NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX40TAX1ZWVP6K8QP3P9MC9A
Run Details
Model:
GPT-5.6 Terra (Reasoning)
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
31.4s
Cost:
$0.038780
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)
71.67%
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)
93.82%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
100.00%
Paragraph length variance
(details)
100.00%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
100.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
46.68%
Sentence opener variety
(details)
52.91%
Adverb-first sentence starts
(details)
99.37%
Pronoun-first sentence starts
(details)
0.00%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
86.5927%
Overall
Model input
System
You are an expert and award-winning novel writer in the dark Literary Fiction genre. Your readers are hooked on your stories and can't wait to read the book you have in store. <important> - MUST: Start each chapter in medias res (in the middle of action). AVOID talking about the weather, time of day, the position of the sun, or other boring stuff. - The instructions/summary are just a that, a summary. Feel free to add details, stretch sections and add interesting transitions/descriptions/fillers. - When called for it, have fast-paced action, but otherwise take things slow. This is an experience, and not for people with short attention spans. Enjoy the wine, not slurp Red Bull. - Add descriptions when transitioning places/times/etc, or when coming by new places (e.g. a corner shop, a cafe, etc.). But remember: NOT at the start or end of a chapter. - MUST: AVOID ending in internal monologue, reminiscing or waiting for the next day. A good chapter end is when we're ending right when shit hits the fan. We want to have the reader be excited for what comes next. So no reminiscing, contemplating or summarizing the day. It's popcorn time! </important>
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <codex> <character id="4412" name="Aurora Carter" aliases="Rory, Laila, Aurora, Carter, Malphora" pronouns="she/her" species="Human" storyRole="Protagonist"> <eyeColor>bright blue</eyeColor> <hair>straight shoulder-length black</hair> <height>5'6"</height> <age>25</age> <scar>small crescent-shaped scar on her left wrist from a childhood accident</scar> <description>Aurora, referred to by her friends as Rory, is cool-headed, intelligent, and known for quick out-of-the-box thinking.</description> <backstory>Born in Cardiff to an Irish barrister father (Brendan Carter) and Welsh teacher mother (Jennifer Carter née Ellis), Rory reluctantly pursued Pre-Law at Cardiff University. She fled to London at the behest of her childhood friend Eva after leaving an abusive ex named Evan. By day, Rory works part-time as a delivery person for Yu-Fei Cheung's Golden Empress restaurant. She lives in a flat above Silas' bar.</backstory> </character> <character id="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</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> </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 literary fiction genre. Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret. 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
“Don’t say my name.”
Aurora had just set a
pint beneath the brass rail when the man at the end of the bar caught her wrist.
His fingers pressed the small
crescent scar she had carried since childhood. Not hard. Not gentle either.
Her other hand closed around
the bottle neck before she looked at him.
The man wore a charcoal
suit that fitted him too well to belong to the boy she remembered.
His hair had retreated from
his forehead, leaving a clean pale shelf of skin above sharp brows.
A thin white line cut
from his left ear to his jaw.
He had lost weight in
the face, gained it in the shoulders.
His mouth, though, had not
changed.
The same crooked mouth that
had stolen chips from her school lunch and smiled its way out of detentions. “Rhys?”
He let go as if
her skin had burned him. Across the room, Silas Blackwood stopped polishing a glass.
His hazel eyes moved from
Rory to the stranger, then to the hand Rory still held around the bottle. “You know him?” Silas asked. Rhys looked towards Silas first. Calculating.
The old Rhys had counted
cards under tables and told lies with no more strain than breathing.
This newer version did the
same thing, only his suit had taught the gesture better manners. “Not any more,” he said. Rory put the bottle down.
The Raven’s Nest pressed close
around them, dim and narrow, its old maps curling behind smoked glass.
A black-and-white photograph of dockworkers
leaned crooked above the whisky shelves.
The green neon from the
sign outside bled through the front windows and laid a sickly tint across the faces of the late drinkers. “You vanished,” Rory said. “I moved.” “You vanished after my mother asked whether you’d seen me.”
Rhys rubbed at the scar
below his jaw. “Your mother still has a talent for making an ordinary question sound like a charge sheet.” “You remember her, then.” “I remember everything.”
Silas placed the clean glass
beneath the bar.
His silver signet ring tapped
once against the wood. “Rory,” he said, “back room.” “No.” Rhys’s gaze
flicked
to the door hidden behind the bookshelf, then came back to her. His pupils had widened.
