NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX406P8WNZX8XR7MBFTQH35B
Run Details
Model:
GPT-5.6 Luna (Reasoning)
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
15.1s
Cost:
$0.014252
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)
72.49%
AI-ism word frequency
(details)
100.00%
Cliché density
(details)
100.00%
Emotion telling (show vs. tell)
(details)
100.00%
Filter word density
(details)
100.00%
Gibberish response detection
(details)
100.00%
Markdown formatting overuse
(details)
100.00%
Missing dialogue indicators (quotation marks)
(details)
33.33%
Name drop frequency
(details)
100.00%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
100.00%
Paragraph length variance
(details)
99.18%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
94.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
59.73%
Sentence opener variety
(details)
64.10%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
30.51%
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)
89.5136%
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 bonnet
of a black cab and vanished between two shuttered shops.
Quinn reached the crossing three
seconds later, boots skidding on wet tarmac. A horn blared. The cab driver leaned out, shouting something about her parentage.
She ignored him and cut
through the traffic, one hand pressed against her coat to keep the warrant card from bouncing loose.
The suspect had left a
trail.
A smear of blood marked
the brickwork beside the shops. Not much. Four red fingers, dragged at shoulder height. Quinn touched her radio. “Control, Detective Quinn. Pursuit on foot, heading north through Camden Passage. Male, late twenties, dark coat, carrying a small metal case. Possible knife. Send units to intercept at the next junction.” Static answered. She glanced at the radio. The display had gone black. “Of course.”
The narrow passage spat her
into a crowded street. Rain hammered the awnings and turned the pavement into a slick ribbon of reflected signs.
People pushed past with their
collars raised, blind to the chase unfolding around them.
The suspect shouldered through the
crowd without slowing.
Quinn caught a glimpse of
his face in the glass of a closed betting shop. Olive skin. Short curly dark hair.
A dark coat torn at
the left shoulder. Tomás Herrera.
She had seen him at
The Raven’s Nest three nights earlier, though he had denied being there.
He had sat beneath a
black-and-white photograph of a drowned woman, Saint Christopher shining at his throat. Former paramedic. Licence revoked. Known to treat people who did not appear on any NHS register.
Quinn had found a dead
man in a rented room in Kentish Town with Herrera’s fingerprints on the medical kit.
Now Herrera carried the same
silver case recovered from the room. “Tomás!” He looked back. Warm brown eyes. No surprise in them. Only calculation. Then he ran faster. Quinn followed.
He cut left down a
service lane, scattering two men unloading crates.
She hurdled a stack of
flattened cardboard and struck the wall with her palm to swing around the corner. The rain had soaked through her shirt beneath the stab vest.
Her breath came hard, but
her stride held. Eighteen years of training had carved pursuit into muscle and bone. Herrera climbed a metal staircase behind a row of restaurants. Quinn heard a door slam above.
She took the steps two
at a time. The landing opened onto the back of a disused station entrance, its tiled
facade
covered by plywood and council notices. One notice bore a red closure symbol. Another had
been torn
down, leaving only four rusted screws and a rectangle of clean brick. Herrera stood at the bottom of the stairs.
He had stopped beside a
steel service door. Quinn drew her pistol. “Hands where I can see them.” Herrera raised both hands. Rainwater ran from his curls and down his olive cheeks. The silver case hung from his right wrist. “You’ve chosen a poor night to become brave, Detective.” “You’ve chosen a poor night to run.” “I had a patient.” “You had a corpse.” His jaw tightened. For the first time, she saw the exhaustion behind his eyes. “Your people found the wrong room.” “Then you can explain the right one at the station.” Herrera glanced at the service door. Quinn saw the movement. Small. Deliberate. A man checking an exit. “Step away from it.” “You don’t know what’s below.” “I know enough.” “No, you know files. Reports. Names typed by people who have never stood over a body that still moved after the heart stopped.” “Put the case down.” Herrera lowered his arm. “Now.” The service door burst open. Something pale and jointed struck Herrera across the chest and flung him into the brickwork. The silver case clattered down the steps. Quinn fired once. The muzzle flash lit a long, wet arm withdrawing into the doorway. Herrera slid to the ground. Quinn kept her pistol trained on the darkness. The thing inside made a clicking sound, like teeth tapping against glass.
