NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX41FQZ14WXGF0RFAEE4R9XJ
Run Details
Model:
GPT-5.6 Terra (Reasoning)
Test:
Bad Writing Habits
Scenario:
Romance: separated couple reunites
Duration:
33.1s
Cost:
$0.039306
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)
86.69%
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)
56.90%
Name drop frequency
(details)
99.49%
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)
46.08%
Sentence opener variety
(details)
75.19%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
16.39%
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)
89.3582%
Overall
Model input
System
You are an expert and award-winning novel writer in the dark Romance 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="4415" name="Lucien Moreau" aliases="Lucien, Luc, the Frenchman" pronouns="he/him" species="Half-Demon" storyRole="Ally"> <eyeColor>heterochromatic — one amber, one black</eyeColor> <hair>slicked-back platinum blond</hair> <height>5'11"</height> <age>32</age> <cane>ivory-handled cane that conceals a thin blade</cane> <dress>tailored charcoal suits</dress> <description>An impeccably dressed fixer and information broker in London's supernatural underworld. He speaks four languages fluently.</description> <backstory>Born in Marseille to a human mother and a demon father from the realm of Avaros.</backstory> </character> <location id="858" name="Eva's Flat" aliases="Eva's place, the flat on Brick Lane" realm="Earth"> <cat>tabby cat named Ptolemy</cat> <security>three deadbolts on the front door</security> <description>A cramped one-bedroom flat above a curry house on Brick Lane, East London. Every surface is covered with books, scrolls, and research notes.</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 romance genre. Two people who parted on complicated terms are forced together again when one shows up unannounced at the other's flat. There's history between them — attraction, hurt, and things left unsaid. Write the scene from the moment the door opens. 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 third deadbolt scraped free
beneath Aurora’s thumb, and Lucien Moreau stood on the other side of Eva’s door with blood on his ivory cane.
He wore charcoal wool and
a white shirt open at the throat.
Someone had torn one sleeve
from cuff to elbow.
His platinum hair had come
loose from its usual hard shine, a pale strand falling across one mismatched eye. Aurora kept the chain on. “You know how bells work.” “Your building has no bell.” “It has windows. Stones. A pavement full of people with lungs.”
Lucien rested both hands over
the silver head of his cane.
Blood had dried in the
grooves around his knuckles. The amber eye held her.
The black one held everything
else. “I had a less theatrical plan,” he said. “It collapsed.” “Pity.”
A thud rolled up from
the curry house below. Ptolemy shot from the kitchen, striped tail puffed twice its size, then vanished beneath Eva’s sofa.
Lucien’s gaze flicked past Aurora’s
shoulder. “Your hostess has acquired a cat.” “Eva acquired him. He owns the furniture.” “An enviable arrangement.” “Why are you here?”
His mouth shifted, not a
smile.
Lucien had once smiled against
the inside of her wrist, his lips warm beside the small crescent scar.
He had called it a
moon cut from her skin.
Then he had vanished for
six weeks without a word, leaving only a pressed black rose in an envelope with no name on it.
That had been nine months
ago.
He looked down at the
blood on his cane. “May I come inside?” “No.” “Aurora.” “You used my name. That must mean the world is ending.” “Not the world. A district, if fortune turns ugly.” “Your fortune always turns ugly. It wears cufflinks and speaks French.” His jaw tightened.
The small crack pleased her
more than it should have. “A man died in my office.” “Call someone who enjoys corpses.” “He died asking for you.”
The chain went still between
her fingers. Lucien watched the change land.
He had always watched too
closely. During those weeks when she had thought he cared, his attention had
felt like sunlight through smoked glass
. Warm enough to stand in. Dark enough to hide in. Then she had learned better. “Who?” she asked. “He gave no name.” “Convenient.” “He had no tongue.” Aurora stared at him. Lucien reached into his inner pocket. Aurora’s body moved before her mind caught up.
Her hand slid beneath the
hem of her jumper and closed around the small knife taped against her ribs.
His gaze lowered to the
movement. “Still carrying steel.” “Still arriving armed at women’s doors.”
He withdrew a folded square
of paper between two clean fingers. “This was sewn beneath his left eyelid.” “Jesus.” “Not a name I heard him invoke.” “Put it through the gap.” Lucien crouched with a wince that he concealed too late. Aurora saw the dark stain spreading beneath his torn sleeve. The scent reached her then, sharp as coins held too long in a fist, with something burnt beneath it. Not human blood. The air around Lucien carried the dry, bitter trace of Avaros.