He knew enough to fear
a locked door and a man who offered it. “I only need five minutes,” Rhys said. “You used to say that before you borrowed money.” “I paid it back.” “Three years later.” “Plus interest.” “You stole the interest from your father’s till.”
His crooked smile appeared, then
failed. “You kept score.” “Someone had to.” Silas picked up the bottle again and reached for a glass. “Five minutes. You sit where I can see you. If this becomes an old romance, I’ll put the music on and disappoint everybody.” “It wasn’t a romance,” Rory said. Rhys studied her. “That would have been easier, wouldn’t it?” Silas set the glass down with enough force to make the ice jump. “Five minutes,” he repeated. Rhys took the stool opposite Rory’s place behind the bar.
He moved stiffly when he
sat.
His right hand remained in
his jacket pocket. Rory noticed. So did Silas. “You have a drink,” she said. “Then you leave.” “Tea, if you have it.” Silas gave him a flat look. “Whisky, then. Neat.” Rory poured from the bottle closest to hand. The amber liquid caught the low light. Rhys watched it fall, and she saw the boy in him for a second, fourteen years old, watching rain run down the windows of the Cardiff bus station because neither of them wanted to go home.
He had once told her
every house had a particular
silence
.
His house had the silence
of someone hiding a broken plate.
Her house had the silence
of books left open on tables and her parents speaking in careful voices after they thought she had gone upstairs. She had believed him then.
She had believed nearly everything
he said. “What happened to your hair?” she asked. He gave a small laugh. “Hello to you too.” “You had enough of it to annoy teachers.” “I got older.” “You got expensive.” “I got employed.” “At what?” “Consulting.” “Rhys.”
His fingers tightened around the
whisky glass. “Risk management.” Silas looked up from the till. Rory leaned on the bar. “You used to manage risk by setting fire to it.” “I got better.” “You look worse.” The line beneath his left ear pulled taut. He took the drink but did not swallow. She remembered the last time she had seen him. Cardiff Central. Her suitcase had one broken wheel, and Evan had stood beside the ticket barrier with his hands in his pockets, smiling because he knew how much she hated scenes. Rhys had arrived too late, breathless and red-faced, carrying the bag she had left at his flat. He had handed it to Evan. Not to her. Evan had thanked him. Rhys had looked at the bruise beneath Rory’s sleeve, then looked away. After that, London had taken her in its hard mouth. Eva had found her a mattress, then a job lead, then the flat above the Raven’s Nest. Rory learned the streets by delivery route, learned which doorbells worked, which customers liked a joke, which ones watched her too closely through their chains. She had not heard Rhys’s name in six years. “You gave him my bag,” she said. Rhys’s glass stopped halfway to his mouth. “Still there, then.” “What?” “The bruise.” “You remember it.” “I remember you wore a blue jumper in June. I remember you said you’d walked into a door. I remember he stood close enough that you stopped breathing.” “And you gave him my bag.” “He said you were ill.” “You knew he lied.” “I knew something was wrong.” “Same thing.” “No.” Rhys drank then, a fast
swallow that seemed to hurt
. “It isn’t the same thing. It is worse.” The bar shifted around them. Someone laughed too loudly near the dartboard. A pair of tourists argued over a phone charger. The old speakers played a song with a bass line like a slow
pulse
. Rory kept her hands flat on the counter. “Why are you here?” Rhys looked towards the front windows. A black car had pulled up beyond the green glare. Its windows held no reflection. “I needed somewhere that wasn’t mine.” “You chose Soho.” “I chose you.” “That’s not better.” “I know.” For the first time, his voice lost its polish. The words came out scraped and bare. Silas moved along the bar. His limp showed when he passed the second stool, subtle but firm, as though he had made terms with the damaged knee and neither trusted the other. “Who’s outside?” he asked. Rhys did not answer. Silas set a hand on the bar. “Son, that question has a short life.” “Men from my work.” “Risk management?” Rhys’s mouth made that old, useless smile. “More like risk creation.” Rory stared at him. “What did you do?” “What I got paid to do.” “Which was?” “Collect things. Find things. Persuade people to surrender things.” The hand in his pocket shifted. Silas’s gaze dropped to the movement. “Take it out.” Rhys’s face tightened. “Now,” Silas said. Rhys placed a small black mobile on the bar. Blood darkened the cuff of his white shirt. Rory followed the stain to his side. “You’re hurt.” “It’s a graze.” “That’s a lot of blood for a graze.” “It looks dramatic. I’ve always had a flair for it.” “Lift your jacket,” Silas said. “No.” Silas leaned closer. “I did not ask because I enjoy the sound of my own voice.” Rhys’s eyes went to Rory. An old reflex, that look. He used to do it before every bad decision, as if she had signed a secret form agreeing to witness the outcome. She
hated that she
still understood it. “Lift it,” she said. Rhys unbuttoned his jacket. The dark patch had spread over his shirt near the ribs. He pulled the fabric aside. A shallow wound ran across his skin, ugly but not deep. Blood slicked his waist. Silas inspected it without touching. “Whoever fired wanted you walking.” “They wanted the phone walking.” The mobile
vibrated
on the bar. Nobody moved. It
vibrated
again, sharp against the wood. Rory looked at the screen. No name. Only a number. “You brought that here?” she said. “I brought a problem here. The phone came with it.” “Same difference.” “No.” Rhys looked at Silas. “The phone holds account files, recordings, names. Men who buy favours from people who should not sell them. I copied it from a client.” “You stole from your employer,” Rory said. “I stole from men who buy boys from care homes and call it hospitality.” The nearby laughter died in her ears. The glass in Rhys’s hand
trembled
once. He set it down before it could show him up. Silas said nothing for a long moment.
