Run: 2026-07-09-01KX41NV0F3P4RF0GRV8KPMCPK

Run Details

Duration:
16.6s
Cost:
$0.015020
Provider:
OpenAI

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

AI
The suspect vaulted the bonnet of a black cab and vanished between two brick terraces. Quinn reached the taxi a second later. The driver leaned on his horn, swearing through the open window. She ignored him, planted one hand on the wet bonnet, and hauled herself over. Her boots struck the pavement hard enough to jar her knees. “Police! Stop!” The figure ahead glanced back. Male. Slim. Dark coat. No hat. A white strip showed at his throat, perhaps a shirt collar, perhaps something wrapped around his neck. Quinn saw his face for less than a second, all sharp cheekbones and frightened eyes, before he cut left through a narrow service lane. Quinn followed. Rain glazed the paving stones and turned the alley into a black chute. Rubbish bags burst beneath her shoulder as she pushed through them. Rotten fruit and hot engine oil filled her nose. Somewhere above, music thudded through a wall. A woman shouted. A bottle broke. The suspect hit a steel gate at the far end. It should have locked him in. He climbed it without slowing. Quinn gripped the bars and looked up. The top bristled with rusted spikes. The suspect swung one leg over, caught his coat, and tore the sleeve free. Then he dropped beyond the gate and disappeared. She checked her left wrist. The worn leather watch had taken a spray of rain. 22:17. “Damn it.” Quinn stepped back, found the lowest crossbar, and climbed. Her hands slipped twice. On the third attempt, she hooked an elbow over the top and dragged herself across. The spikes scraped her coat but missed flesh. She landed in a yard crowded with broken pallets and delivery crates. No suspect. Only rain tapping on corrugated roofs and the thin, electric buzz of a security light. Quinn moved behind the nearest stack of crates. She drew her torch and swept the beam across the yard. A door stood open at the rear of a disused warehouse. The suspect had left muddy prints across the concrete. They led inside. Quinn touched the radio at her shoulder. “Control, Detective Quinn. I’m pursuing a male suspect through a warehouse off Denmark Street. Request immediate units.” Static answered. She tried again. Nothing. The open door breathed out cold air that smelled of damp stone. Quinn crossed the yard with her torch lowered. Her right hand stayed near her holster. Eighteen years on the Metropolitan Police had taught her to respect open doors, dark corners, and suspects who ran as if they knew the ground better than she did. Inside, the warehouse held the remains of a wholesale furniture business. Display cabinets leaned against the walls. Cardboard boxes sagged beneath sheets of mould. Rain dripped through holes in the roof and struck the concrete with a patient tick-tock. The muddy prints stopped beside a service lift. The lift doors stood apart by six inches. Quinn crouched and studied the gap. Fresh scratches marked the steel. Something had forced the doors open from inside. She pressed the call button. The lift groaned below. Quinn drew her pistol. “Metropolitan Police,” she called. “Come out with your hands visible.” The lift rose another foot, then halted. A hand emerged through the gap. Quinn aimed at it. The hand opened. A small object dropped onto the floor. A bone token. It struck the concrete with a dry clack. Quinn kept her weapon raised. The lift doors shuddered. A face appeared in the gap, pale and wet, eyes wide. “Don’t follow me,” the suspect said. “You’ve made that request rather late.” “They’ll hear you.” “Who?” His mouth worked. Blood ran from one nostril. The lift cable gave a violent jerk. The doors slammed together, crushing his fingers. He screamed and pulled back. The lift dropped out of sight. Quinn ran to the shaft. The darkness swallowed the beam of her torch. Far below, metal rattled and a man shouted once. Then came a deep impact that travelled through the walls and up her legs. She looked at the bone token. It had been carved from a small, curved section of bone, smooth from handling. A black line circled its middle. On one side, someone had scratched a symbol that resembled an eye with its lid sewn shut. Quinn picked it up with a folded handkerchief from her pocket. The radio hissed. “Detective Quinn?” She snatched it from her shoulder. “Go ahead.” “Your location?” “Warehouse service entrance, Denmark Street. Suspect entered an underground shaft. Send units and ambulance.” A pause. “Repeat, underground what?” “Just send the units.” The radio crackled again, then died. Quinn stared into the shaft. The lift had reached the bottom. She could see a faint rectangle of yellow light below, far beneath the warehouse floor. The suspect had left her a way down. That made it bait. She searched the lift controls and found a service panel hanging loose. Behind it, cables and a second button waited under a film of grime. Someone had used it recently. Fresh grease darkened the metal. Quinn pressed the button. The lift climbed towards her, empty. She stepped inside. The