NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0P99GS070YK0JK9R1YKZ14
Run Details
Model:
GPT-5.5 (Reasoning, Low)
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
1m 24s
Cost:
$0.102505
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
97.94%
AI-ism adverb frequency
(details)
60.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
79.36%
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)
16.67%
Name drop frequency
(details)
100.00%
Narrator intent-glossing
(details)
34.92%
"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)
61.49%
Sentence opener variety
(details)
38.10%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
54.29%
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)
84.7585%
Overall
Model input
System
You are an expert and award-winning novel writer in the dark Mystery 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="4416" name="Detective Harlow Quinn" aliases="Quinn, Detective Quinn, Harlow" pronouns="she/her" species="Human" storyRole="Antagonist"> <eyeColor>brown</eyeColor> <hair>closely cropped salt-and-pepper</hair> <height>5'9"</height> <age>41</age> <jawline>sharp jaw</jawline> <watch>worn leather watch on her left wrist</watch> <bearing>military precision</bearing> <description>A Metropolitan Police detective with 18 years of decorated service who suspects the clique is involved in criminal activity.</description> <backstory>She lost her partner, DS Morris, during a case three years ago under unexplained circumstances that had supernatural origins she doesn't yet understand.</backstory> </character> <character id="4414" name="Eva Kowalski" aliases="Eva, Evie" pronouns="she/her" species="Human" storyRole="Best Friend"> <eyeColor>green</eyeColor> <hair>curly red</hair> <height>5'4"</height> <age>26</age> <glasses>round glasses</glasses> <satchel>worn leather satchel full of books</satchel> <freckles>freckled complexion</freckles> <nervousHabit>tucking hair behind her left ear</nervousHabit> <description>Aurora's childhood friend and an occult researcher.</description> <backstory>Moved to London two years before Aurora and works as a research assistant at the British Museum's restricted archives. She holds a master's degree in Ancient History from Oxford.</backstory> </character> <location id="856" name="The Veil Market" aliases="Veil Market, the Market, underground market" realm="Earth"> <currentLocation>abandoned Tube station beneath Camden</currentLocation> <entryRequirement>bone token</entryRequirement> <schedule>moves locations every full moon</schedule> <description>A hidden supernatural black market that sells enchanted goods, banned alchemical substances, and information.</description> </location> <item id="2004" name="Veil Compass" aliases="the Compass, shadow compass" type="Tool" origin="The Veil Market"> <casingMaterial>small brass compass</casingMaterial> <faceMarkings>face etched with protective sigils</faceMarkings> <needle>points toward the nearest supernatural rift or portal</needle> <patina>casing has a patina of verdigris</patina> <creator>crafted by a Shade artisan</creator> <description>A compass attuned to supernatural energy.</description> </item> </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 mystery genre. A detective arrives at a crime scene in an unusual location. Something is wrong — the evidence doesn't add up. A colleague is present, offering a different interpretation. Through careful observation and deduction, the detective begins to see what others have missed. 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
Detective Harlow Quinn had one
knee on a dead man’s chest when the brass compass in his fist
began to
scream. Not ring. Not buzz. Scream.
The sound knifed through the
abandoned Tube platform beneath Camden, high and wet and almost human, and every officer in the cordon flinched except Quinn.
She tightened her gloved fingers
around the corpse’s wrist and forced the hand open one stiff knuckle at a time. “Ma’am, I wouldn’t touch that.” “Then it’s fortunate you’re over there,
Patel
.”
DC Imran Patel stopped at
the yellow evidence markers and looked as though he regretted every career choice that had led him underground.
His paper overshoes had already
torn at the heel.
Dust clung to the cuffs
of his suit. Behind him, the old station tunnel swallowed the light from the portable lamps and gave back only grime, tile, and the soft drip-drip of water from somewhere beyond the tracks.
The compass lay in the
dead man’s palm like a thing with a
pulse
. Small. Brass. Green with a patina of verdigris along the hinge.