Then he reached below the
bar and pressed a silent button. The bookshelf at the rear clicked open by an inch. “Inside,” he said. Rory did not move. Rhys gave a faint shake of his head. “No. You don’t want this.” “That choice arrived with you,” Silas said. “I can take it away.” “You’ve bled on my counter. That makes it personal.” Rhys looked at Rory again. “I didn’t come to make you clean up after me.” “You came because you knew I would.” His eyes dropped. The answer lay in that movement, six years old and rotten. She came around the bar before she could think better of it. Silas caught her elbow. “Rory.” “He needs pressure on it.” “He needs fewer friends.” She pulled free, grabbed a clean bar towel, and pressed it to Rhys’s side. He flinched but did not make a sound. “Hold that.” He took the towel. “You didn’t call,” she said. “I wrote.” “Once.” “I wrote twelve times.” “I got one postcard.” “Evan intercepted the rest.” Rory’s hand froze. Rhys swallowed. “I sent them to your old address. I thought, after you left, he might, I don’t know, give them to your parents.” “You thought he’d do me a kindness?” “I thought I had already done enough damage.” “That part was accurate.” The phone lit up. A message
appeared beneath the number
. WE CAN SEE THE GREEN SIGN. Silas read it over their shoulders. The room changed around him. The bar owner vanished. The old operative remained, still and narrow-eyed. “Back room,” he said. The front door opened. A man entered with a gun held low beneath his coat.
created_at
"2026-07-09T18:04:10.543Z"
7/9/2026, 6:04:10 PM
model
"openai/gpt-5.6-terra-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3862
moderation_latency
(null)
generation_time
31272
tokens_prompt
4618
tokens_completion
2935
native_tokens_prompt
4131
native_tokens_completion
2516
native_tokens_completion_images
0
native_tokens_reasoning
225
native_tokens_cached
4128
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
0.0387795
router
(null)
provider_responses
0
endpoint_id
"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id
"resp_046b52d9170f6c86016a4fe29ab138819495465967dc39d023"
is_byok
false
latency
574
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-1783620250-lnaAUJA9zhRto1q9WJNv"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620250-TCouCoLlYKxBVFnlRvcG"
upstream_id
"resp_046b52d9170f6c86016a4fe29ab138819495465967dc39d023"
total_cost
0.0387795
cache_discount
0.009288
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
22
adverbTagCount
1
adverbTags
0
"Rhys drank then [then]"
dialogueSentences
110
tagDensity
0.2
leniency
0.4
rawRatio
0.045
effectiveRatio
0.018
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1765
totalAiIsmAdverbs
0
found
(empty)
highlights
(empty)
100.00%
AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0
"Blackwood"
found
(empty)
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
71.67%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1765
totalAiIsms
10
found
0
word
"weight"
count
1
1
word
"calculating"
count
1
2
word
"flicked"
count
1
3
word
"silence"
count
3
4
word
"pulse"
count
1
5
word
"vibrated"
count
2
6
word
"trembled"
count
1
highlights
0
"weight"
1
"calculating"
2
"flicked"
3
"silence"
4
"pulse"
5
"vibrated"
6
"trembled"
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
153
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
1
narrationSentences
153
filterMatches
(empty)
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
241
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
36
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1765
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
29
unquotedAttributions
0
matches
(empty)
33.33%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
79
wordCount
1212
uniqueNames
10
maxNameDensity
2.15
worstName
"Rhys"
maxWindowNameDensity
4
worstWindowName
"Rhys"
discoveredNames
Silas
21
Blackwood
1
Rory
20
Rhys
26
Raven
2
Nest
2
Cardiff
2
Central
1
Evan
3
London
1
persons
0
"Silas"
1
"Blackwood"
2
