NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KKAC6DBNYDR0K14QKXRG90QB
Run Details
Model:
GPT-5.4 (Reasoning, Low)
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
1m 2s
Cost:
$0.050605
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
97.42%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
66.48%
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)
81.39%
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)
66.67%
Sentence opener variety
(details)
95.24%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
88.57%
Subject-first sentence starts
(details)
85.71%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
41.67%
Useless dialogue additions
(details)
53.23%
Dialogue tag variety (said vs. fancy)
(details)
92.5459%
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
“Stop!”
The man in the butcher’s
apron glanced back once, saw Detective Harlow Quinn gaining on him, and hurled a crate into her path. Oranges burst across the pavement.
Quinn hit the crate with
her shin, swore, and vaulted the mess instead of slowing.
The alley spat her into
a wider street thick with taxis, neon, and people who knew how to mind their own business.
Her leather watch slapped against
her wrist as she pumped harder. Ahead, the apron flashed white between shoulders, then vanished behind a bus. “Armed police!”
she barked, though she was
alone and the shout was a lie. It worked anyway. A couple
lurched
apart.
A courier dragged his bike
sideways.
Quinn used the gap, cut
round the back of the bus, and found the suspect again at the crossing, one hand clamped to the messenger bag under his coat. Not a butcher. Never had been.
She’d clocked him in The
Raven’s Nest an hour earlier, sitting under a wall map of old Constantinople, drinking ginger ale and pretending to read a
racing
sheet upside down.
The green neon sign above
the entrance had painted his face sickly as he watched the back of the bar instead of the room.
Then the fire alarm had
gone off.
Then someone had slipped out
through the crowd.
Then Quinn had seen the
wrong man leave with the wrong bag.
Now he was thirty feet
ahead and running like he knew London’s bones.
He cut left into Greek
Street. Quinn followed.
Water sheeted off awnings and
rattled through gutters. Tyres hissed.
Her coat dragged at her
shoulders, soaked through.
The city shone black and
gold around her, every lamp doubled in the wet roads.
The suspect kicked through a
puddle and clipped an old woman’s shopping trolley. It tipped. Tins skittered. “Sorry, love,” he called over his shoulder, cheerful as a pub thief. Quinn nearly smiled despite herself. Cocky on a sprint. That told her things. Not desperate, not random, not local police prey. Someone used to heat.
She snatched her warrant card
from her pocket as she ran and flashed it at a uniform outside a kebab shop. “Detain that man!” The constable turned, saw the sprinting figure, and stepped into the path at the wrong angle. The suspect lowered a shoulder. The constable crashed into the takeaway window hard enough to rattle the hanging lamb. Quinn didn’t break stride. “Useless,” she muttered. The suspect shot into an arcade, then out the far side into a narrower lane rank with stale beer, fryer fat and wet brick. Bins lined one wall, lids clapping in the gusts from passing traffic. A cat sprang off a stack of pallets and vanished. Quinn closed the distance. Ten feet. Eight. “Bag on the ground!” He glanced back again. Mid thirties. Narrow face. Broken capillaries around the nose. A pale scar under one ear. Not her first sighting after all.
She’d seen him in a
photo from a seizure in Whitechapel. Courier. Fence. Market runner.
He smiled, reached into his
coat, and
flicked
something behind him. Quinn ducked on instinct. The glass vial
shattered
against the wall beside her. A sharp, sweet stench hit at once, not chemical, not floral, something rotten dressed in perfume. The alley lights blinked. Every shadow along the brickwork shivered and tugged in the same direction, as if the lane had inhaled. Quinn’s
pulse
kicked. Three years ago, Morris had laughed at the first thing that moved where no thing should move. He had only laughed once.
She drove the memory down
and kept running. The suspect burst out onto Charing Cross Road, cut through the edge of traffic, and forced a black cab to brake hard. The driver leaned on his horn. “Wanker!” “Story of the city,” the suspect shouted back. Quinn leapt the bonnet of the cab.
Her soles slapped metal, then
road. Pain sparked up her ankle. She ignored it. The suspect had lost speed at last. Good. He was tiring.
His right arm clamped the
bag too
tightly
now. Protecting contents. Valuable enough to carry by hand, small enough not to weigh him down. Documents, vials, cash, charms, weapons. In her line of work those categories bled into each other more often than they should.
