NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX41C21GNGGGXYSCBWZD22BV
Run Details
Model:
GPT-5.6 Luna (Reasoning)
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
15.7s
Cost:
$0.013258
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
100.00%
AI-ism adverb frequency
(details)
80.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
89.53%
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)
72.73%
Name drop frequency
(details)
100.00%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
100.00%
Paragraph length variance
(details)
100.00%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
100.00%
Em-dash & semicolon overuse
(details)
100.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
54.91%
Sentence opener variety
(details)
0.00%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
26.93%
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)
87.4700%
Overall
Model input
System
You are an expert and award-winning novel writer in the dark Mystery 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="4414" name="Eva Kowalski" aliases="Eva, Evie" pronouns="she/her" species="Human" storyRole="Best Friend"> <eyeColor>green</eyeColor> <hair>curly red</hair> <height>5'4"</height> <age>26</age> <glasses>round glasses</glasses> <satchel>worn leather satchel full of books</satchel> <freckles>freckled complexion</freckles> <nervousHabit>tucking hair behind her left ear</nervousHabit> <description>Aurora's childhood friend and an occult researcher.</description> <backstory>Moved to London two years before Aurora and works as a research assistant at the British Museum's restricted archives. She holds a master's degree in Ancient History from Oxford.</backstory> </character> <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> <item id="2004" name="Veil Compass" aliases="the Compass, shadow compass" type="Tool" origin="The Veil Market"> <casingMaterial>small brass compass</casingMaterial> <faceMarkings>face etched with protective sigils</faceMarkings> <needle>points toward the nearest supernatural rift or portal</needle> <patina>casing has a patina of verdigris</patina> <creator>crafted by a Shade artisan</creator> <description>A compass attuned to supernatural energy.</description> </item> </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 mystery genre. A detective arrives at a crime scene in an unusual location. Something is wrong — the evidence doesn't add up. A colleague is present, offering a different interpretation. Through careful observation and deduction, the detective begins to see what others have missed. 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 dead man’s hand snapped
shut around Quinn’s wrist.
She drove her elbow into
his throat before she remembered he had no
pulse
.
The corpse jerked once, teeth
clicking together, then collapsed across the tiled platform.
Its fingers left a dark
smear on her leather
watch
.
Quinn stepped back, drew her
service pistol and held it on the body. “Don’t shoot him,”
Sergeant Vale called
. “He moved.” “Post-mortem spasm.” “Post-mortem spasms don’t grip.”
Vale stood beside the rusted
ticket machine, one hand pressed to his mouth.
He had arrived before her
and looked as if the station had arrived on top of him. Blood spotted his collar.
A row of red lamps
hung from the disused ceiling, though no cables fed them.
Their light pulsed across the
platform in a slow, sick rhythm.
Quinn kept the pistol trained
on the corpse. “Where’s the paramedic?” Vale swallowed. “There isn’t one.” “Why not?” “Because he’s been dead for three days.”
The abandoned station crouched beneath
Camden like a buried throat. Old Tube signs flaked from the walls.
Someone had painted over the
Northern Line roundel with a silver eye, and beneath it, in neat white letters, someone had written NO BUYERS AFTER THE THIRD BELL.
The body lay in the
centre of the platform, dressed in a black suit too fine for the torn station.
His throat bore a narrow
puncture. No blood pooled beneath him. No blood stained his shirt.
A black glass shard rested
between his teeth.
Quinn lowered her pistol by
an inch. “Three days?” “That’s what the pathologist’s portable kit says.” “You brought a pathologist down here?” Vale pointed towards the tracks.
A woman in a disposable
white suit crouched beside the body. Dr
Patel
had her sleeves rolled to the elbows and a plastic evidence bag clenched between her teeth.
She removed the bag, held
it up and frowned at the black shard. “Temperature’s wrong,” she said. “For the body?” “For the whole station. He’s cold enough to have frozen, but the rails are warm. Feel them.” Quinn did not.
She looked at the corpse’s
shoes. Polished brown leather, clean soles, no mud. The platform carried a thin layer of dust except for the path between the dead man and the tracks. Someone had disturbed it. Several someones. Curved footprints crossed one another, each impression long and narrow, with three deep marks at the front. “Who found him?” “Market traders,” Vale said. “They ran before we could take names.” “Market?”
