NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX41DY1Z8DYJ83683PRNB6FC
Run Details
Model:
GPT-5.6 Terra (Reasoning)
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
44.2s
Cost:
$0.043085
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)
71.66%
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)
33.33%
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)
49.29%
Sentence opener variety
(details)
96.90%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
41.40%
Subject-first sentence starts
(details)
29.07%
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)
90.7214%
Overall
Model input
System
You are an expert and award-winning novel writer in the dark Thriller 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="4417" name="Tomás Herrera" aliases="Tommy, Tomás, Herrera" pronouns="he/him" species="Human" storyRole="Support"> <eyeColor>warm brown</eyeColor> <hair>short curly dark brown</hair> <height>5'10"</height> <age>29</age> <skinTone>olive skin</skinTone> <scar>scar running along his left forearm from a knife attack</scar> <medallion>Saint Christopher medallion around his neck</medallion> <birthplace>Seville, Spain</birthplace> <description>A former paramedic who provides off-the-books medical care for the clique.</description> <backstory>Born in Seville, Spain. He moved to London to work for the NHS but lost his license after administering unauthorized treatments to supernatural patients.</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> <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> </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 thriller genre. A detective is pursuing a suspect through rain-soaked city streets at night. The chase takes them from the street level down into an underground market. The detective must decide whether to follow the suspect into unfamiliar and potentially dangerous territory. 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
Quinn hit the kerb hard
enough to jar her teeth, caught herself on a parked van, and saw the suspect vanish between two delivery lorries. “Stop! Police!”
Her voice broke against the
narrow Soho street and came back in fragments from wet brick.
The runner did not look
round.
A black hood bounced between
the lorries, then cut through a service alley where the bins stood in slick ranks. Quinn vaulted a low chain, boots splashing through a gutter swollen with rainwater.
Her coat dragged at her
thighs.
She had lost one glove
somewhere behind her, but the cold on her bare right hand sharpened her grip on the radio. “Control, Quinn. Foot pursuit. Male, dark hood, grey scarf, heading east from Greek Street towards Charing Cross Road.” Static hissed. “Copy, Detective. Units are circling.” Circling. Too slow.
The suspect burst from the
alley and shoved through a knot of people under the awning of a late-night café.
A woman cried out as
coffee slopped over her hand.
Quinn clipped a metal table
with her hip and sent it skittering across the pavement. “Sorry,”
she snapped, already past
.
The man ran with his
left shoulder held stiff.
Injury, or something tucked beneath
his jacket.
He had dropped a scrap
of cloth at the murder scene on Wardour Street, grey wool with a thread of silver running through it.
Quinn had spent six hours
watching a service entrance opposite The Raven’s Nest after that. Six hours in rain that soaked through her collar and made every passing drunk look guilty.
Then he had stepped out
of Silas’s bar carrying a small leather case handcuffed to his wrist. No one left a bar with a case chained to their body unless the contents bought blood or buried it. He crossed against the lights.
A taxi shrieked to a
halt, tyres spitting water.
The driver leaned on his
horn and filled the street with abuse.
Quinn swung round the bonnet
and kept moving.
Her leather watch struck against
her wrist as she ran.
Its scratched face caught the
glare from a shopfront, then darkness swallowed it.
She had worn that watch
through eighteen years of warrants, riots, bodies in rivers and one hotel siege in Croydon. Morris had called it her lucky
charm
. Morris had died with its strap pressed against his cheek. Ahead, the suspect cut left beneath the green neon sign of The Raven’s Nest. Quinn slowed. The bar’s black windows reflected the street in broken slices. Old maps and black-and-white photographs crowded the walls inside, visible through the glass. The public entrance stood locked. A broad man in shirtsleeves blocked the doorway, smoking beneath a recessed porch. The suspect did not go in.
He slipped through an iron
gate beside the building, into a passage Quinn had marked on no plan. The bouncer saw her.
His cigarette fell from his
mouth. “Private property.” Quinn flashed her warrant card without stopping. “Then I’ll trespass professionally.” He lunged for her arm. Quinn twisted, drove her elbow into the soft place beneath his ribs, and shoved him back against the tiled wall. The man folded with a wet grunt. “Tell Silas his friends are getting careless.” She went through the gate. The passage pinched tight between the bar and a shuttered tailor’s shop. Water poured from a broken drainpipe and hammered her shoulder. The suspect’s shoes slapped ahead, then the sound stopped. Quinn drew her sidearm. A painted door waited at the end of the passage. Someone had marked it with a white circle, crossed by three black lines. Fresh paint bled down the wood. The door stood open. Beyond it, steps descended beneath the city. Quinn approached with her weapon raised. Old posters peeled from the walls, their bright faces swollen and sagging. A dead bulb swung from exposed wire. The air changed by degrees. Rain and exhaust faded behind her. Damp stone, rust, and something sweet took their place. She knew the smell. Morris’s clothes had carried it home from the case that killed him. Not perfume. Not incense. Something cloying, like burnt sugar poured over spoiled meat. Her radio clicked. “Detective Quinn? Update.” She pressed the transmit button. “Suspect entered an underground access point behind The Raven’s Nest. Send uniforms to secure the alley. No one follows me down.” “Received. Detective, hold position. Armed response is eight minutes out.” Quinn stared down the stairs. Eight minutes turned a live suspect into a missing person.
