NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX41B9V5KD4BETWTPE3RPCVT
Run Details
Model:
GPT-5.6 Terra (Reasoning)
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
31.4s
Cost:
$0.036290
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
100.00%
AI-ism adverb frequency
(details)
80.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
73.84%
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)
50.00%
Name drop frequency
(details)
100.00%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
100.00%
Paragraph length variance
(details)
100.00%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
100.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
53.74%
Sentence opener variety
(details)
21.37%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
40.13%
Subject-first sentence starts
(details)
32.05%
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)
88.3707%
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
The suspect vaulted the barrier
and vanished between two stalled buses.
Quinn hit the pavement hard
enough to jar her teeth, caught herself on one palm, and drove on. A taxi horn blared. Tyres hissed over wet tarmac.
She cut across the road
before the next bus could shear her in half. “Police! Stop!”
The man glanced back beneath
a black hood. Lean face. Grey beard.
A strip of blood marked
one cheek.
He clutched something pale against
his chest and plunged into the knot of late shoppers beneath the Camden shopfronts.
Quinn drove an elbow through
the crowd. “Out of the way.” Someone swore at her.
A woman dropped a paper
bag of chips. They scattered under Quinn’s shoes, greasy and pale against the black street.
Her leather watch snagged the
cuff of her coat as she checked the time without slowing. Forty-three seconds since the man had slipped the lock at the storage unit. Thirty since he had stabbed the security guard.
The guard had not looked
surprised when he bled.
That bothered her more than
it should have.
The suspect rounded a corner
beside a closed tattoo parlour.
Quinn followed and found a
narrow lane, brick walls closing around bins swollen with leaking rubbish.
Rainwater chased itself along the
gutter, carrying cigarette ends, red flyers, a crushed plastic syringe.
The man had dropped his
hood. “Darren Vale!” Quinn shouted. “Put it down and face me.” He ran faster.
She saw what he held
now. Not a weapon. A small white disc, polished smooth, drilled through with a hole. Bone. Vale reached a rusted iron gate at the lane’s end. A dead Tube roundel hung above it, half covered by a poster for a band that had split up ten years earlier.
He shoved his hand into
the brickwork beside the gate. The wall opened. Not a door. The brick itself gave way, a vertical seam parting with the scrape of stone on stone. Vale slipped through. Quinn stopped at the threshold. Beyond it, stairs fell into darkness. Old Underground tiles lined the walls, their white glaze cracked and brown with age. A smell rose from below, sharp as metal filings and sweet as rot. No emergency lights. No station sign.
No sound but
water dripping somewhere deep under London. Her radio crackled. “Quinn? Harlow, status?” She pressed the transmit button. “Foot pursuit. Suspect entered a disused access point off Camden High Street.” “Which access point?” “The one that wasn’t there a minute ago.” Silence.
Then the control operator cleared
his throat. “Say again?” Quinn looked at the narrow black stairwell. Vale’s bloody footprint shone on the first step. Another marked the second. “Suspect went underground. Send uniforms to seal the lane. No one enters until I call it.” “Quinn, we need a location.” “I gave you one.”
She clipped the radio back
to her vest.
Her hand rested on the
grip of her service pistol. Procedure said wait for support. Procedure also said Darren Vale was a known fence with three arrests, no convictions, and a talent for leaving frightened people with their throats opened. The storage unit had held six stolen mobile phones, counterfeit passports, and a woman’s handbag soaked in fresh blood. Vale had carried the only lead that still breathed. Quinn stepped through the gap. The wall sealed behind her with a soft, final knock. She spun, drew her pistol, and aimed at solid brick. “No.”