He pushed the paper through
the narrow space below the chain. Aurora picked it up. The paper felt warm. A symbol covered one side in black ink, a circle broken by three hooked lines. Eva had filled half her notebooks with marks like it, but Aurora recognised this one from a page she wished she had never found. A seal of binding. Not one used to summon demons. One used to keep them from leaving. On the other side, someone had written her name. Not Aurora. MALPHORA. The old name made the cramped hall shrink around her. Lucien rose. “Let me in.” “No.” “Someone has found what you are called below.” “You told me that name was dead.” “I told you it was buried.” “You’re splitting hairs.” “No. I am telling you graves open.” Aurora looked over her shoulder at the flat. Books leaned in wounded towers from every available surface. Scrolls carpeted Eva’s dining table. A chipped blue mug sat beside an open volume on Welsh death rites. Eva had gone to Whitechapel with a bag of chalk, three brass pins, and strict instructions not to let anyone through the door. That last part sat badly now. Lucien had come to this flat before.
He had stood in this
hall with his coat folded over one arm, his cane in the other hand, while Eva had accused him of tracking mud over a seventeenth-century warding diagram.
He had kissed Aurora in
the narrow kitchen after, slow and merciless, his fingers under her chin while Ptolemy’s predecessor, a one-eyed black cat named Beelzebub, had watched from the counter.
He had also left from
this hall. No kiss. No warning. Nothing but absence. Aurora shut the door in his face. The chain rattled as she slid it free. When she opened it again, Lucien did not move. “Take your shoes off,” she said. His brows rose. “Your carpet has a thing about blood.” “Of course it does.” “And if you stain Eva’s rug, I’ll let her curse your reproductive organs into decorative spoons.” “That image will sustain me through difficult times.”
He stepped inside, then bent
with
grave
care to remove his shoes.
His black socks had a
hole at one heel. The sight struck Aurora with absurd force. Lucien Moreau, fixer to monsters and men, elegant enough to make a morgue
look
like an opera foyer, had a hole in his sock. “You’re injured.” “I have noticed.” “Sit.” “Such authority.” “Sit, Lucien.”
He set the cane against
the wall. The ivory handle clicked against plaster. Aurora hated how
familiar
the sound was.
He crossed to the sofa
and lowered himself onto its edge without disturbing the piles of books. Ptolemy hissed from beneath it. “Your cat has excellent judgement,” Lucien said. “He’s not my cat.” “Even better. He dislikes you on principle.” Aurora fetched Eva’s first-aid tin from the bathroom.
It had a faded cartoon
plaster on the lid and a row of protection runes scratched beneath it. She returned to find Lucien examining the pages spread across the coffee table. His fingers hovered above them but did not touch. “Don’t.” “I have not.” “That was not a compliment.” “No, it was a question.” He looked at her. The black eye
seemed bottomless in the low lamplight
. The amber one caught gold from the bulb overhead. “Why is Eva researching the Ninth Gate?” Aurora set the tin down harder than she meant to. Bottles clinked. “She’s researching a lot of things.” “The Ninth Gate is not a lot of things. It is one thing, and it turns sensible scholars into corpses with excellent libraries.” “She found a reference in a ledger.” “Where?” “Not your business.” Lucien leaned back. Pain tightened the line of his mouth. “Then tell me why a tongueless man arrived at my office with your forbidden name under his eyelid, carrying a seal used by the Keepers of the Ninth Gate.” Aurora pulled a pair of scissors from the tin. “Take off your shirt.” His gaze drifted to her face, then to the scissors. “A request I once found more encouraging.” “That was before you made disappearing your main hobby.” “I did not disappear.” “You left.” “I left because staying would have got you killed.” “And you decided that alone.” “Yes.” The answer came clean and quick. No excuse. No apology wrapped in polished language. Aurora’s fingers closed around the scissors. “You arrogant bastard.” “I have missed your
warmth