She moved towards Herrera without
lowering the weapon. “Can you stand?” “Not without the case.” “Forget the case.” “That case contains the only thing keeping a dozen people alive.” The clicking came again, closer. Quinn grabbed Herrera by the collar and hauled him upright.
He staggered, one hand clamped
over his ribs.
His Saint Christopher medallion swung
between them. “Move.”
They reached the service door
together. The corridor beyond descended at a sharp angle, lined with cracked white tiles and dead
electric
lamps. The air smelled of rust, wet stone and something sweet that had turned rotten. Quinn kicked the silver case towards herself. Herrera snatched it up. Behind them, claws scraped over the steps. “Where does this go?” “Camden’s old Northern line.” “That station closed in 1940.” “Officially.” Herrera limped down the corridor. Quinn followed, pistol raised.
Their footsteps slapped through shallow
water.
Somewhere ahead, a bell rang
once. The sound travelled through the tunnel and returned with a second note that did not belong to it. At the foot of the stairs, Herrera stopped beside a brick arch. A circular hole had been cut into the wall at chest height.
He reached inside and pulled
out a small object wrapped in black cloth. Quinn caught his wrist. “What’s that?” “Permission.” “Show me.” He unfolded the cloth. A finger bone lay inside.
It had been polished until
it shone, with a thin copper wire wound around the middle joint. A symbol had
been carved
into the tip, three hooked lines meeting at a dark centre. Quinn stared at it. “Where did you get that?” Herrera looked at her hand around his wrist. “Let go.” “Answer me.” “The market won’t open without it.” “What market?” He gave her a flat, humourless look. “You came this far without knowing?” The tunnel lights
flickered
. Beyond the arch, a train screamed through the dark, though no rails ran beneath them. Quinn felt the vibration in her teeth. Herrera pressed the bone against a black iron plate set into the brick. The wall inhaled. Mortar split. Bricks rolled inward like loose teeth. A doorway opened onto a cavernous platform flooded with amber light. Voices rose from below. Not London voices. Not all of them human. Quinn shoved Herrera against the wall and brought the pistol under his chin. “You go first.” His eyes dropped to the gun. “Put that away before someone notices.” “Someone already noticed.” A woman in a red
velvet
coat stood at the far end of the platform. Her face looked young until she smiled.
Then the skin around her
mouth folded into fine, dry cracks. Beside her, a child with silver eyes held a tray of glass bottles. Each bottle contained a small, beating heart. The woman studied Quinn. “Police.” Herrera’s fingers tightened around the case. “Not here,” he said. The woman’s smile widened. “Police are always here. They just don’t know it.” Quinn pushed Herrera through the opening. The market stretched along the abandoned platform and into tunnels that had no business fitting beneath Camden. Stalls crowded the old tracks, covered with striped awnings and tarnished brass lamps. A vendor with a fox’s narrow face displayed rows of black candles. Another sold teeth in
velvet
-lined drawers. Glass jars bubbled beside handwritten labels in languages Quinn could not read. Old maps covered the station walls. Some showed London as she knew it. Others showed a second city beneath it, a knot of streets and rivers that crossed the first at impossible angles. The noise pressed against her from all sides. Haggling. Laughter. Wet coughing. The hiss of alchemical burners. Herrera shoved through the crowd. Quinn stayed on him, shoulder to shoulder, her pistol hidden beneath her coat. Hands brushed her sleeves. Fingers tugged at her belt. She knocked one away and saw a grey little face grin up at her from beneath a hood. “Touch me again and I’ll break your wrist.” The creature’s grin vanished. Herrera ducked between two stalls. Quinn followed. A man in a stained apron hurled a cleaver at her. She twisted aside. The blade buried itself in a wooden pillar, quivering. “Where’s my property?” the man roared. “Ask the man running from me.” Herrera glanced back. “Stop making friends.” “You brought me to an illegal market.” “You followed.” “You’re under arrest.” “Not until we leave.” They reached a narrow footbridge over a black trench. Shapes moved beneath the surface, pale backs rolling in the water. Herrera crossed first. The bridge swayed under his
weight
. A hand shot through the gaps and seized his ankle. He slammed onto his