He darted past a closed
record shop and shouldered through a knot of smokers outside a basement jazz bar. One of them grabbed for him. “Watch it!” The suspect stabbed an elbow back. The smoker folded. Quinn slipped through the confusion and saw the man hesitate at the corner, just one hitch, just one choice point. “End of the line,” she said.
He looked at the street
sign, then chose north. Camden. That moved the needle.
By the time she reached
the main road the crowd had thinned and changed. Fewer drinkers, more workers stacking chairs, dragging shutters down, smoking under doorways. Steam rolled from grates. Water drummed from the hems of market tarps. A fried chicken box spun along the kerb, caught in the run-off. Ahead, the suspect flew down the slope towards the canal, then cut into a side street lined with
pawn
shops and shuttered tattoo parlours. Quinn’s earpiece crackled. She thumbed it live. “Quinn.” “Ma’am, you dropped off camera at Soho. Uniforms are asking for direction.” Davies. Young, eager, too loud on radio. “Single male, dark coat, white apron discarded, carrying a black messenger bag. Heading Camden. I want roads closed near the station.” “Camden station?” “Do I sound like I’m at Kew Gardens?” A beat. “No, ma’am.” “Then move.” She killed the line. The suspect skidded round a corner and vanished again. Quinn gained the corner seconds later and found the street empty. No. Not empty. Wrong word. Paused. A row of shops hunched under metal shutters scrawled with tags. Light leaked from one basement stairwell where a betting shop still clung to life behind filthy windows. A laundrette hummed beside it, blue-white and blank as an operating theatre. Water dripped from every ledge.
Somewhere nearby, a train growled
under the city. Quinn slowed at once. Fast men vanished in two ways. Up, into cover. Or down, where sensible people stopped looking. She crouched. Fresh prints cut through the surface grime and the thin wash of water on the pavement, one deep, one lighter. Right foot favouring. He had tweaked something on the hill. The trail led past the betting shop, then broke at a hoarding plastered with gig posters and notices for missing cats, missing bikes, missing girls. A handbill peeled back at one corner. Behind it, a service door stood ajar. Quinn drew her Glock and moved in. The stairwell stank of damp concrete and old electricity. She descended with the muzzle low, each step careful, body angled to the wall. Voices drifted up, blurred and busy. Not one room. A crowd. A market, by the sound of it. Metal clink. Traders calling. A laugh too sharp to be human. Her jaw tightened. At the bottom the corridor split. On one side, old Underground tiles, cream gone nicotine-yellow, curved away into darkness. On the other, a narrow chamber held ticket barriers ripped from their hinges years ago. Someone had painted arrows on the wall in flaking red, then scratched them out and painted new ones. Candles guttered in old wine bottles. Wax bled onto the floor. The city above had one
pulse
. This place had another. She heard
footsteps
ahead and advanced. The corridor widened, then opened onto a disused platform transformed into something obscene and alive. Stalls packed the old station from track bed to tiled wall. Tarpaulins hung where adverts had once been. Strings of low bulbs turned faces hollow. The air held spice, coal smoke, incense, blood, wet wool and something animal under all of it. A woman with silver coins braided into her hair sold jars of pale teeth. A man in a
velvet
coat displayed knives laid on black felt, each blade
etched
with marks that made Quinn’s eyes skid away. Crates of herbs, bottles, bones, prayer cards, old phones, forged passports, cages shrouded with cloth that twitched from inside. Buyers drifted in knots, some in office suits, some in leathers, one in a doctor’s scrubs stained the colour of rust. Nobody
looked surprised
to be here. At the mouth of the platform stood two doormen, broad as fridges, each with a token hanging from a cord at his chest. Bone, polished smooth. The Veil Market. Quinn had heard the name in interviews conducted under caution and in whispers that stopped when she entered the room. She had filed it with ghost stories and organised crime jargon because paperwork demanded categories. Seeing it made those categories
feel
like children’s blocks. The suspect pushed through the crowd halfway down the platform. He risked one more glance back and his smile slipped at last. He had not expected her this far. One of the doormen blocked Quinn with an arm like a gate. “Token.” She kept the gun close to her leg, hidden by her coat. “Police. Move.” “No token, no trade.” “I’m not here to shop.” “You’re not here.” His voice carried no threat because he had no need of one. Quinn showed her warrant card. The man did not even look at it. Around them, the nearest traders had gone quiet. Not afraid. Interested. Her eyes cut to the suspect. He was nearly at the far tunnel now, elbowing past a butcher’s block stacked with wax-sealed parcels.