cage smelled of rust, wet wool, and something sweet that had spoiled. A strip of the suspect’s dark coat clung to one of the doors. Quinn removed it with her gloved fingers. The material felt warm. The doors closed. As the lift descended, the warehouse vanished above her. The walls narrowed into black concrete. Water threaded down the seams. The motor strained like an animal on a chain. Quinn checked her pistol, then slid the bone token into an evidence pouch. The lift stopped. The doors opened on a tiled platform. A disused Tube station spread beyond it, vast and dim. Old posters peeled from the curved walls. Their faces had faded into blank smears, while the lettering remained sharp: routes that no longer existed, stations erased from every modern map. Rusted rails vanished into a tunnel packed with darkness. The yellow light came from hundreds of lamps strung along the platform. People moved beneath them. They wore long coats, veils, leather masks, school uniforms, evening dress. A woman with silver teeth sold vials from a suitcase. A broad man with antlers curling from his temples argued over a stack of paper charms. A child stood beside a cage containing a bird with human fingers. Quinn remained inside the lift. The platform smelt of hot metal, incense, and blood. A bell rang somewhere in the station. The crowd turned towards her. Then a voice spoke from behind the lift. “You brought the police.” Quinn spun. The suspect stood at the mouth of a service tunnel, clutching his crushed hand against his chest. He had lost his coat. His shirt clung to a narrow, muscular frame, and black veins spread from his throat to his jaw. Three figures stood around him. They looked human until Quinn noticed their eyes, pale and glassy, without visible pupils. “I didn’t bring anyone,” the suspect said. “She followed.” One of the figures looked at Quinn. “Show us the token.” Quinn held her pistol at chest height. “You’re under arrest.” A low laugh passed through the market. The woman with the silver teeth shut her suitcase. Glass clicked inside. The suspect shook his head. “You don’t understand where you are.” “Then explain it while lying face down.” “Put the token on the ground.” Quinn moved one step out of the lift. The station seemed to tighten around her. Conversations stopped. Even the lamps gave a faint electrical hum, as if power ran through the air instead of the wires. She had worked raids in crack houses, gun clubs, illegal casinos, and one private clinic beneath a Mayfair townhouse. She had faced men with knives and women with bombs. None of them had made the skin between her shoulders prickle like this. A sign hung above the far staircase. THE VEIL MARKET. The lettering crawled when she looked at it. Not moved, exactly. It rearranged itself in the corner of her sight. Quinn stepped fully onto the platform. The lift doors began to close behind her. The suspect’s face tightened. “No.” Quinn looked at him. “No what?” “You must leave before the bell rings again.” The bell rang. Every lamp went out. Darkness crushed the platform. Someone screamed. The sound came from the crowd, then from the tunnel, then from directly beneath Quinn’s feet. She raised her torch. The beam flickered, caught a dozen faces, and failed. Something brushed her trouser leg. Quinn fired. The shot cracked through the station. Muzzle flash lit the platform in hard white fragments. The bullet struck the tiled wall beside the suspect’s head. He flinched, then smiled. Not with relief. With recognition. The market erupted. Stalls overturned. Vials burst across the ground, releasing green smoke that crawled along the tiles. People ran in all directions, but the crowd did not move like a crowd. It split around invisible bodies. Some fled on two legs. Others dropped to all fours. A thing with a woman’s face and a long, jointed neck climbed the wall above Quinn. Quinn backed towards the lift. The doors had shut. She hit the call button. Nothing happened. The suspect pushed through the panic towards her. “You shot at me?” “You’re welcome to complain at the station.” “They know your name now.” “Who?” The bone token in her pocket grew hot. Quinn pulled it out. The black line around its centre had opened into a narrow red slit. The suspect stopped. Behind him, the three pale-eyed figures sank to their knees. Not in fear. In welcome. The tunnel lights came on one by one, stretching away into the dark. At the far end, something dragged itself along the rails. Metal shrieked under its weight. Quinn lifted her pistol towards the sound. The suspect grabbed her wrist. His fingers felt too strong for a man with a crushed hand. “Don’t look at it,” he whispered. Quinn drove her elbow into his ribs. He folded, and she tore free. The thing on the tracks rose. It had the height of a man, but no face. A police coat hung from its shoulders, soaked through with black water. One sleeve ended in a hand that dragged a familiar silver watch along the rail. Quinn’s breath caught. The watch struck the metal with a bright, thin chime. Tick. Tock. The dead detective’s voice came from the tunnel. “Harlow.”
