NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX40Y63MBJ56DSE6EW6SS6VW
Run Details
Model:
GPT-5.6 Luna
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
19.0s
Cost:
$0.014252
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
88.64%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
100.00%
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)
44.42%
Sentence opener variety
(details)
77.52%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
25.89%
Subject-first sentence starts
(details)
38.76%
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)
89.1744%
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 woman at the bar
lifted her glass with Aurora’s childhood toast. “To the ones who got out.”
Aurora stopped with one hand
on the Raven’s Nest door.
The green neon sign bled
through the glass behind her, staining the room’s old maps and black-and-white photographs with a sickly colour.
Somewhere near the shelves, a
bottle broke.
Silas swore once, in a
voice too calm to be anger. The woman turned.
Eva Morgan had cut her
hair to the jaw.
Once it had fallen in
a dark, unruly sheet down her back, and Aurora had known its moods better than her own.
Now it framed a narrow
face sharpened by expensive make-up and something less cosmetic.
A pale line crossed her
lower lip.
Her eyes, which had once
found jokes in every locked door, held no light at all.
Eva stared at Aurora’s delivery
jacket.
Then at the insulated bag
hanging from her shoulder. “Rory?”
Aurora closed the door behind
her. “Not many people call me that.” “I know.”
Silas appeared from behind the
bar, carrying a cloth and an unbroken tumbler. At fifty-eight, he moved with a slight drag in his left leg, but nothing in him looked slow.
His hazel eyes crossed from
Eva to Aurora, measuring the distance between them. “Golden Empress?” he asked. “Yu-Fei’s order.”
Aurora slipped the bag from
her shoulder. “Two roast duck, one salt-and-pepper squid, one portion of noodles. Someone in Flat Fourteen has chosen death by sodium.” Silas held out his hand. “I’ll take it.” “I can deliver it.” “You can also sit down.” He glanced at Eva. “Your friend has been waiting for someone for twenty minutes.”
Eva’s fingers tightened around her
glass. “I wasn’t waiting for her.” “No,” Silas said. “That would make the evening too simple.” Aurora handed him the bag.
The restaurant’s heat clung to
it, soy, ginger and charred skin, a small domestic world sealed inside plastic.
Silas carried it towards the
back corridor, limping only when he thought no one watched.
Eva slid from the bar
stool. “You own this place?” Silas paused. “I own the debts attached to it.” “That wasn’t my question.” “It’s the answer you get.”
He disappeared behind the bookshelf
at the rear. A moment later, the shelves shifted with a soft wooden groan. Aurora heard the hidden room swallow him. Eva watched the bookcase. “Still collecting strays?” “Silas collects information. Strays come free.” “You always did like men with secrets.” Aurora removed her helmet. Straight black hair clung to her cheek.
She pushed it back and
took the stool beside Eva, leaving one empty between them. The bar smelled of spilled beer, lemon peel and old smoke trapped beneath the varnish. Lamps hung low over the counter. Maps of Europe covered one wall, their edges curled like dry skin. In a photograph above the optics, a group of young men stood outside a railway station, all of them smiling at something beyond the frame. Eva looked at Aurora’s left wrist. The small crescent scar showed where her sleeve had ridden up. “You still have it.” “A scar?” “The moon.” “You gave it that name.” “I gave everything a name.” “You gave my bicycle a name.” “Brendan. He deserved one.” Aurora almost smiled. The attempt stopped before it reached her mouth. Eva drank.
Her lipstick left a dark
crescent on the rim. “What are you doing in London?” “Living here.” “That’s not what I meant.” “It’s the answer you get.” The words landed between them, borrowed from Silas and already ruined by use. Eva looked down at her drink. “You look well.” “You look rich.” “I am.” The answer came too fast. Eva
seemed to
hear it after she had spoken.
She turned the glass in
small circles, making the ice click against the sides. “Is that what you wanted?” “No.” “What did you want?” “To stop being poor.” “Same thing, for most people.” Aurora studied her. The coat was black wool, narrow at the waist, with a silver clasp at the throat. No rings. No watch.