If he reached cover in
that maze, he
was gone
. Evidence gone with him. So was any chance of understanding why Morris had bled out in a locked room while the CCTV failed and the walls smelled of burnt sugar. “Last warning,” she said. The second doorman sniffed the air near her shoulder. “Copper and old grief. You’re bad for custom.” “Charming.” He nodded towards the entry. “Three rules. No badge, no blood, no names.” “I’ll break all three.” A
flicker
in his expression, not fear, not amusement. Respect, perhaps. Or appetite. “Then pay.” Quinn’s free hand moved before the thought had fully formed. She reached under her shirt, hooked a finger beneath the chain at her throat, and pulled off the small silver ring she wore there, Morris’s wedding band, kept as evidence until evidence had become relic. She dropped it into the doorman’s palm. He weighed it. Looked at her face. Closed his fist. “Not bone.” “Good enough.” Behind him, the crowd shifted and opened for one heartbeat. The suspect was visible again, stepping down from the platform onto the track bed. He turned and lifted two fingers to Quinn in a mocking salute. She moved. The first doorman grabbed for her coat. Quinn smashed the butt of the Glock into his nose, drove her shoulder into his chest, and slipped through the gap before the second could lock it. Someone shouted. A lantern toppled and burst. Oil
raced
across the platform edge in a
wavering
line of fire. “Police!”
Quinn yelled, the word sounding absurd here
. The market exploded. Stallholders snatched goods. Buyers scattered. A cage cloth fell away and something with too many joints scrambled up a pillar. The suspect dropped to the tracks and ran into the tunnel, bag thumping his side. Quinn jumped down after him. The rails rang under her boots. Behind her, one of the doormen roared. Ahead, the suspect hit a switch lantern with his hand as he passed. The tunnel lights died in a stuttering chain, one by one, deeper and deeper into the black.
Then something huge answered from
the dark, and started running towards them both.
created_at
"2026-03-09T22:41:28.966Z"
3/9/2026, 10:41:28 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5810
moderation_latency
(null)
generation_time
61917
tokens_prompt
4663
tokens_completion
3180
native_tokens_prompt
4132
native_tokens_completion
2685
native_tokens_completion_images
0
native_tokens_reasoning
169
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.050605
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_04b77661b750b9310169af4c990d008196afa76e46893e09f4"
is_byok
false
latency
196
model_permaslug
"openai/gpt-5.4-20260305"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773096088-w9MtC6Fon6FjI9AIgPc8"
upstream_id
"resp_04b77661b750b9310169af4c990d008196afa76e46893e09f4"
total_cost
0.050605
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
6
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
31
tagDensity
0.194
leniency
0.387
rawRatio
0
effectiveRatio
0
97.42%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1939
totalAiIsmAdverbs
1
found
0
adverb
"tightly"
count
1
highlights
0
"tightly"
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)
66.48%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1939
totalAiIsms
13
found
0
word
"lurched"
count
1
1
word
"racing"
count
1
2
word
"flicked"
count
1
3
word
"shattered"
count
1
4
word
"pulse"
count
2
5
word
"pawn"
count
1
6
word
"footsteps"
count
1
7
word
"velvet"
count
1
8
word
"etched"
count
1
9
word
"flicker"
count
1
10
word
"raced"
count
1
11
word
"wavering"
count
1
highlights
0
"lurched"
1
"racing"
2
"flicked"
3
"shattered"
4
"pulse"
5
"pawn"
6
"footsteps"
7
"velvet"
8
"etched"
9
"flicker"
10
"raced"
11
"wavering"
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
1
narrationSentences
209
matches
0
"looked surprised"
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
2
hedgeCount
0
narrationSentences
209
filterMatches
0
"watch"
1
"feel"
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
233
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
35
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1939
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
7
unquotedAttributions
0
matches
(empty)
81.39%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
52
wordCount
1822
uniqueNames
20
maxNameDensity