.” “Take off the shirt.” Lucien unbuttoned it without haste. Aurora watched despite herself. The shirt fell open over his chest, pale skin marked by old scars that no tailored suit ever revealed. One long mark cut across his ribs, silver and ridged. A fresh wound sat beneath it, angry and black at the edges, as if a blade had carried soot into his flesh. Aurora’s anger shifted shape. She hated that too. “That isn’t blood,” she said. “Some of it is.” “What cut you?” “A covenant knife.” “Those are meant to kill demons.” “Half-demons. It matters to bureaucrats.” “It matters to you.” His fingers paused at the last button. “It mattered to my father.” The air altered. Lucien rarely spoke of his father. His demon blood had always lived in the room with them, unnamed but present, a third body in every
silence
. Aurora cut the sleeve away from his left arm. The wound ran from bicep to wrist, not deep enough to kill him, deep enough to make him shake once when cold air hit it. His hand clenched over his knee. “Hold still.” “You sound like a nurse.” “My mother was a teacher. This is worse.” She cleaned the wound. Lucien’s skin felt warmer than it should have, heat gathering under her fingertips. He did not flinch. He looked at her mouth instead. “Don’t,” she said. “I said nothing.” “You don’t need to.” “Then you remember.” “I remember you lying to me in a graveyard.” “I told you the truth in that graveyard.” “You told me you’d come back.” His throat worked. “I did come back.” “After six weeks.” “I came back to find Evan outside your building with a knife.” The antiseptic bottle slipped from Aurora’s hand and hit the carpet. Lucien caught her wrist before she could bend for it. Not hard. Never hard. His thumb rested over the crescent scar, exactly where his mouth had been all those months ago. “Evan was in London?” she asked. “He was.” “You told me he was gone.” “I told you I had dealt with him.” “And what did that mean?” Lucien’s eyes lowered. The amber one had gone bright. Gold bled through the black pupil until it looked lit from behind. “It meant he would not touch you again.” The room
seemed to
breathe around them. Eva’s papers rustled on the table though no window stood open. “You killed him.” “No.” Aurora pulled her wrist free. Lucien let her go at once. “What did you do?” “I gave him a choice. Cardiff, prison, or a place he would not leave.” “That sounds worse than murder.” “It was kind compared with what I wanted.” She stared at him. Under the rage, beneath the old bruise of abandonment, something dangerous stirred. Not gratitude. Never that. It had teeth. “You had no right.” “No.” “You don’t get to decide who I fear.” “No.” “You don’t get to vanish and call it protection.” His face went blank in the careful way that meant she had struck bone. “No,” he said. A heavy knock slammed into the front door. Ptolemy shrieked from under the sofa. Every page on Eva’s table lifted at once, then dropped flat. Aurora looked towards the hall. Lucien rose, moving between her and the door. He took his cane in one hand. With the other, he caught the edge of his unbuttoned shirt and pulled it closed. Another knock landed. Not fists this time. Something with too many joints tapped against the wood. “Aurora Carter,” a woman called from the corridor. Her voice sounded young. Her voice also scraped like stone dragged over teeth. “Open the door. We have come to collect Malphora.”
created_at
"2026-07-09T18:15:52.044Z"
7/9/2026, 6:15:52 PM
model
"openai/gpt-5.6-terra-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2091
moderation_latency
(null)
generation_time
32378
tokens_prompt
4556
tokens_completion
3269
native_tokens_prompt
4075
native_tokens_completion
2552
native_tokens_completion_images
0
native_tokens_reasoning
136
native_tokens_cached
4072
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
0.0393055
router
(null)
provider_responses
0
endpoint_id
"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id
"resp_0ae3d88947eb68ef016a4fe558202481979ec0355d83435edb"
is_byok
false
latency
234
model_permaslug
"openai/gpt-5.6-terra-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-1783620952-d84sSmMdd6C5YOVhk2Xb"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620952-L3qyb05nOcQnkPK51lu9"
upstream_id
"resp_0ae3d88947eb68ef016a4fe558202481979ec0355d83435edb"
total_cost
0.0393055
cache_discount
0.009162
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
9
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
112
tagDensity
0.08
leniency
0.161
rawRatio
0
effectiveRatio
0
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1878
totalAiIsmAdverbs
0
found
(empty)
highlights
(empty)
100.00%
AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
86.69%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1878
totalAiIsms
5
found
0
word
"flicked"
count
1
1
word
"grave"
count
1
2
word
"familiar"
count
1
3
word
"warmth"
count
1
4
word
"silence"
count
1
highlights
0
"flicked"
1
"grave"
2