Her hands looked bloodless and
carefully
scrubbed. “Where have you been?” Eva’s gaze moved towards the photographs. “Here and there.” “You sent me a postcard from Marseille.” “Did I?” “You wrote, ‘The water’s too blue. Come and see it.’” “Sounds like me.” “You never told me you’d left.” “You were busy.” “I was seventeen.” “You were busy being seventeen.” Aurora placed both hands on the bar. Beneath her right palm, the wood held a faint tackiness.
She rubbed her thumb against
it. “We were both seventeen.” “That was a long time ago.” “Not to me.” Eva flinched.
It was small, but the
movement gave her away.
She lifted her glass again
and found it empty. Silas returned from the hidden room carrying no food, only a fresh bottle of whisky.
He set it on the
bar and removed the stopper. “Your usual?”
he asked Eva
. “I don’t have a usual.” “You had three neat bourbons before your friend arrived.” “Then I’ll have a fourth.” He poured. The whisky caught the low light, amber and cold. Aurora watched his signet ring flash as he withdrew the bottle. Silver, square-faced, worn at the edges. “You know him well?” Eva asked. “Too well,” Silas said. “I know that feeling.”
He left them with the
bottle. Aurora lifted the whisky and smelt oak, smoke, something medicinal. “Why are you here?” Eva pressed her mouth to the glass. “To see you.” “Why?” “I wanted to know if you hated me.” “I don’t.” “That’s worse.” “Why?” “Because hate would mean I mattered.” Aurora turned towards her. “Don’t make this theatrical.” “I’m not. I’ve spent years rehearsing this.” “And you still chose that line?” “I used to be better.” “You used to be many things.” Eva laughed once. It sounded like a cough. Outside, a bus passed, washing the window with white light. For a moment Eva’s reflection floated over the green neon, two faces layered together, neither one belonging to the woman Aurora remembered. “You left because of him,” Eva said. Aurora’s fingers stopped moving. “Evan?” “Is there another?” “You told me to leave Cardiff.” “I told you to get away from him.” “You said London would swallow me.” “It did.” “You knew that.” “I knew it would be kinder than he was.” Aurora looked towards the back room. The bookshelf had returned to its place. A book titled The Decline and Fall of the Roman Empire sat
slightly
crooked. “You vanished after I came here.” Eva’s hand tightened around the tumbler. “I called.” “Once.” “Twice.” “You left messages with my mother.” “I didn’t know where you were.” “You knew where I worked.” “I went there.” Aurora turned back. “When?” “After closing.” “Why didn’t you come in?” Eva looked at her then, and the years opened between them without making a sound. “Because I saw him.” Aurora felt the scar on her wrist itch beneath her sleeve. “Evan?” “He was outside.” “He didn’t know where I lived.” “He knew where you worked. He knew everything.” Aurora drew a breath through her nose. “You could have told me.” “I thought you knew.” “I knew he lied. I didn’t know he followed.” “You never asked.” “You were my friend.” Eva’s eyes dropped. There it was. The old accusation, still breathing under the polished surface. Aurora remembered Eva at fifteen, sitting cross-legged on the floor of her bedroom, painting black stars around her eyes. Eva had promised to burn the world down if anyone hurt Aurora. At seventeen, she had helped Aurora pack a suitcase. At nineteen, she had stopped answering. “I waited,” Aurora said. Eva’s face changed. “For what?” “For you to explain.” “I didn’t have one.” “You had years.” “I had reasons.” “Those aren’t the same.” “No. Reasons are what people use when they want forgiveness without admitting guilt.” The bar had filled around them, though neither had noticed. Two men argued
softly
over a football match near the door. A woman in a red scarf fed coins into the jukebox.