1.37
worstName
"Quinn"
maxWindowNameDensity
2.5
worstWindowName
"Quinn"
discoveredNames
Detective
1
Harlow
1
Quinn
25
Raven
1
Nest
1
Constantinople
1
London
1
Greek
1
Street
1
Whitechapel
1
Morris
3
Charing
1
Cross
1
Road
1
Glock
2
Underground
1
Veil
1
Market
2
Ahead
3
Water
3
persons
0
"Harlow"
1
"Quinn"
2
"Constantinople"
3
"Morris"
4
"Market"
5
"Water"
places
0
"Raven"
1
"London"
2
"Greek"
3
"Street"
4
"Whitechapel"
5
"Charing"
6
"Cross"
7
"Road"
globalScore
0.814
windowScore
0.833
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
126
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1939
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
233
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
98
mean
19.79
std
23.01
cv
1.163
sampleLengths
0
1
1
23
2
65
3
14
4
42
5
6
6
81
7
13
8
8
9
50
10
12
11
25
12
21
13
3
14
35
15
4
16
3
17
53
18
4
19
40
20
11
21
51
22
3
23
22
24
8
25
28
26
1
27
8
28
77
29
25
30
2
31
29
32
6
33
9
34
1
35
4
36
74
37
7
38
1
39
12
40
7
41
21
42
2
43
8
44
2
45
2
46
2
47
4
48
20
49
5
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
209
matches
0
"was gone"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
319
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
233
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1826
adjectiveStacks
0
stackExamples
(empty)
adverbCount
57
adverbRatio
0.0312157721796276
lyAdverbCount
6
lyAdverbRatio
0.0032858707557502738
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
233
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
233
mean
8.32
std
6.64
cv
0.798
sampleLengths
0
1
1
23
2
5
3
15
4
22
5
11
6
12
7
14
8
3
9
4
10
6
11
29
12
3
13
3
14
30
15
24
16
7
17
8
18
12
19
13
20
6
21
2
22
8
23
2
24
8
25
15
26
13
27
2
28
2
29
12
30
5
31
4
32
4
33
8
34
4
35
21
36
3
37
16
38
5
39
14
40
4
41
3
42
24
43
12
44
10
45
4
46
2
47
1
48
4
49
4
66.67%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
13
diversityRatio
0.4334763948497854
totalSentences
233
uniqueOpeners
101
95.24%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
5
totalSentences
175
matches
0
"Then the fire alarm had"
1
"Then someone had slipped out"
2
"Then Quinn had seen the"
3
"Somewhere nearby, a train growled"
4
"Then something huge answered from"
ratio
0.029
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
37
totalSentences
175
matches
0
"Her leather watch slapped against"
1
"she barked, though she was"
2
"It worked anyway."
3
"She’d clocked him in The"
4
"He cut left into Greek"
5
"Her coat dragged at her"
6
"he called over his shoulder,"
7
"She snatched her warrant card"
8
"He glanced back again."
9
"She’d seen him in a"
10
"He smiled, reached into his"
11
"He had only laughed once."
12
"She drove the memory down"
13
"Her soles slapped metal, then"
14
"She ignored it."
15
"He was tiring."
16
"His right arm clamped the"
17
"He darted past a closed"
18
"He looked at the street"
19
"She thumbed it live."
ratio
0.211
88.57%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
130
totalSentences
175
matches
0
"The man in the butcher’s"
1
"Oranges burst across the pavement."
2
"Quinn hit the crate with"
3
"The alley spat her into"
4
"Her leather watch slapped against"
5
"she barked, though she was"
6
"It worked anyway."
7
"A couple lurched apart."
8
"A courier dragged his bike"
9
"Quinn used the gap, cut"
10
"She’d clocked him in The"
11
"The green neon sign above"
12
"He cut left into Greek"
13
"Water sheeted off awnings and"
14
"Her coat dragged at her"
15
"The city shone black and"
16
"The suspect kicked through a"
17
"he called over his shoulder,"
18
"Quinn nearly smiled despite herself."
19
"That told her things."
ratio
0.743
85.71%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
3
totalSentences
175
matches
0
"Now he was thirty feet"
1
"By the time she reached"
2
"If he reached cover in"
ratio
0.017
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
72
technicalSentenceCount
0
matches
(empty)
41.67%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
6
uselessAdditionCount
1
matches
0
"Quinn yelled, the word sounding absurd here"
53.23%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
6
fancyCount
3
fancyTags
0
"she barked (bark)"
1
"she muttered (mutter)"
2
"Quinn yelled (yell)"
dialogueSentences
31
tagDensity
0.194
leniency
0.387
rawRatio
0.5
effectiveRatio
0.194
92.5459%