He gave her a humourless
glance. “You know what this place is supposed to be.” Quinn had heard the rumours. Every city had its private rot, places where stolen medicine, weapons and secrets changed hands beneath the official map. The Veil Market belonged to London’s more imaginative criminals. Enchanted goods. Banned alchemical substances. Information. Nonsense dressed in candle smoke. Yet the station had no entrance. The service gate at the far end stood open, its lock cut cleanly through. The access tunnel behind it ended after twelve feet at a brick wall. No passage. No ladder. No stairwell. Quinn had checked the plans in the car. The line closed in 1932. The station had never existed. “Uniforms searched the tunnel?” she asked. “Twice.” “And found no way in or out.” “Correct.” “Then the killer came through the wall.” Vale’s mouth tightened. “Or the traders made the body appear. One of their little performances.” “Where are the traders now?” “Gone.” “Convenient.” Dr
Patel
slid a swab beneath the dead man’s fingernail. “Convenience has nothing to do with it. There’s no tissue under the nails, no fibres, no skin. No defensive wounds. He didn’t struggle.” Quinn crouched beside the body. The puncture in the throat looked too precise for a knife. The skin had folded inward around it, as though something had bored through from the outside and withdrawn without tearing. She leaned closer. Copper prickled her nostrils. Not blood. Burnt metal, old coins and something sweet beneath it. “Your three-day reading,” Quinn said. “What gave you that?” “Rigidity, decomposition, body temperature.” “His
watch
.” Dr
Patel
looked at the corpse’s wrist. A slim silver
watch
showed 11:18. The second hand sat still. “Stopped at the moment of death, perhaps.” “Dust beneath it.” Quinn hooked a gloved finger beneath the strap. A crescent of clean skin marked the wrist, but dust lay in the indentation left by the
watch
casing.
It had not rested there
during the man’s final hours. Someone had placed it on him afterwards. Vale bent over the body. “Or he lost the
watch
, and someone returned it.” “Then why did they return the wrong time?” “Because criminals aren’t famous for their attention to detail.” Quinn pointed to the corpse’s left sleeve. The cuff carried a dark stain.
It looked like ink until
the red lamps passed over it. The mark shone with a blue-green sheen. “Verdigris,” she said. Dr
Patel
lifted the sleeve with forceps. A small brass object lay beneath the wrist, trapped against the skin.
It had the shape of
a compass, though its face held no north, south, east or west. Protective sigils covered the glass. Green corrosion feathered the casing. The needle spun in tight circles. Vale stared at it. “Cheap prop,” he said. “Why does it move?” “Magnet in the floor.” Quinn lifted her head. “Then why does it point at him?” The needle had stopped.
Its tip aimed across the
platform, past the corpse, towards the blank brick wall at the end of the tracks. Dr
Patel
followed her gaze. “There’s no chamber beyond that.” “Your plans say so?” “My plans say the station isn’t here.” The red lamps
flickered
. A bell rang somewhere beneath the tracks. Once. Vale reached for his radio. “Control, we’ve got a noise in the south tunnel. Send—” The radio hissed. A woman’s voice breathed through the static. “Buyers have thirty seconds.” Vale froze. Quinn rose and surveyed the platform. The blood smear from the corpse’s hand ended at her
watch
. No footprints led to the body from the service gate. The tracks held no dust at all. That seemed impossible. Dust settled everywhere, even underground.
She crossed to the edge
and looked down. The rails glistened as though someone had polished them. A wet black substance coated the sleepers.
It reflected the lamps, but
not Quinn’s face. “Don’t step down,” Vale said. “Why?” “Because
Patel
found a footprint.”
He pointed beside the third
rail. One impression marked the black coating. It had no heel. Three narrow toes pressed into the surface, each ending in a hooked groove. Another footprint appeared two metres farther along. Then another. The prints led from the tunnel towards the corpse. Quinn looked back. “Where are the return prints?” Vale shook his head. “That’s what I’m saying. It came in, killed him and left through the wall.” “No.” “You have a better explanation?” “The prints came from the body.” “Bodies don’t walk.” “This one did.” Dr
Patel
stood and removed her gloves. “You saw him move?” “He gripped my wrist.” “Muscle contraction.” “His fingers moved with purpose.” “Purpose is a human interpretation.” Quinn examined the corpse’s hand. The fingernails had cracked. Black grit filled the creases of his palm, packed deep beneath the skin. Not station dust. It looked like crushed glass. She turned the hand over. A strip of paper clung to the wrist, folded into a narrow triangle.