It played three notes and
died. Eva leaned closer. “Do you know what happened to Evan?” Aurora’s throat tightened. “He moved back to Cardiff.” “He didn’t.” “Then I don’t know.” “He went to prison.” Aurora watched the whisky tremble in Eva’s glass. “For what?” “A woman in Birmingham. He put her in hospital.” The words entered the space between them and changed its shape. “Was it you?” Aurora asked. Eva’s pupils narrowed. “No.” “You knew.” “I gave evidence.” Aurora looked at the pale line across Eva’s lip. “Against him?” “Against the man who taught him.” Silas appeared at the far end of the bar.
His expression had lost its
lazy patience. “Eva.” She turned. The room
seemed to
contract around the sound of her name. A phone began vibrating on the counter. Eva glanced at it. The screen displayed no number, only a black field. Silas’s hand moved beneath the bar. “Don’t answer.” Eva’s face emptied. Aurora reached for the phone, but Eva caught her wrist.
Her grip felt hard and
cold. The crescent scar pressed against Eva’s thumb. “You shouldn’t have come here,” Eva said. “I work here.” “Not tonight.” The phone stopped. A second later, every light in the Raven’s Nest went out. The jukebox clicked alive. A voice came through its dead speaker, warped by static and distance. “Laila Carter.” Aurora’s blood turned cold. Silas moved first.
He vaulted the bar with
a violence his injured leg had no right to manage and dragged Aurora down as the front window exploded inwards. Glass tore through the room. Someone screamed. The men by the door dropped behind a table. The woman in the red scarf vanished beneath the bar. Eva remained standing. The black phone lit in her hand. The voice spoke again, clearer now. “Malphora. We know where you are.” Silas seized Eva by the coat and pulled her towards the bookshelf. Aurora scrambled after them as a second impact struck the wall, punching a crater through the photograph of the railway station. The bookshelf swung open. Beyond it, a figure waited in the hidden room, face covered, pistol raised. Silas stopped so
sharply
that Eva collided with him. The masked figure tilted the gun towards Aurora. “Not her,” Eva said. The gun turned back to Eva. “Then tell us where the ledger is.” Eva looked at Aurora. For the first time that night, she looked exactly as she had at seventeen, frightened and furious and ready to set fire to everything. “It’s in her flat,” she said.
created_at
"2026-07-09T18:06:16.71Z"
7/9/2026, 6:06:16 PM
model
"openai/gpt-5.6-luna-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
363
moderation_latency
(null)
generation_time
18620
tokens_prompt
4618
tokens_completion
3136
native_tokens_prompt
4131
native_tokens_completion
2306
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
0.0142518
router
(null)
provider_responses
0
endpoint_id
"eebea444-34a5-4642-a766-cb319471d33a"
id
"resp_0dc78934134debb0016a4fe318c9588193b171fb65c231cf46"
is_byok
false
latency
200
model_permaslug
"openai/gpt-5.6-luna-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-1783620376-fUHggRvBngG0zzPMqTKm"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620376-1GfBhPPsUwrARX901u01"
upstream_id
"resp_0dc78934134debb0016a4fe318c9588193b171fb65c231cf46"
total_cost
0.0142518
cache_discount
0.0037152
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
12
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
134
tagDensity
0.09
leniency
0.179
rawRatio
0
effectiveRatio
0
88.64%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1760
totalAiIsmAdverbs
4
found
0
adverb
"carefully"
count
1
1
adverb
"slightly"
count
1
2
adverb
"softly"
count
1
3
adverb
"sharply"
count
1
highlights
0
"carefully"
1
"slightly"
2
"softly"
3
"sharply"
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)
100.00%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1760
totalAiIsms
0
found
(empty)
highlights
(empty)
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
147
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
2
narrationSentences
147
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
269
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