stomach
. The silver case skidded towards the edge. Quinn caught the back of his coat with one hand and grabbed the case with the other. The thing below pulled. Herrera’s fingers clawed at the wet boards. His Saint Christopher medallion snapped free and dropped into the trench. The water opened around it. “Quinn!” She holstered her pistol and seized his forearm. The scar along his left arm stood out white as he fought for purchase. “Let go of the case!” “Can’t.” “Then cut my leg loose.” The fingers around his ankle tightened. Black nails pierced the fabric. Quinn braced her boot against the bridge rail and pulled with all her strength. The wood groaned. Herrera’s shoulder struck the boards. A woman’s voice rose from the crowd behind them. “Detective Quinn.” She turned. The woman in the
velvet
coat stood at the bridge entrance. Rainwater dripped from her hair though no rain reached the market. Her smile had disappeared. “You took something from us three years ago.” Quinn’s grip faltered. Below, the thing dragged Herrera another inch towards the trench. The woman lifted one pale hand. “Bring me the detective alive.” Every stallholder in the market turned towards Quinn. The bridge ropes snapped.
created_at
"2026-07-09T17:53:26.822Z"
7/9/2026, 5:53:26 PM
model
"openai/gpt-5.6-luna-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2249
moderation_latency
(null)
generation_time
14893
tokens_prompt
4663
tokens_completion
2913
native_tokens_prompt
4132
native_tokens_completion
2306
native_tokens_completion_images
0
native_tokens_reasoning
214
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
0.0142519
router
(null)
provider_responses
0
endpoint_id
"eebea444-34a5-4642-a766-cb319471d33a"
id
"resp_03f487c80795ac9b016a4fe016e4bc819399ee76497a6cf4a6"
is_byok
false
latency
264
model_permaslug
"openai/gpt-5.6-luna-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-1783619606-MCpSUgrNyLRopfvU3wkR"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783619606-8MYyynDD2XHghdiuEofe"
upstream_id
"resp_03f487c80795ac9b016a4fe016e4bc819399ee76497a6cf4a6"
total_cost
0.0142519
cache_discount
0.0037161
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
55
tagDensity
0.036
leniency
0.073
rawRatio
0
effectiveRatio
0
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1636
totalAiIsmAdverbs
0
found
(empty)
highlights
(empty)
100.00%
AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
72.49%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1636
totalAiIsms
9
found
0
word
"facade"
count
1
1
word
"electric"
count
1
2
word
"footsteps"
count
1
3
word
"flickered"
count
1
4
word
"velvet"
count
3
5
word
"weight"
count
1
6
word
"stomach"
count
1
highlights
0
"facade"
1
"electric"
2
"footsteps"
3
"flickered"
4
"velvet"
5
"weight"
6
"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
0
narrationSentences
173
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
173
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
226
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
31
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1636
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
7
unquotedAttributions
0
matches
(empty)
33.33%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
66
wordCount
1365
uniqueNames
10
maxNameDensity
1.98
worstName
"Herrera"
maxWindowNameDensity
4
worstWindowName
"Herrera"
discoveredNames
Herrera
27
Raven
1
Nest
1
Saint
3
Christopher
3
Kentish
1
Town
1
London
2
Quinn
26
Camden
1
persons
0
"Herrera"
1
"Saint"
2
"Christopher"
3
"Quinn"
places
0
"Raven"
1
"Kentish"
2
"Town"
3
"London"
globalScore
0.511
windowScore
0.333
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
104
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1636
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
226
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
145
mean
11.28
std
12.66
cv
1.122
sampleLengths
0
15
1
47
2
6
3
19
4
4
5
31
6
2
7
10
8
2
9
61
10
14
11
2
12
50
13
20
14
11
15
1
16
3
17
9
18
4
19
2
20
61
21
16
22
8
23
43
24
8
25
8
26
4
27
6
28
22
29
9
30
7
31
4
32
4
33
14
34
6
35
10
36
6
37
11
38
4
39
5
40
3
41
23
42
4
43
4
44
1
45
5
46
37
47
5
48
8
49
12
99.18%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
3
totalSentences
173
matches
0
"been torn"
1
"been polished"
2
"been carved"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
228
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
226
ratio
0
matches
(empty)
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1368
adjectiveStacks
1
stackExamples
0
"Short curly dark hair."