created_at"2026-07-09T18:19:11.773Z" 7/9/2026, 6:19:11 PM
model"openai/gpt-5.6-luna-20260709"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2443
moderation_latency(null)
generation_time16098
tokens_prompt4663
tokens_completion2850
native_tokens_prompt4132
native_tokens_completion2434
native_tokens_completion_images0
native_tokens_reasoning229
native_tokens_cached4129
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"completed"
service_tier"default"
usage0.0150199
router(null)
provider_responses
0
endpoint_id"eebea444-34a5-4642-a766-cb319471d33a"
id"resp_0cdce6e85abb189e016a4fe61fea6c8194be0a7fb50069c934"
is_byokfalse
latency261
model_permaslug"openai/gpt-5.6-luna-20260709"
provider_name"OpenAI"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer(null)
request_id"req-1783621151-g8XLcoK7qSe9ERHySkBm"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1783621151-9rXXqyHMU3t7xiGBMoGK"
upstream_id"resp_0cdce6e85abb189e016a4fe61fea6c8194be0a7fb50069c934"
total_cost0.0150199
cache_discount0.0037161
upstream_inference_cost0
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
totalTags2
adverbTagCount0
adverbTags(empty)
dialogueSentences32
tagDensity0.063
leniency0.125
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1738
totalAiIsmAdverbs0
found(empty)
highlights(empty)
100.00% AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions(empty)
found(empty)
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
88.49% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1738
totalAiIsms4
found
0
word"electric"
count1
1
word"flickered"
count1
2
word"weight"
count1
3
word"familiar"
count1
highlights
0"electric"
1"flickered"
2"weight"
3"familiar"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches0
maxInWindow0
found(empty)
highlights(empty)
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells2
narrationSentences213
matches
0"t with relief"
1"t in fear"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount2
narrationSentences213
filterMatches
0"watch"
hedgeMatches
0"seemed to"
1"began to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences241
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen29
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1738
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions6
unquotedAttributions0
matches(empty)
43.75% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions40
wordCount1600
uniqueNames6
maxNameDensity2.13
worstName"Quinn"
maxWindowNameDensity3
worstWindowName"Quinn"
discoveredNames
Metropolitan1
Police1
Tube1
Quinn34
One2
Mayfair1
persons
0"Police"
1"Quinn"
places(empty)
globalScore0.438
windowScore0.667
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences126
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1738
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences241
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs152
mean11.43
std12.63
cv1.105
sampleLengths
015
143
22
35
447
52
646
710
86
95
1035
1116
122
1348
142
1515
1619
1711
1812
197
2017
212
223
231
2412
2544
2639
278
288
2919
305
314
324
3310
347
356
364
3710
383
398
4020
416
426
433
441
458
4625
475
4831
496
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences213
matches
0"been carved"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs279
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences241
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1602
adjectiveStacks0
stackExamples(empty)
adverbCount43
adverbRatio0.026841448189762796
lyAdverbCount5
lyAdverbRatio0.003121098626716604
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences241
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences241
mean7.21
std4.64
cv0.643
sampleLengths
015
17
211
314
411
52
65
71
81
92
102
1117
1224
132
1413
1511
169
177
183
193
2010
216
225
237
246
2514
268
275
2810
291
302
319
324
3315
348
3512
362
3715
388
3911
4011
419
423
437
4417
452
463
471
4812
498
47.22% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats15
diversityRatio0.32083333333333336
totalSentences240
uniqueOpeners77
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount6
totalSentences191
matches
0"Somewhere above, music thudded through"
1"Then he dropped beyond the"
2"Only rain tapping on corrugated"
3"Then came a deep impact"
4"Then a voice spoke from"
5"Even the lamps gave a"
ratio0.031
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount36
totalSentences191
matches
0"She ignored him, planted one"
1"Her boots struck the pavement"
2"It should have locked him"
3"He climbed it without slowing."
4"She checked her left wrist."
5"Her hands slipped twice."
6"She landed in a yard"
7"She drew her torch and"
8"They led inside."
9"She tried again."
10"Her right hand stayed near"
11"She pressed the call button."
12"It struck the concrete with"
13"His mouth worked."
14"He screamed and pulled back."
15"She looked at the bone"
16"It had been carved from"
17"She snatched it from her"
18"She could see a faint"
19"She searched the lift controls"
ratio0.188
30.68% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount164
totalSentences191
matches
0"The suspect vaulted the bonnet"
1"Quinn reached the taxi a"
2"The driver leaned on his"
3"She ignored him, planted one"
4"Her boots struck the pavement"
5"The figure ahead glanced back."
6"A white strip showed at"
7"Quinn saw his face for"
8"Rain glazed the paving stones"
9"A woman shouted."
10"A bottle broke."
11"The suspect hit a steel"
12"It should have locked him"
13"He climbed it without slowing."
14"Quinn gripped the bars and"
15"The top bristled with rusted"
16"The suspect swung one leg"
17"She checked her left wrist."
18"The worn leather watch had"
19"Quinn stepped back, found the"
ratio0.859
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences191
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences59
technicalSentenceCount1
matches
0"Eighteen years on the Metropolitan Police had taught her to respect open doors, dark corners, and suspects who ran as if they knew the ground better than she di…"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags2
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount1
fancyTags
0"he whispered (whisper)"
dialogueSentences32
tagDensity0.063
leniency0.125
rawRatio0.5
effectiveRatio0.063
90.3382%