Someone had etched tiny marks
around its face, too fine to belong to any tourist trinket.
The needle did not point
north. It spun in frantic circles, then snapped towards the mouth of the tunnel.
Quinn’s worn leather watch ticked
against her left wrist. Tick-tock. The compass screamed again. “Evidence bag.”
Patel
did not move. “
Patel
.”
He tore his eyes from
the compass. “Right. Yes.”
The body belonged to a
man in his thirties, though the face made age a difficult bet.
His skin had collapsed tight
over the cheekbones, grey and puckered, as if someone had drawn years out of him through a straw.
He wore a long black
coat lined with pockets, each one bulging.
Quinn had already counted three
stoppered glass vials, a folded map printed on vellum, a silver thimble filled with salt, and a string of small carved bone discs threaded through his belt. One disc had snapped in half. That detail mattered.
She did not yet know
why, but it had the neat, ugly feel of a key broken in a lock. The platform itself made less sense than the body. Old Underground signs hung crooked on tiled walls, their station name painted over in thick black strokes. Stalls lined the far side of the platform where benches should have stood, each one abandoned in haste. A narrow counter displayed jars full of pale insects suspended in amber fluid. Another held watches with no hands. A third stall had collapsed, spilling feathers, coins, and something that
looked like a child’s milk tooth onto the
tiles. Above it all, someone had strung red thread from pillar to pillar. Dozens of little paper charms dangled from it, marked with the same fine sigils as the compass face. The place smelled of dust, paraffin, burnt sugar, and old blood. “Black market,”
Patel
said. Quinn looked at him. He lifted both hands. “Not saying I approve. Just saying it fits. Hidden setup, illegal goods, dead dealer. Camden’s always had layers.” “Camden has tattoo parlours and overpriced cereal cafés. It does not have a bazaar in a sealed Tube station.” “Apparently it does.” A SOCO near the tracks gave a nervous laugh, then coughed when Quinn turned her head.
Patel
edged closer, careful not to cross the bloodless smear that marked where the body had fallen. “We’ve got entry by the north maintenance shaft. Lock cut. CCTV dead in a six-street radius. Victim carries contraband. Looks like a deal went wrong.” “Does it?” “You’ve got a corpse in a market nobody admits exists.” “That describes half of Westminster after midnight.”
Patel
pressed his lips together.
He had the patience of
a good detective and the shoulders of a man who still went to the gym for reasons unrelated to stress. Usually Quinn liked him. Today, his certainty annoyed her.
She took the evidence bag
and guided the compass inside without letting it touch the platform. The moment the plastic sealed, the scream dropped into a muffled whine. The needle kept pointing towards the tunnel. “Cause of death?” “Pathologist’s not calling it down here. Initial view, cardiac event. No obvious wounds. No blood loss.” Quinn looked at the corpse’s open mouth. The tongue had blackened at the edges. Teeth intact. No foam. No vomit. “Name?” “Nothing formal yet. Stallholder, from the look of him. We found tokens in his pocket. Bone, mostly. Some with initials. One with a crown stamped on it.” Quinn’s eyes moved to the belt. “Not tokens. Permits.” “To sell?” “To enter.”
Patel
glanced around the dead market. The portable lamps cast hard shadows across shuttered stalls. Canvas awnings sagged under damp. A painted sign, THE VEIL TAKES NO CREDIT, leaned against a stack of crates. “The Veil,” he read. “Subtle.” “People who hide in plain sight often enjoy a joke.” “You sound as if you’ve seen this before.” Quinn’s jaw tightened. Three years ago, DS Morris had bled out in a locked room that contained no blood. Three years ago, the Met had closed a file with phrases like structural collapse, misadventure, high-risk pursuit. Three years ago, Quinn had found black ash under her fingernails though she had never touched a flame. She rose. “No.”
Patel
studied her face for half a second too long. “Ma’am.” Quinn walked the perimeter. The uniforms had done an adequate job, for uniforms.