It turned a handcuffed case
into ash, acid, or a package in someone else’s hands.
Whoever had killed Daniel Pike
had carved symbols into his chest and packed his throat with black feathers. The pathologist had found no poison, no blade wounds beyond the ritual cuts, and no reason for the dead man’s heart to hold a trace of saltwater when he had not been near the Thames in three days. Quinn had stopped accepting neat reasons after Morris. She started down. The stairwell ended at a steel security door. A brass plate sat at eye level. NO ENTRY WITHOUT BONE. The suspect had left the door ajar. Quinn crouched beside it. A pale chip lay on the floor, no bigger than a thumbnail.
It bore a drilled hole
and a crude raven
etched
into one side. Bone, polished smooth from use. A token.
She slipped it into an
evidence bag, then eased the door open. Music reached her first.
Not a song she recognised, but a throb of drum
and string that
seemed to
crawl through the concrete. Then light flooded the corridor, amber and blue, spilling around the bend ahead. Quinn moved forward. The abandoned station should have opened onto tracks and platforms.
Instead, it opened onto a
market. Stalls filled the old concourse beneath tiled arches. Their canvas roofs sagged under strings of coloured bulbs. Traders leaned over tables crowded with things no council licence would permit. Glass jars held pale roots suspended in cloudy liquid. A woman in a fox-fur coat sold teeth arranged in
velvet
trays. Beside her, a boy with silver paint beneath his eyes
measured
black powder into paper packets. People moved through the market in clumps and shadows. Some looked ordinary, if ordinary people chose midnight to buy dead flowers and stoppered bottles of green smoke. Others did not bother with disguise. A tall figure with skin like cracked clay haggled over a cage full of white mice. Two women with milk-pale eyes drank something dark from
porcelain
cups. Every face turned towards Quinn. She had entered carrying a gun. The suspect crossed the far end of the concourse, his grey scarf bright beneath the lights. He shoved through a hanging curtain of rusted chain and disappeared into an old platform tunnel. Quinn kept her weapon low but visible. A stallholder with a shaved head and gold wire stitched through one
eyebrow
smiled at her. “Police don’t shop here.” “Good. I hate crowds.” “You came through the wrong door.” “I’m following a murder suspect.” The stallholder glanced towards the chain curtain. “Everyone comes here looking for something.” “Did you see him?” “I saw a man run. Men run for many reasons.” “His left wrist is chained to a case.” The smile left the stallholder’s face. Quinn caught that. A flinch, small but clean. “What’s in the case?” “You ought to leave.” “Not an answer.” “It’s the only gift I’ve got for you.” A hand seized Quinn’s shoulder. She spun, weapon rising. Tomás Herrera stood behind her with both hands raised. His olive skin had gone pale beneath the harsh lights. Rain had flattened his short curls against his forehead. A Saint Christopher medallion gleamed at his throat, caught against the open collar of his dark shirt. “Easy,” he said. “You shoot here, everyone panics. Panic gets expensive.” Quinn lowered the muzzle an inch. “Herrera.” “Detective.” “What are you doing in an illegal market?” “Buying aspirin.” She looked at the jars of fingernails and stoppered smoke around them. “Your chemist has changed.” “My chemist asks fewer questions.” “You lost your licence because you answered the wrong ones.” His jaw tightened. The scar on his left forearm flashed as he reached into his jacket. Quinn raised the gun again. Tomás stopped. “Bone token,” he said. “You left yours in the doorway.” He held out the evidence bag. Quinn had not felt him take it. “You touch police evidence now?” “I stopped it from being noticed. That place runs on rules. You don’t carry a token inside without declaring yourself a guest.” “I’m not anyone’s guest.” “Then you’re meat in a coat.” The market had grown quieter around them. Not silent. The music still
pulsed
. Coins clinked. A child laughed somewhere behind a stall. Yet Quinn felt the attention settle on her with the
weight
of a loaded room. She took the bag from him. “Where did he go?” Tomás looked at the chain curtain. “You saw the scarf.” “I saw it.” “Then we need to talk about why you’re here.” “I’ll put it in simple terms. You tell me where he went, or I arrest you for obstruction.” “You can’t arrest half the people in this room.” “Watch me start.” Tomás leaned closer. His voice dropped. “That case holds a casket heart.” Quinn held still. “A what?” “A human heart, in a box made for it. It keeps someone alive after they ought to be dead. It also gives the owner a leash.” “Who owns the leash?” “That’s the question people kill over.” Daniel Pike had died with his ribs spread like cabinet doors. The pathologist had
reported that his
heart had not been in his chest. At the time, Quinn had assumed an organ trafficker, a butcher with theatre in his blood. “What did Pike have to do with it?” Tomás looked at her then, not at the gun. “You found him.” “You know I did.” “I saw the photographs.” “Where?” “The Raven’s Nest.” That struck harder than it should have. Quinn stepped into him until he had stall shelves at his back. “You saw restricted crime scene photographs in a bar.” “I saw them on a table. Your name was on the folder.” “Whose table?” Tomás’s eyes shifted. The answer sat there, locked behind his teeth. A bottle exploded behind Quinn. She turned as black liquid splashed across the tiles. It hissed, ate a smoking hole through the grout, and filled the air with the stench of rotten eggs. The suspect had come back through the chain curtain. He stood on the platform steps with the leather case still chained to his wrist. His hood had fallen back. He had no face. Smooth skin covered the space where features belonged. No eyes. No nose. No mouth.