"familiar"
3
"warmth"
4
"silence"
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
152
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
1
narrationSentences
152
filterMatches
0
"look"
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
255
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
33
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1878
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
24
unquotedAttributions
0
matches
(empty)
56.90%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
65
wordCount
1289
uniqueNames
9
maxNameDensity
1.86
worstName
"Aurora"
maxWindowNameDensity
3
worstWindowName
"Aurora"
discoveredNames
Aurora
24
Lucien
22
Moreau
2
Eva
9
Avaros
1
Welsh
1
Whitechapel
1
Ptolemy
4
Beelzebub
1
persons
0
"Aurora"
1
"Lucien"
2
"Moreau"
3
"Eva"
4
"Ptolemy"
5
"Beelzebub"
places
0
"Whitechapel"
globalScore
0.569
windowScore
0.667
99.49%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
99
glossingSentenceCount
2
matches
0
"felt like sunlight through smoked glass"
1
"seemed bottomless in the low lamplight"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1878
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
255
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
180
mean
10.43
std
12.67
cv
1.214
sampleLengths
0
25
1
40
2
5
3
5
4
5
5
11
6
31
7
10
8
1
9
25
10
6
11
6
12
7
13
3
14
4
15
58
16
6
17
9
18
4
19
1
20
1
21
11
22
9
23
11
24
13
25
6
26
5
27
5
28
7
29
39
30
5
31
3
32
4
33
1
34
4
35
4
36
33
37
6
38
3
39
6
40
11
41
7
42
1
43
7
44
5
45
53
46
11
47
4
48
4
49
49
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
152
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
212
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
255
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1292
adjectiveStacks
0
stackExamples
(empty)
adverbCount
45
adverbRatio
0.0348297213622291
lyAdverbCount
5
lyAdverbRatio
0.003869969040247678
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
255
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
255
mean
7.36
std
5.57
cv
0.757
sampleLengths
0
25
1
12
2
9
3
19
4
5
5
5
6
5
7
11
8
11
9
9
10
5
11
6
12
8
13
2
14
1
15
9
16
16
17
6
18
6
19
7
20
3
21
4
22
6
23
18
24
10
25
24
26
6
27
9
28
4
29
1
30
1
31
11
32
9
33
11
34
3
35
10
36
6
37
5
38
5
39
7
40
5
41
6
42
18
43
5
44
5
45
5
46
3
47
4
48
1
49
4
46.08%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
10
diversityRatio
0.27058823529411763
totalSentences
255
uniqueOpeners
69
75.19%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
3
totalSentences
133
matches
0
"Then he had vanished for"
1
"Dark enough to hide in."
2
"Then she had learned better."
ratio
0.023
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
39
totalSentences
133
matches
0
"He wore charcoal wool and"
1
"His platinum hair had come"
2
"His mouth shifted, not a"
3
"He had called it a"
4
"He looked down at the"
5
"His jaw tightened."
6
"He had always watched too"
7
"Her hand slid beneath the"
8
"His gaze lowered to the"
9
"He withdrew a folded square"
10
"He pushed the paper through"
11
"He had stood in this"
12
"He had kissed Aurora in"
13
"He had also left from"
14
"His brows rose."
15
"He stepped inside, then bent"
16
"His black socks had a"
17
"He set the cane against"
18
"He crossed to the sofa"
19
"It had a faded cartoon"
ratio
0.293
16.39%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
118
totalSentences
133
matches
0
"The third deadbolt scraped free"
1
"He wore charcoal wool and"
2
"Someone had torn one sleeve"
3
"His platinum hair had come"
4
"Aurora kept the chain on."
5
"Lucien rested both hands over"
6
"Blood had dried in the"
7
"The amber eye held her."
8
"The black one held everything"
9
"A thud rolled up from"
10
"Ptolemy shot from the kitchen,"
11
"Lucien’s gaze flicked past Aurora’s"
12
"His mouth shifted, not a"
13
"Lucien had once smiled against"
14
"He had called it a"
15
"That had been nine months"
16
"He looked down at the"
17
"His jaw tightened."
18
"The small crack pleased her"
19
"The chain went still between"
ratio
0.887
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
133
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
46
technicalSentenceCount
2
matches
0
"A fresh wound sat beneath it, angry and black at the edges, as if a blade had carried soot into his flesh."
1
"His face went blank in the careful way that meant she had struck bone."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
9
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
9
fancyCount
0
fancyTags
(empty)
dialogueSentences
112
tagDensity
0.08
leniency
0.161
rawRatio
0
effectiveRatio
0
89.3582%