They had taped the platform
entrance, logged bodies in and out, and kept the curious at a distance. The trouble lay
not with their discipline, but with their assumptions
.
They had treated the market
as a crime scene built from human motives. Money. Theft. Panic. Violence. Familiar shapes, easy labels. The first wrong thing waited beside the dead man’s left boot. A drag mark, three inches long. Not from the body. The sole tread did not match. Too narrow. A woman’s shoe, perhaps, though Quinn disliked the laziness of that thought. Plenty of men wore narrow shoes. The mark pointed away from the corpse, towards a stall hung with cracked mirrors. “
Patel
.” He joined her. “What do you see?” “Scuff. From the struggle.” “What struggle?” He looked at the corpse, then at the scuff. “He falls, someone steps back.” “Falls how?” “Heart gives out. He grabs the compass. Killer flees.” “Why grab a compass when you’re dying?” “To identify the killer?” “You’ve watched too much telly.” “Occupational hazard.” Quinn crouched again.
Her closely cropped salt-and-pepper hair
brushed the collar of her coat. “If he had a cardiac event, he reached for what mattered. Not a weapon. Not a phone. This.” “The compass.” “The compass pointed before it screamed.” “You can’t know that.” “I can.” Quinn angled her torch over the tiles. “Look.” Fine dust covered the platform, disturbed by boots, overshoes, and the frantic shuffle of first response. Near the dead man’s hand, however, the dust formed a clean crescent. The compass had lain face down at first. Someone had turned it over after he died.
Patel
leaned in. “SOCO?” “No. Their first photograph shows it face up already. The officer who found him?” “PC Laird. He swears he didn’t touch anything.” “Then someone else stayed after the body dropped.”
Patel
’s expression shifted,
not quite doubt, not quite hunger
. Good. A detective needed both. Quinn moved to the mirror stall. The stall had escaped the general ransacking. Seven mirrors hung from hooks, each one no bigger than a serving tray, each frame different. Tarnished silver. Black wood. Bone. One cracked oval mirror reflected Quinn’s face in pieces, sharp jaw here, brown eye there, her leather
watch
sliced into two separate wrists. On the counter beneath them sat an open ledger.
Patel
whistled low. “Now that’s helpful.” “Don’t sound relieved. Helpful things lie.” Quinn read without touching. The handwriting looked cramped, elegant, and spiteful. A. Finch, dream salt, paid in molar. Mrs Venn,
whisper
spool, paid in wedding hair. E.K., rift reading, outstanding. Quinn stopped.
Patel
noticed. “You know E.K.?” “Do you?” “No.” The initials sat in fresh ink. No dust on the line. The entry had not dried long before whatever happened here had happened. Beside it, someone had pressed a small round mark into the page. Not a fingerprint. Too clean. A seal. The shape resembled a door half-open. “Photograph this.”
Patel
signalled the SOCO. “Could be a customer list. Motive’s forming. Debt dispute.” “A debt dispute that shuts down CCTV across six streets and makes forty traders vanish without packing their stock?” “Fear spreads fast.” “Not that fast.” Quinn’s torch dipped beneath the counter. There. A drop of wax on the floor. Blue. Fresh enough to hold the print of a thumb. A burnt match lay beside it, snapped in two.
She followed the line from
wax to counter to hanging mirrors, then to the red thread stretched between pillars. One thread had been cut. Not torn. Cut.
She straightened and scanned the
platform again. “Everyone assumed he died where he fell.” “He didn’t?” “No. He died exactly where someone wanted him.”