25
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1760
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
23
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
102
wordCount
1186
uniqueNames
11
maxNameDensity
3.46
worstName
"Eva"
maxWindowNameDensity
6
worstWindowName
"Aurora"
discoveredNames
Aurora
37
Raven
2
Nest
2
Morgan
1
Eva
41
Silas
14
Europe
1
Decline
1
Fall
1
Roman
1
Empire
1
persons
0
"Aurora"
1
"Raven"
2
"Nest"
3
"Morgan"
4
"Eva"
5
"Silas"
6
"Empire"
places
0
"Europe"
globalScore
0
windowScore
0
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
98
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1760
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
269
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
213
mean
8.26
std
9.99
cv
1.209
sampleLengths
0
12
1
6
2
10
3
40
4
3
5
68
6
6
7
9
8
1
9
6
10
6
11
2
12
44
13
4
14
28
15
5
16
3
17
4
18
5
19
4
20
10
21
6
22
5
23
10
24
38
25
6
26
4
27
2
28
7
29
4
30
5
31
26
32
4
33
3
34
6
35
7
36
26
37
58
38
6
39
11
40
4
41
2
42
2
43
5
44
5
45
6
46
4
47
11
48
11
49
6
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
147
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
219
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
269
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1192
adjectiveStacks
0
stackExamples
(empty)
adverbCount
35
adverbRatio
0.02936241610738255
lyAdverbCount
10
lyAdverbRatio
0.008389261744966443
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
269
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
269
mean
6.54
std
4.57
cv
0.699
sampleLengths
0
12
1
6
2
10
3
22
4
7
5
11
6
3
7
9
8
22
9
14
10
7
11
16
12
6
13
9
14
1
15
6
16
6
17
2
18
13
19
18
20
13
21
4
22
9
23
19
24
5
25
3
26
4
27
5
28
4
29
10
30
6
31
5
32
3
33
7
34
5
35
18
36
15
37
6
38
4
39
2
40
7
41
4
42
5
43
8
44
11
45
7
46
4
47
3
48
6
49
7
44.42%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
15
diversityRatio
0.2379182156133829
totalSentences
269
uniqueOpeners
64
77.52%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
3
totalSentences
129
matches
0
"Somewhere near the shelves, a"
1
"Once it had fallen in"
2
"Then at the insulated bag"
ratio
0.023
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
19
totalSentences
129
matches
0
"Her eyes, which had once"
1
"His hazel eyes crossed from"
2
"He glanced at Eva."
3
"He disappeared behind the bookshelf"
4
"She pushed it back and"
5
"Her lipstick left a dark"
6
"She turned the glass in"
7
"Her hands looked bloodless and"
8
"She rubbed her thumb against"
9
"It was small, but the"
10
"She lifted her glass again"
11
"He set it on the"
12
"he asked Eva"
13
"He left them with the"
14
"It sounded like a cough."
15
"It played three notes and"
16
"His expression had lost its"
17
"Her grip felt hard and"
18
"He vaulted the bar with"
ratio
0.147
25.89%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
112
totalSentences
129
matches
0
"The woman at the bar"
1
"Aurora stopped with one hand"
2
"The green neon sign bled"
3
"Silas swore once, in a"
4
"The woman turned."
5
"Eva Morgan had cut her"
6
"A pale line crossed her"
7
"Her eyes, which had once"
8
"Eva stared at Aurora’s delivery"
9
"Aurora closed the door behind"
10
"Silas appeared from behind the"
11
"His hazel eyes crossed from"
12
"Aurora slipped the bag from"
13
"Silas held out his hand."
14
"He glanced at Eva."
15
"Eva’s fingers tightened around her"
16
"Aurora handed him the bag."
17
"The restaurant’s heat clung to"
18
"Silas carried it towards the"
19
"Eva slid from the bar"
ratio
0.868
38.76%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
129
matches
0
"Now it framed a narrow"
ratio
0.008
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
47
technicalSentenceCount
1
matches
0
"Aurora remembered Eva at fifteen, sitting cross-legged on the floor of her bedroom, painting black stars around her eyes."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
12
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
11
fancyCount
0
fancyTags
(empty)
dialogueSentences
134
tagDensity
0.082
leniency
0.164
rawRatio
0
effectiveRatio
0
89.1744%