.” “Yes.” “And you thought of me.” “I thought of Camden. Your face after. The cut under your eye you blamed on a railing. That trick with your left hand when you wanted to leave before the shouting started.” Eva’s gaze dropped to Aurora’s wrist, to the small crescent scar she rubbed without knowing. “I thought of all the ways I got it wrong.” Aurora said nothing. “He asked if I still spoke to you.” “And?” “I said I hadn’t seen you in years.” “That part was true.” “I left the office and came here.” Aurora looked towards Silas. He had turned
slightly
now, enough to see the room in the mirror behind the bottles. His posture had changed. Less barman, more blade kept in a drawer. “How did you find me?” Eva gave a tired half shrug. “Your father once said you would hide above a legal loophole or a pub. Cardiff produces habits. I rang four places before someone in Chinatown mentioned a girl from the Golden Empress who lived over a bar in Soho.” Aurora almost smiled at that. Almost. “So this was not fate.” “God, no. Fate dresses better.” The front door opened. Neither woman looked at it first. They saw the change in Silas. His hand dropped below the counter. His limp vanished as he shifted his
weight
. The man in the flat cap set down his pint without drinking. Eva’s eyes snapped to the entrance, and all the colour left her face. A man stood in the doorway with city grime on his coat and a smile worn thin by years of use. Older now. Heavier at the jaw. The same eyes, flat and bright as wet stones. He saw Aurora, and the smile settled into place. “There you are,” Evan said. Silas lifted the baseball bat from beneath the bar and stepped out into the aisle.
created_at
"2026-03-09T16:32:18.489Z"
3/9/2026, 4:32:18 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
101932
moderation_latency
(null)
generation_time
185610
tokens_prompt
4618
tokens_completion
4227
native_tokens_prompt
4131
native_tokens_completion
6867
native_tokens_completion_images
0
native_tokens_reasoning
3678
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
0.1133325
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_01430209843bdb8d0169aef612931c8195b97eaa382babaeba"
is_byok
false
latency
194
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-1773073938-f6vUzA777SlQk6Qp21ss"
upstream_id
"resp_01430209843bdb8d0169aef612931c8195b97eaa382babaeba"
total_cost
0.1133325
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
15
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
151
tagDensity
0.099
leniency
0.199
rawRatio
0
effectiveRatio
0
98.02%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2526
totalAiIsmAdverbs
1
found
0
adverb
"slightly"
count
1
highlights
0
"slightly"
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)
80.21%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2526
totalAiIsms
10
found
0
word
"grave"
count
1
1
word
"weight"
count
3
2
word
"eyebrow"
count
1
3
word
"silence"
count
2
4
word
"pulse"
count
1
5
word
"charged"
count
1
6
word
"flicked"
count
1
highlights
0
"grave"
1
"weight"
2
"eyebrow"
3
"silence"
4
"pulse"
5
"charged"
6
"flicked"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"let out a breath"
count
1
highlights
0
"let out a breath"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
195
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
0
narrationSentences
195
filterMatches
0
"look"
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
331
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
47
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2526
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
39
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
106
wordCount
1592
uniqueNames
6
maxNameDensity
3.2
worstName
"Aurora"
maxWindowNameDensity
7
worstWindowName
"Aurora"
discoveredNames
Aurora
51
Raven
1
Nest
1
Eva
41
Prague
1
Silas
11
persons
0
"Aurora"
1
"Raven"
2
"Nest"
3
"Eva"
4
"Silas"
places
0
"Prague"
globalScore
0
windowScore
0
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
110
glossingSentenceCount
1
matches
0
"appeared beside the table as if the room had carried him there"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
2526
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
331
matches
0
"had that effect"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
227
mean
11.13
std
14.31
cv
1.286
sampleLengths
0
12
1
1
2
34
3
65
4
6
5
1
6
43
7
83
8
28
9
52
10
4
11
4
12
6
13
39
14
9
15
3
16
3
17
22
18
7
19
3
20
7
21
8
22
15
23
5
24
12
25
12
26
1
27
62
28
16
29
4
30
2
31
3
32
9
33
57
34
5
35
3
36
4
37
15
38
29
39
13
40
4
41
4
42
1
43
6
44
7
45
27
46
3
47
3
48
1
49
4
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
2
totalSentences
195
matches
0
"been mined"
1
"got shushed"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
273
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
331
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1596
adjectiveStacks
0
stackExamples
(empty)
adverbCount
45
adverbRatio
0.02819548872180451
lyAdverbCount
9
lyAdverbRatio
0.005639097744360902
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
331
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
331
mean
7.63
std
7.39
cv
0.968
sampleLengths
0
12
1
1
2
10
3
24
4
27
5
14
6
24
7
6
8
1
9
6
10
11
11
10
12
7
13
9
14
11
15
40
16
32
17
5
18
2
19
2
20
5
21
14
22
14
23
23
24
7
25
8
26
4
27
4
28
6
29
13
30
6
31
20
32
9
33
3
34
3
35
7
36
6
37
2
38
4
39
3
40
7
41
3
42
7
43
8
44
6
45
9
46
5
47
12
48
12
49
1
43.66%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
21
diversityRatio
0.23867069486404835
totalSentences
331
uniqueOpeners
79
81.30%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
4
totalSentences
164
matches
0
"Then the face settled into"
1
"Only her wrist gave her"
2
"Somewhere a man laughed too"
3
"Then Eva’s smile died."
ratio
0.024
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
39
totalSentences
164
matches
0
"She caught the tumbler before"
1
"His silver signet ring flashed"
2
"He followed Aurora’s stare to"
3
"He saved words the way"
4
"She looked wrong inside it,"
5
"Her hair sat in a"
6
"She had lost flesh from"
7
"Her mouth had thinned with"
8
"Her hand moved in neat"
9
"He had that effect on"
10
"She did neither."
11
"She used to move as"
12
"He watched her long enough"
13
"She set a tumbler of"
14
"Her nails were short and"
15
"It held no joy and"
16
"It had weight."
17
"She kept them flat."
18
"It stopped them from fidgeting."
19
"Her throat worked."
ratio
0.238
33.17%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
140
totalSentences
164
matches
0
"The glass slipped in Aurora’s"
1
"Gin splashed over her knuckles"
2
"She caught the tumbler before"
3
"The woman by the green-lit"
4
"The neon from the sign"
5
"Silas glanced up from the"
6
"His silver signet ring flashed"
7
"He followed Aurora’s stare to"
8
"That was one of his"
9
"He saved words the way"
10
"Eva came in and let"
11
"The Raven’s Nest took her"
12
"She looked wrong inside it,"
13
"Aurora remembered a different Eva."
14
"Rings on half her fingers."
15
"A laugh that entered a"
16
"This Eva wore a black"
17
"Her hair sat in a"
18
"She had lost flesh from"
19
"Her mouth had thinned with"
ratio
0.854
30.49%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
164
matches
0
"Now she checked sightlines in"
ratio
0.006
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
56
technicalSentenceCount
1
matches
0
"The woman by the green-lit entrance stood half in shadow, one hand still on the door as if she had not decided whether to enter or flee."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
15
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
14
fancyCount
1
fancyTags
0
"Aurora repeated (repeat)"
dialogueSentences
151
tagDensity
0.093
leniency
0.185
rawRatio
0.071
effectiveRatio
0.013
88.8947%