Patel
folded his arms. “Explain the leap.” Quinn pointed without looking away from the scene. “Body square to the tunnel. Compass in hand. Thread cut only above his sightline. Mirrors angled towards him, not towards customers. That stallholder didn’t collapse during a sale. He stood here for a ritual, or a con built to look like one.” “A ritual.” “You prefer ‘interactive murder installation’?” “I prefer words that survive in court.” “So do I. That’s why we find the person who staged it.” One of the SOCOs muttered from near the tracks. “Boss?” Quinn turned. “What?” The young woman,
Evans
, held her torch over the ballast beyond the platform edge. “There’s another print.” Quinn stepped down onto the track bed before
Patel
could object. Gravel shifted under her shoes. The air inside the tunnel tasted metallic, like pennies held under the tongue.
Her torch caught a shape
in the dust near the third rail, inactive now but still treated with the old fear. A bare footprint. Small. Human. Toes spread wide. The skin had left a faint dark residue, as if the foot had
been dipped
in ash.
Patel
lowered himself onto the track with more care. “Victim’s?” “He wore boots.” “Second victim?” “No blood.” “Witness, then.” Quinn followed the prints. One, two, three.
They appeared from the tunnel
and stopped beneath the platform edge. No return trail. “Someone climbed up.” “There’d be hand marks.” “Not if they didn’t use hands.”
Patel
stared at her. Quinn gave him nothing. The tunnel beyond the lamps lay sealed by darkness. Old posters clung to the curved walls, their colours leached to bruised ghosts. A beauty advert from another decade smiled down at a line of chalk marks that ran along the brickwork. Not graffiti. Directional symbols. Some matched the compass face.
She lifted the bagged compass
from her coat pocket. The whine rose, eager and ugly. The needle strained towards the dark.
Patel
took half a step back. “We need specialist support.” “We are specialist support.” “Since when?” “Since everyone else decided not to notice.” A clatter rang out from the far end of the platform. Every torch swung. For a second, nothing moved.
Then a book slid from
beneath a torn canvas flap and landed open on the tiles.
Patel
raised his baton. A uniform swore. Quinn climbed back onto the platform and crossed towards the sound with a hand near her shoulder holster. “Met Police. Show yourself.” Silence. She hooked the canvas aside with her torch. A woman crouched behind the stall, one hand clamped around the strap of a worn leather satchel full of books. Curly red hair spilled loose from a hasty knot. Round glasses sat crooked on her freckled face. She had tucked a strand of hair behind her left ear so many times that the curl there looked stretched and damp. Quinn aimed the torch at her eyes. Green. “Name.” The woman swallowed. “Eva Kowalski.”
Patel
breathed out. “E.K.” Eva’s gaze
flicked
to the corpse, then to the compass bag in Quinn’s hand, and whatever colour remained in her face drained. “You shouldn’t have sealed it.” Quinn did not lower the torch. “Interesting first line.” “It isn’t evidence in the way you think.” “Everything is evidence in the way I think.” “That compass points to ruptures. If it screamed, the rupture opened.”
Patel
stepped closer. “You’re under arrest on suspicion of murder.” Eva looked at him as if he had recited bad Latin. “Murder? He was dead before I arrived.” “Convenient.” “He sold me a reading. I came to pay. The Market had emptied.” Her fingers tightened on the satchel strap. “That never happens. Not unless something comes through.” Quinn watched the left hand, the
pulse
in the throat, the eyes. Fear, yes. But not the neat fear of capture. Messier. Older. “You work at the British Museum.” Eva blinked. “Restricted archives.”
Patel
looked at Quinn. “You know her?” “I read.” Eva’s mouth opened, then closed. Her gaze settled on Quinn’s leather
watch
, and something in her face shifted again. Recognition,
not of the woman, but of the damage
. “You’ve seen a rift before.”
Patel
snapped, “Don’t answer that.” Quinn ignored him. “Who was he?” “Marcell Voss. Shade goods, portal trinkets, false prophecies for rich idiots. But that”, Eva pointed at the compass, “that wasn’t false.” “Who killed him?” “No one who left by the entrances.” Quinn stepped closer. “Say that plainly.” Eva licked cracked lips. “The Market moves every full moon. It has rules. Bone token to enter. No iron bargains. No open doors below ground.” She nodded towards the tunnel. “Someone opened one anyway.” A sound rolled out of the dark tunnel. Not a train. The line had been dead for years. This sound had
weight
. A low scrape, followed by a damp pull, as if something large dragged itself over tile and stopped to breathe. Every lamp on the platform
flickered
.