Her voice came back to
her from the tunnel, thin and warped. She holstered the weapon. A locked exit was a problem. Vale remained the priority. The stairs dropped farther than any sensible station stairway. Her boots struck wet stone. Old posters peeled from the walls. One showed a laughing family at a seaside resort. Another advertised a political campaign from decades ago, the candidate’s face scratched out by long, angry nails. At the bottom, a ticket hall waited. No, not waited. Breathed. Quinn held still. The station had no trains, no working lights, no public entrance. Yet yellow bulbs glowed in caged fixtures along the ceiling. The air moved around her with a low, damp exhale. Water threaded down the tiled walls and ran into drains choked with black petals. A turnstile blocked the way ahead. Vale stood on the far side. “Detective.” His voice had changed. Above ground, he had coughed and wheezed through the chase. Now each word landed cleanly. Quinn approached the barrier. “Drop the token.” Vale held up the bone disc.
His fingers trembled, though his
mouth wore a smile. “You’ve no idea where you are.” “I know you stabbed a man.” “He was going to sell her.” “Who?” Vale looked towards the dark passage beyond the turnstile. Lanterns glimmered there, a line of faint gold lights that did not reach the floor. “The girl in the handbag.” Quinn’s jaw tightened. “Name.” “
Lily
Morris.” The ticket hall shrank around her. Vale’s smile vanished. “That name means something to you.” Quinn crossed the space in two strides and slammed both hands against the turnstile. The metal rattled. “Say it again.” “
Lily
Morris. Nineteen. Taken from a flat in Kentish Town. Her father paid three times. The last payment went through a broker called Sadiq. Sadiq used the storage unit. The guard was there to collect.” Quinn stared at him through the bars. “Where is she?” Vale lifted the token. “Down there.” “Then open the gate.” “You don’t have a token.” “Open it.” “You don’t know the rules.” “I know enough.” Vale gave a low laugh that held no humour. “Everyone says that before they go through.” A bell rang in the passage beyond him. One note. Deep enough to stir dust from the ceiling. Shapes moved behind the lanterns. Quinn caught flashes of faces, coats, bare hands, bright cloth. A woman in a red
silk
dress carried a cage full of small pale birds. A boy with antlers branching from his brow pushed a trolley stacked with glass jars. Something tall walked behind them with its head bowed beneath the low ceiling. Vale pressed the bone token into a narrow slot beside the turnstile. The barrier clicked. “Vale, don’t.” He pushed through. Quinn grabbed the rail and vaulted after him. The turnstile snapped shut against her thigh. Pain flared, clean and hot.
She landed badly, rolled, rose
with her pistol raised. Vale had already vanished into the market. The passage opened onto an abandoned platform remade into a bazaar. Stalls crowded the track bed and platform edge beneath strings of coloured bulbs. Old Tube signs hung crooked above them, their names painted over in languages Quinn did not recognise. Traders sold their wares from battered suitcases, butcher’s blocks,
velvet
-lined cases. A chalk-skinned woman offered bundles of teeth threaded on red string. An old man with ink-black eyes weighed powdered blue crystals on brass scales. Two men in funeral suits argued over a stoppered bottle that contained a human
whisper
. The market smelled of incense, damp wool, scorched sugar, and blood. Nobody
looked surprised
to see a detective with a drawn weapon. That
unsettled
Quinn more than the antlered boy.