Only a seam ran from
forehead to chin, stitched shut with coarse black thread. The market recoiled. Tomás grabbed Quinn’s sleeve. “Don’t let it see you.” “It hasn’t got eyes.” “That’s not how it sees.” The faceless man lifted his free hand. A thin metal blade lay across his palm. He drew it through the stitches on his face. One by one, the threads snapped. Something beneath the skin moved. Quinn fired. The shot tore through the market. Her bullet struck the man’s shoulder and spun him sideways. He hit the tiled wall, yet no blood came. The leather case banged against his hip. The chain curtain whipped around him as he stumbled into the tunnel. Screams broke loose. Stalls slammed shut. Glass
shattered
. The clay-skinned figure overturned a table and
charged
for an exit. A cage burst open and white mice scattered underfoot. Tomás swore in Spanish and clamped a hand over his medallion. “You shot a hollow.” “He had a knife.” “He has no heart. Bullets don’t matter.” “Everything matters when it hits hard enough.” Quinn ran for the platform. Tomás followed, boots scraping over the old tiles. “You don’t know what’s down there!” “I know a suspect ran down there with evidence.” “That thing isn’t your suspect.” “It left Pike’s blood under its fingernails.” “It doesn’t have fingernails.” “Then it bought them.” They reached the chain curtain. Beyond it, an abandoned platform stretched into darkness, its edge marked by cracked yellow lines. The old tracks had vanished beneath black water. Candles floated in saucers along the tunnel walls, each flame bent towards a point far ahead. The faceless man stood at the far end of the platform. He had opened the leather case. Inside lay a human heart, red and wet, beating against black
velvet
. The stitched seam on the creature’s face split wide. A mouth opened where none had been. Then every candle went out, and something huge climbed from the water beneath the tracks.
created_at
"2026-07-09T18:14:52.745Z"
7/9/2026, 6:14:52 PM
model
"openai/gpt-5.6-terra-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1692
moderation_latency
(null)
generation_time
44146
tokens_prompt
4663
tokens_completion
3500
native_tokens_prompt
4132
native_tokens_completion
2803
native_tokens_completion_images
0
native_tokens_reasoning
117
native_tokens_cached
4129
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
0.04308475
router
(null)
provider_responses
0
endpoint_id
"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id
"resp_06e71870a54dd6f5016a4fe51cd72c8196a4c59c4dec8e4247"
is_byok
false
latency
237
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-1783620892-JHzBo9DVK2dtQUPVMkIz"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620892-RzhOIaoBoThnzccHNvwU"
upstream_id
"resp_06e71870a54dd6f5016a4fe51cd72c8196a4c59c4dec8e4247"
total_cost
0.04308475
cache_discount
0.00929025
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
3
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
71
tagDensity
0.042
leniency
0.085
rawRatio
0
effectiveRatio
0
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
2117
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)
71.66%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
2117
totalAiIsms
12
found
0
word
"charm"
count
1
1
word
"etched"
count
1
2
word
"throb"
count
1
3
word
"velvet"
count
2
4
word
"measured"
count
1
5
word
"porcelain"
count
1
6
word
"eyebrow"
count
1
7
word
"pulsed"
count
1
8
word
"weight"
count
1
9
word
"shattered"
count
1
10
word
"charged"
count
1
highlights
0
"charm"
1
"etched"
2
"throb"
3
"velvet"
4
"measured"
5
"porcelain"
6
"eyebrow"
7
"pulsed"
8
"weight"
9
"shattered"
10
"charged"
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
189
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
1
narrationSentences
189
filterMatches
0
"watch"
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
257
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
38
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
2117
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
8
unquotedAttributions
0
matches
(empty)
33.33%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
61
wordCount
1682
uniqueNames
17
maxNameDensity
1.78
worstName
"Quinn"
maxWindowNameDensity
4