Patel
lifted his baton higher. “What the hell was that?” Eva rose
slowly
, one hand still gripping her satchel, the other reaching towards the sealed compass. “If the needle points at the tunnel, you need to break the bag.” Quinn held the compass away from her. “Why?” “Because if it stops screaming, it means the rift has found a body.” The plastic evidence bag sagged in Quinn’s hand. Inside it, the needle ceased its frantic tremor and pointed, steady as a finger,
not at the tunnel now, but at Patel
. He looked down. A black seam opened across his shadow.
created_at
"2026-04-24T21:28:12.066Z"
4/24/2026, 9:28:12 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4696
moderation_latency
(null)
generation_time
84345
tokens_prompt
4671
tokens_completion
4193
native_tokens_prompt
4157
native_tokens_completion
3300
native_tokens_completion_images
0
native_tokens_reasoning
51
native_tokens_cached
3840
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"
usage
0.102505
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_04bdc2539dfebeb70169ebe06c26a88194b9a0a1c9ea79c968"
is_byok
false
latency
253
model_permaslug
"openai/gpt-5.5-20260423"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777066092-lFge56ct7xW1dR5mKXLA"
session_id
(null)
api_type
"completions"
id
"gen-1777066092-sIzuRxCwrbENys0wbmoN"
upstream_id
"resp_04bdc2539dfebeb70169ebe06c26a88194b9a0a1c9ea79c968"
total_cost
0.102505
cache_discount
0.01728
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
7
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
112
tagDensity
0.063
leniency
0.125
rawRatio
0
effectiveRatio
0
97.94%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2423
totalAiIsmAdverbs
1
found
0
adverb
"slowly"
count
1
highlights
0
"slowly"
60.00%
AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions
(empty)
found
0
"Evans"
1
"Patel"
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
79.36%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2423
totalAiIsms
10
found
0
word
"pulse"
count
2
1
word
"etched"
count
1
2
word
"familiar"
count
1
3
word
"whisper"
count
1
4
word
"scanned"
count
1
5
word
"silence"
count
1
6
word
"flicked"
count
1
7
word
"weight"
count
1
8
word
"flickered"
count
1
highlights
0
"pulse"
1
"etched"
2
"familiar"
3
"whisper"
4
"scanned"
5
"silence"
6
"flicked"
7
"weight"
8
"flickered"
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
217
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
3
hedgeCount
1
narrationSentences
217
filterMatches
0
"watch"
hedgeMatches
0
"began to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
322
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
42
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2423
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
14
unquotedAttributions
0
matches
(empty)
16.67%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
86
wordCount
1761
uniqueNames
16
maxNameDensity
2.04
worstName
"Quinn"
maxWindowNameDensity
4.5
worstWindowName
"Quinn"
discoveredNames
Harlow
1
Quinn
36
Tube
1
Camden
1
Imran
1
Patel
24
Underground
1
Morris
1
Met
1
Fine
1
Venn
1
Evans
1
Latin
1
One
5
Three
3
Eva
7
persons
0
"Harlow"
1
"Quinn"
2
"Imran"
3
"Patel"
4
"Underground"
5
"Morris"
6
"Met"
7
"Venn"
8
"Evans"
9
"One"
10
"Three"
11
"Eva"
places
(empty)
globalScore
0.478
windowScore
0.167
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
123
glossingSentenceCount
2
matches
0
"looked like a child’s milk tooth onto the"
1
"not quite doubt, not quite hunger"
2
"not quite hunger"
34.92%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
4
per1kWords
1.651
wordCount
2423
matches
0
"not yet know why, but it had the neat, ugly feel of a key broken in a lock"
1
"not with their discipline, but with their assumptions"
2
"not of the woman, but of the damage"
3