She lowered the pistol to
her side. Not surrender. Assessment. There were too many bodies, too many exits, too many hands hidden in sleeves and coat pockets. Her warrant card would carry no
weight
here. Her radio gave a hiss, then died. Vale’s blood trail cut across the platform. Quinn followed it past a stall hung with jars of preserved tongues. One of them pressed itself against the glass as she passed. “Officer.” She ignored it. “Officer Quinn.” Her hand went to her gun again. A man sat behind a tea stall built from an old luggage cart. He wore a moss-green suit and white gloves, and his face carried the smooth, blank look of a shop mannequin. Steam curled from a dented silver pot before him. “You know my name?” “I know many names. Yours has attracted attention.” “Where’s Vale?” The man pointed at a row of cups. “Tea first.” “Answer the question.” “Your suspect has no value to me. The object in his hand does.” “He used it to enter.” “It admitted him. It does not belong to him.” Quinn looked down the platform. Vale’s trail ended at a crowd gathered around a stall draped in black cloth. She could see his shoulder pushing through them. The tea seller’s white-gloved finger tapped the counter. “Uninvited police work often ends in awkward arrangements.” “Charge me for trespass.” “You will not enjoy the currency.” Quinn walked on. At the black-draped stall, a woman sat behind a counter filled with antique lockets. Her skin had the grey cast of old ash. She wore a lace veil pinned beneath a crown of iron nails. Vale stood before her, hunched over, both hands wrapped around the bone token. “I brought what you asked for.” “You brought a key.” “I brought payment.” “You brought trouble.” The veiled woman’s eyes found Quinn. They were black from lid to lid. “Metropolitan Police,” Quinn said. “Step away from him.” The shoppers peeled back. Not in panic. With interest. Vale turned. His cheek had gone waxy. The blood on his face had stopped dripping. “Detective, leave.” “Where’s
Lily
Morris?” His eyes
flicked
towards the veiled woman. “She’s not here.” “That handbag says otherwise.” “I took it from Sadiq.” “After you stabbed his guard.” “He had a knife.” “So did you.” Vale opened his mouth, then doubled over. Something moved beneath his coat, a violent ripple travelling from his ribs to his
stomach
. The crowd leaned closer. Quinn drew her pistol. “Hands where I can see them, Vale.” He looked up, his warm brown eyes
flooded with terror
. “It’s inside me.” The veiled woman reached across the counter. “Payment accepted.” Vale screamed. His back arched. The bone token burst from his fist and flew into the woman’s palm. At the same instant, a thin black shape forced its way through the torn skin beneath his jaw. Quinn fired. The shot cracked across the platform. The bullet struck the creature’s head and vanished with a tiny flash, as if it had hit deep water. The thing uncoiled from Vale’s throat, slick and jointed, with too many small hands opening and closing along its length. Vale collapsed at Quinn’s feet. The creature sprang for her face.
created_at
"2026-07-09T18:13:26.513Z"
7/9/2026, 6:13:26 PM
model
"openai/gpt-5.6-terra-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1907
moderation_latency
(null)
generation_time
31091
tokens_prompt
4663
tokens_completion
2877
native_tokens_prompt
4132
native_tokens_completion
2350
native_tokens_completion_images
0
native_tokens_reasoning
120
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
0.03628975
router
(null)
provider_responses
0
endpoint_id
"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id
"resp_0ba09805a71f4bce016a4fe4c69b088190ba940498fecef4e9"
is_byok
false
latency
275
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-1783620806-jW4nwId30Gh0VFQyne4b"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620806-vU4Klru1IWznhY4sueCe"
upstream_id
"resp_0ba09805a71f4bce016a4fe4c69b088190ba940498fecef4e9"
total_cost
0.03628975
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
2
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
64
tagDensity
0.031
leniency
0.063
rawRatio
0
effectiveRatio
0
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1720
totalAiIsmAdverbs
0
found
(empty)
highlights
(empty)
80.00%
AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions
(empty)
found
0
"Lily"
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
73.84%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1720
totalAiIsms
9
found
0
word
"silence"
count
1
1
word
"trembled"
count
1
2
word
"silk"
count
1
3
word
"velvet"
count
1
4
word
"whisper"
count
1
5
word
"unsettled"
count
1
6
word
"weight"
count
1
7
word
"flicked"
count
1
8
word
"stomach"
count
1
highlights
0