adverbCount
19
adverbRatio
0.013888888888888888
lyAdverbCount
3
lyAdverbRatio
0.0021929824561403508
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
226
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
226
mean
7.24
std
5
cv
0.691
sampleLengths
0
15
1
12
2
3
3
10
4
22
5
6
6
10
7
2
8
7
9
4
10
31
11
2
12
5
13
5
14
2
15
9
16
15
17
14
18
8
19
15
20
2
21
4
22
8
23
2
24
17
25
17
26
2
27
2
28
12
29
20
30
11
31
1
32
3
33
3
34
4
35
2
36
4
37
2
38
12
39
19
40
11
41
8
42
11
43
10
44
6
45
8
46
20
47
7
48
16
49
8
59.73%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
5
diversityRatio
0.37168141592920356
totalSentences
226
uniqueOpeners
84
64.10%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
3
totalSentences
156
matches
0
"Then he ran faster."
1
"Somewhere ahead, a bell rang"
2
"Then the skin around her"
ratio
0.019
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
29
totalSentences
156
matches
0
"She ignored him and cut"
1
"She glanced at the radio."
2
"She had seen him at"
3
"He had sat beneath a"
4
"He looked back."
5
"He cut left down a"
6
"She hurdled a stack of"
7
"Her breath came hard, but"
8
"She took the steps two"
9
"He had stopped beside a"
10
"His jaw tightened."
11
"She moved towards Herrera without"
12
"He staggered, one hand clamped"
13
"His Saint Christopher medallion swung"
14
"They reached the service door"
15
"Their footsteps slapped through shallow"
16
"He reached inside and pulled"
17
"He unfolded the cloth."
18
"It had been polished until"
19
"He gave her a flat,"
ratio
0.186
30.51%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
134
totalSentences
156
matches
0
"The suspect vaulted the bonnet"
1
"Quinn reached the crossing three"
2
"A horn blared."
3
"The cab driver leaned out,"
4
"She ignored him and cut"
5
"The suspect had left a"
6
"A smear of blood marked"
7
"Quinn touched her radio."
8
"She glanced at the radio."
9
"The display had gone black."
10
"The narrow passage spat her"
11
"People pushed past with their"
12
"The suspect shouldered through the"
13
"Quinn caught a glimpse of"
14
"A dark coat torn at"
15
"She had seen him at"
16
"He had sat beneath a"
17
"Quinn had found a dead"
18
"He looked back."
19
"He cut left down a"
ratio
0.859
32.05%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
156
matches
0
"Now Herrera carried the same"
ratio
0.006
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
58
technicalSentenceCount
0
matches
(empty)
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
"the man roared (roar)"
dialogueSentences
55
tagDensity
0.036
leniency
0.073
rawRatio
0.5
effectiveRatio
0.036
89.5136%