"not at the tunnel now, but at Patel"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
322
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
179
mean
13.54
std
16.14
cv
1.193
sampleLengths
0
21
1
5
2
45
3
5
4
7
5
70
6
60
7
9
8
1
9
4
10
2
11
4
12
1
13
9
14
84
15
6
16
23
17
83
18
30
19
11
20
4
21
4
22
22
23
19
24
3
25
16
26
42
27
2
28
10
29
7
30
39
31
35
32
3
33
16
34
20
35
1
36
27
37
9
38
2
39
2
40
34
41
5
42
10
43
8
44
3
45
51
46
2
47
1
48
11
49
4
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
217
matches
0
"been dipped"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
278
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
322
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1767
adjectiveStacks
0
stackExamples
(empty)
adverbCount
41
adverbRatio
0.02320316921335597
lyAdverbCount
7
lyAdverbRatio
0.003961516694963215
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
322
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
322
mean
7.52
std
6.59
cv
0.876
sampleLengths
0
21
1
2
2
2
3
1
4
25
5
20
6
5
7
7
8
23
9
9
10
8
11
30
12
14
13
1
14
1
15
9
16
16
17
6
18
13
19
9
20
1
21
4
22
2
23
4
24
1
25
7
26
2
27
17
28
23
29
12
30
32
31
6
32
3
33
20
34
9
35
17
36
18
37
13
38
6
39
20
40
12
41
18
42
11
43
4
44
4
45
4
46
18
47
19
48
3
49
16
61.49%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
12
diversityRatio
0.391304347826087
totalSentences
322
uniqueOpeners
126
38.10%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
2
totalSentences
175
matches
0
"Usually Quinn liked him."
1
"Then a book slid from"
ratio
0.011
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
26
totalSentences
175
matches
0
"She tightened her gloved fingers"
1
"His paper overshoes had already"
2
"It spun in frantic circles,"
3
"He tore his eyes from"
4
"His skin had collapsed tight"
5
"He wore a long black"
6
"She did not yet know"
7
"He lifted both hands."
8
"He had the patience of"
9
"She took the evidence bag"
10
"They had taped the platform"
11
"They had treated the market"
12
"He joined her."
13
"He looked at the corpse,"
14
"Her closely cropped salt-and-pepper hair"
15
"She followed the line from"
16
"She straightened and scanned the"
17
"Her torch caught a shape"
18
"They appeared from the tunnel"
19
"She lifted the bagged compass"
ratio
0.149
54.29%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
142
totalSentences
175
matches
0
"Detective Harlow Quinn had one"
1
"The sound knifed through the"
2
"She tightened her gloved fingers"
3
"DC Imran Patel stopped at"
4
"His paper overshoes had already"
5
"Dust clung to the cuffs"
6
"The compass lay in the"
7
"Someone had etched tiny marks"
8
"The needle did not point"
9
"It spun in frantic circles,"
10
"Quinn’s worn leather watch ticked"
11
"The compass screamed again."
12
"Patel did not move."
13
"He tore his eyes from"
14
"The body belonged to a"
15
"His skin had collapsed tight"
16
"He wore a long black"
17
"Quinn had already counted three"
18
"That detail mattered."
19
"She did not yet know"
ratio
0.811
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
175
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
64
technicalSentenceCount
3
matches
0
"DC Imran Patel stopped at the yellow evidence markers and looked as though he regretted every career choice that had led him underground."
1
"His skin had collapsed tight over the cheekbones, grey and puckered, as if someone had drawn years out of him through a straw."
2
"A low scrape, followed by a damp pull, as if something large dragged itself over tile and stopped to breathe."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
7
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
2
fancyCount
1
fancyTags
0
"Patel snapped (snap)"
dialogueSentences
112
tagDensity
0.018
leniency
0.036
rawRatio
0.5
effectiveRatio
0.018
84.7585%