"silence"
1
"trembled"
2
"silk"
3
"velvet"
4
"whisper"
5
"unsettled"
6
"weight"
7
"flicked"
8
"stomach"
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
5
narrationSentences
170
matches
0
"looked surprised"
1
"looked surprised"
2
"t in panic"
3
"flooded with terror"
4
"d with terror"
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
0
narrationSentences
170
filterMatches
0
"watch"
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
232
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
35
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1720
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
11
unquotedAttributions
0
matches
(empty)
50.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
59
wordCount
1414
uniqueNames
9
maxNameDensity
1.77
worstName
"Quinn"
maxWindowNameDensity
3.5
worstWindowName
"Vale"
discoveredNames
Camden
1
Quinn
25
Tube
2
Underground
1
London
1
Darren
1
Vale
22
Old
3
One
3
persons
0
"Quinn"
1
"Tube"
2
"Underground"
3
"Darren"
4
"Vale"
5
"One"
places
0
"London"
1
"Old"
globalScore
0.616
windowScore
0.5
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
114
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.581
wordCount
1720
matches
0
"No sound but"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
232
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
147
mean
11.7
std
14.19
cv
1.213
sampleLengths
0
11
1
41
2
2
3
38
4
7
5
4
6
61
7
9
8
8
9
41
10
6
11
10
12
3
13
21
14
42
15
3
16
22
17
5
18
48
19
3
20
3
21
5
22
12
23
3
24
8
25
1
26
7
27
2
28
19
29
16
30
5
31
4
32
48
33
19
34
9
35
5
36
10
37
10
38
1
39
12
40
14
41
46
42
7
43
4
44
48
45
6
46
6
47
1
48
19
49
4
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
170
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
250
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
232
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1421
adjectiveStacks
0
stackExamples
(empty)
adverbCount
30
adverbRatio
0.0211118930330753
lyAdverbCount
4
lyAdverbRatio
0.0028149190710767065
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
232
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
232
mean
7.41
std
5.08
cv
0.686
sampleLengths
0
11
1
18
2
4
3
5
4
14
5
2
6
8
7
2
8
2
9
7
10
19
11
7
12
4
13
4
14
8
15
12
16
16
17
13
18
8
19
9
20
8
21
10
22
16
23
15
24
6
25
4
26
6
27
3
28
6
29
3
30
11
31
1
32
10
33
22
34
10
35
3
36
3
37
16
38
3
39
5
40
6
41
14
42
13
43
3
44
3
45
9
46
3
47
3
48
5
49
12
53.74%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
7
diversityRatio
0.34051724137931033
totalSentences
232
uniqueOpeners
79
21.37%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
156
matches
0
"Then the control operator cleared"
ratio
0.006
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
33
totalSentences
156
matches
0
"She cut across the road"
1
"He clutched something pale against"
2
"They scattered under Quinn’s shoes,"
3
"Her leather watch snagged the"
4
"He ran faster."
5
"She saw what he held"
6
"He shoved his hand into"
7
"Her radio crackled."
8
"She pressed the transmit button."
9
"She clipped the radio back"
10
"Her hand rested on the"
11
"She spun, drew her pistol,"
12
"Her voice came back to"
13
"She holstered the weapon."
14
"Her boots struck wet stone."
15
"His voice had changed."
16
"His fingers trembled, though his"
17
"He pushed through."
18
"She landed badly, rolled, rose"
19
"She lowered the pistol to"
ratio
0.212
40.13%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
131
totalSentences
156
matches
0
"The suspect vaulted the barrier"
1
"Quinn hit the pavement hard"
2
"A taxi horn blared."
3
"Tyres hissed over wet tarmac."
4
"She cut across the road"
5
"The man glanced back beneath"
6
"A strip of blood marked"
7
"He clutched something pale against"
8
"Quinn drove an elbow through"
9
"Someone swore at her."
10
"A woman dropped a paper"
11
"They scattered under Quinn’s shoes,"
12
"Her leather watch snagged the"
13
"The guard had not looked"
14
"That bothered her more than"
15
"The suspect rounded a corner"
16
"Quinn followed and found a"
17
"Rainwater chased itself along the"
18
"The man had dropped his"
19
"He ran faster."
ratio
0.84
32.05%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
156
matches
0
"Now each word landed cleanly."
ratio
0.006
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
60
technicalSentenceCount
1
matches
0
"A dead Tube roundel hung above it, half covered by a poster for a band that had split up ten years earlier."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
2
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
2
fancyCount
1
fancyTags
0
"Quinn shouted (shout)"
dialogueSentences
64
tagDensity
0.031
leniency
0.063
rawRatio
0.5
effectiveRatio
0.031
88.3707%