"Rory"
3
"Rhys"
4
"Raven"
5
"Nest"
6
"Evan"
places
0
"Cardiff"
1
"London"
globalScore
0.427
windowScore
0.333
93.82%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
89
glossingSentenceCount
2
matches
0
"swallow that seemed to hurt"
1
"appeared beneath the number"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1765
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
241
matches
0
"hated that she"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
166
mean
10.63
std
12.73
cv
1.198
sampleLengths
0
4
1
22
2
30
3
84
4
1
5
10
6
28
7
5
8
39
9
5
10
5
11
52
12
4
13
2
14
10
15
24
16
4
17
3
18
17
19
5
20
1
21
33
22
7
23
9
24
4
25
3
26
2
27
8
28
9
29
3
30
34
31
6
32
10
33
13
34
4
35
24
36
5
37
9
38
5
39
6
40
3
41
51
42
47
43
12
44
7
45
9
46
8
47
3
48
3
49
3
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
0
totalSentences
153
matches
(empty)
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
215
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
241
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1216
adjectiveStacks
0
stackExamples
(empty)
adverbCount
40
adverbRatio
0.03289473684210526
lyAdverbCount
8
lyAdverbRatio
0.006578947368421052
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
241
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
241
mean
7.32
std
5.71
cv
0.779
sampleLengths
0
4
1
22
2
12
3
2
4
3
5
13
6
18
7
17
8
12
9
12
10
6
11
19
12
1
13
10
14
9
15
19
16
5
17
5
18
1
19
17
20
16
21
5
22
5
23
17
24
11
25
24
26
4
27
2
28
10
29
8
30
16
31
4
32
3
33
8
34
9
35
5
36
1
37
15
38
4
39
14
40
7
41
9
42
4
43
3
44
2
45
8
46
6
47
3
48
3
49
11
46.68%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
8
diversityRatio
0.26556016597510373
totalSentences
241
uniqueOpeners
64
52.91%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
2
totalSentences
126
matches
0
"Only a number."
1
"Then he reached below the"
ratio
0.016
99.37%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
38
totalSentences
126
matches
0
"His fingers pressed the small"
1
"Her other hand closed around"
2
"His hair had retreated from"
3
"He had lost weight in"
4
"His mouth, though, had not"
5
"He let go as if"
6
"His hazel eyes moved from"
7
"His silver signet ring tapped"
8
"His pupils had widened."
9
"He knew enough to fear"
10
"His crooked smile appeared, then"
11
"He moved stiffly when he"
12
"His right hand remained in"
13
"He had once told her"
14
"His house had the silence"
15
"Her house had the silence"
16
"She had believed him then."
17
"She had believed nearly everything"
18
"He gave a small laugh."
19
"His fingers tightened around the"
ratio
0.302
0.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
118
totalSentences
126
matches
0
"Aurora had just set a"
1
"His fingers pressed the small"
2
"Her other hand closed around"
3
"The man wore a charcoal"
4
"His hair had retreated from"
5
"A thin white line cut"
6
"He had lost weight in"
7
"His mouth, though, had not"
8
"The same crooked mouth that"
9
"He let go as if"
10
"His hazel eyes moved from"
11
"Rhys looked towards Silas first."
12
"The old Rhys had counted"
13
"This newer version did the"
14
"Rory put the bottle down."
15
"The Raven’s Nest pressed close"
16
"A black-and-white photograph of dockworkers"
17
"The green neon from the"
18
"Rhys rubbed at the scar"
19
"Silas placed the clean glass"
ratio
0.937
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
126
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
43
technicalSentenceCount
2
matches
0
"The same crooked mouth that had stolen chips from her school lunch and smiled its way out of detentions."
1
"His limp showed when he passed the second stool, subtle but firm, as though he had made terms with the damaged knee and neither trusted the other."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
22
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
20
fancyCount
1
fancyTags
0
"he repeated (repeat)"
dialogueSentences
110
tagDensity
0.182
leniency
0.364
rawRatio
0.05
effectiveRatio
0.018
86.5927%