worstWindowName
"Quinn"
discoveredNames
Soho
1
Wardour
1
Street
1
Raven
2
Nest
2
Silas
1
Croydon
1
Quinn
30
Daniel
2
Pike
2
Thames
1
Morris
4
Herrera
1
Saint
1
Christopher
1
Spanish
1
Tomás
9
persons
0
"Raven"
1
"Silas"
2
"Quinn"
3
"Daniel"
4
"Pike"
5
"Morris"
6
"Herrera"
7
"Saint"
8
"Christopher"
9
"Tomás"
places
0
"Soho"
1
"Wardour"
2
"Street"
3
"Croydon"
4
"Thames"
5
"Spanish"
globalScore
0.608
windowScore
0.333
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
131
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.472
wordCount
2117
matches
0
"Not a song she recognised, but a throb of drum"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
2
totalSentences
257
matches
0
"worn that watch"
1
"reported that his"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
166
mean
12.75
std
14.47
cv
1.134
sampleLengths
0
25
1
2
2
42
3
41
4
18
5
2
6
5
7
3
8
45
9
5
10
71
11
17
12
20
13
26
14
8
15
50
16
10
17
14
18
2
19
41
20
24
21
10
22
2
23
7
24
4
25
32
26
7
27
5
28
31
29
4
30
29
31
4
32
7
33
45
34
4
35
25
36
3
37
3
38
5
39
21
40
10
41
5
42
81
43
8
44
3
45
15
46
4
47
11
48
30
49
2
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
189
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
283
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
257
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1688
adjectiveStacks
0
stackExamples
(empty)
adverbCount
23
adverbRatio
0.013625592417061612
lyAdverbCount
1
lyAdverbRatio
0.0005924170616113745
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
257
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
257
mean
8.24
std
5.46
cv
0.663
sampleLengths
0
25
1
2
2
16
3
6
4
20
5
13
6
6
7
22
8
18
9
2
10
5
11
1
12
2
13
20
14
10
15
15
16
5
17
9
18
7
19
24
20
15
21
16
22
17
23
20
24
5
25
9
26
12
27
8
28
10
29
13
30
20
31
7
32
10
33
14
34
2
35
10
36
13
37
5
38
13
39
6
40
18
41
4
42
6
43
2
44
7
45
4
46
5
47
20
48
7
49
7
49.29%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
10
diversityRatio
0.31906614785992216
totalSentences
257
uniqueOpeners
82
96.90%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
5
totalSentences
172
matches
0
"Then he had stepped out"
1
"Then light flooded the corridor,"
2
"Instead, it opened onto a"
3
"Only a seam ran from"
4
"Then every candle went out,"
ratio
0.029
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
40
totalSentences
172
matches
0
"Her voice broke against the"
1
"Her coat dragged at her"
2
"She had lost one glove"
3
"she snapped, already past"
4
"He had dropped a scrap"
5
"He crossed against the lights."
6
"Her leather watch struck against"
7
"Its scratched face caught the"
8
"She had worn that watch"
9
"He slipped through an iron"
10
"His cigarette fell from his"
11
"He lunged for her arm."
12
"She went through the gate."
13
"She knew the smell."
14
"Her radio clicked."
15
"She pressed the transmit button."
16
"It turned a handcuffed case"
17
"She started down."
18
"It bore a drilled hole"
19
"She slipped it into an"
ratio
0.233
41.40%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
144
totalSentences
172
matches
0
"Quinn hit the kerb hard"
1
"Her voice broke against the"
2
"The runner did not look"
3
"A black hood bounced between"
4
"Quinn vaulted a low chain,"
5
"Her coat dragged at her"
6
"She had lost one glove"
7
"The suspect burst from the"
8
"A woman cried out as"
9
"Quinn clipped a metal table"
10
"she snapped, already past"
11
"The man ran with his"
12
"Injury, or something tucked beneath"
13
"He had dropped a scrap"
14
"Quinn had spent six hours"
15
"He crossed against the lights."
16
"A taxi shrieked to a"
17
"The driver leaned on his"
18
"Quinn swung round the bonnet"
19
"Her leather watch struck against"
ratio
0.837
29.07%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
172
matches
0
"Whoever had killed Daniel Pike"
ratio
0.006
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
70
technicalSentenceCount
1
matches
0
"Morris’s clothes had carried it home from the case that killed him."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
3
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
3
fancyCount
1
fancyTags
0
"she snapped (snap)"
dialogueSentences
71
tagDensity
0.042
leniency
0.085
rawRatio
0.333
effectiveRatio
0.028
90.7214%