She pulled it free and
unfolded it on the palm of her glove. The paper carried one line. HARLOW QUINN HAS
BEEN NOTIFIED
. Vale read over her shoulder. “Someone knew you were coming.” “Someone knew before I did.” The second bell rang. The lamps brightened. Behind the ticket machine, a narrow doorway appeared in the tiled wall. No hinge. No frame. One moment there was brick. The next, black oak filled the gap, carved with hundreds of tiny names. The smell of hot wax and wet stone rolled across the platform. Dr
Patel
backed away. “Tell me that’s another trick.” Quinn kept the paper in one hand and reached for the compass with the other. The brass casing burned her palm. Its needle swung away from the wall and pointed at the corpse. The dead man’s eyes opened. They
were filled
with silver. Vale raised his weapon. “Quinn.” The corpse’s mouth widened far beyond the shape of a human jaw. The black shard fell from between his teeth and struck the tile. A voice came from inside his throat. “Detective Quinn. Your debt has come due.” The door behind the ticket machine opened inwards. Something tall stepped through, wearing Detective Sergeant Morris’s face.
created_at
"2026-07-09T18:13:51.29Z"
7/9/2026, 6:13:51 PM
model
"openai/gpt-5.6-luna-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2837
moderation_latency
(null)
generation_time
15601
tokens_prompt
4671
tokens_completion
2731
native_tokens_prompt
4157
native_tokens_completion
2140
native_tokens_completion_images
0
native_tokens_reasoning
248
native_tokens_cached
4154
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
0.0132584
router
(null)
provider_responses
0
endpoint_id
"eebea444-34a5-4642-a766-cb319471d33a"
id
"resp_099a80aaf1935544016a4fe4df5bc88197b414558a800c33eb"
is_byok
false
latency
199
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-1783620831-vxvWoNcSpZkzXHtY6Ohw"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620831-eCg11JCWvb2CnAgNnYL3"
upstream_id
"resp_099a80aaf1935544016a4fe4df5bc88197b414558a800c33eb"
total_cost
0.0132584
cache_discount
0.0037386
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
8
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
68
tagDensity
0.118
leniency
0.235
rawRatio
0
effectiveRatio
0
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1433
totalAiIsmAdverbs
0
found
(empty)
highlights
(empty)
80.00%
AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions
(empty)
found
0
"Patel"
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
89.53%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1433
totalAiIsms
3
found
0
word
"pulse"
count
1
1
word
"pulsed"
count
1
2
word
"flickered"
count
1
highlights
0
"pulse"
1
"pulsed"
2
"flickered"
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
147
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
2
hedgeCount
0
narrationSentences
147
filterMatches
0
"watch"
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
207
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
repeatedSegmentCount
0
maxSentenceWordsSeen
28
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1433
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
14
unquotedAttributions
0
matches
(empty)
72.73%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
56
wordCount
1100
uniqueNames
14
maxNameDensity
1.55
worstName
"Quinn"
maxWindowNameDensity
2.5
worstWindowName
"Quinn"
discoveredNames
Quinn
17
Vale
14
Camden
1
Tube
1
Northern
1
Line
1
Patel
7
Veil
1
Market
1
London
1
Dr
7
Detective
1
Sergeant
2
Morris
1
persons
0
"Quinn"
1
"Vale"
2
"Camden"
3
"Tube"
4
"Line"
5
"Patel"
6
"Market"
7
"Dr"
8
"Sergeant"
9
"Morris"
places
0
"London"
globalScore
0.727
windowScore
0.833
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
80
glossingSentenceCount
1
matches
0
"looked like ink until the red lamps passe"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1433
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
207
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
132
mean
10.86
std
12.97
cv
1.194
sampleLengths
0
9
1
14
2
36
3
6
4
2
5
2
6
4
7
60
8
8
9
3
10
2
11
3
12
2
13
7
14
45
15
44
16
7
17
2
18
7
19
6
20
5
21
42
22
4
23
3
24
17
25
3
26
55
27
3
28
11
29
1
30
6
31
9
32
44
33
6
34
51
35
6
36
1
37
7
38
1
39
7
40
3
41
12
42
5
43
1
44
1
45
10
46
23
47
39
48
4
49
11
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
2
totalSentences
147
matches
0
"BEEN NOTIFIED"
1
"were filled"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
184
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
207
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1101
adjectiveStacks
0
stackExamples
(empty)
adverbCount
18
adverbRatio
0.01634877384196185
lyAdverbCount
1
lyAdverbRatio
0.0009082652134423251
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
207
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
207
mean
6.92
std
4.71
cv
0.68
sampleLengths
0
9
1
14
2
13
3
10
4
13
5
6
6
2
7
2
8
4
9
13
10
17
11
4
12
15
13
11
14
8
15
3
16
2
17
3
18
2
19
7
20
10
21
7
22
28
23
20
24
6
25
5
26
5
27
8
28
7
29
2
30
7
31
6
32
5
33
11
34
18
35
13
36
4
37
3
38
17
39
3
40
6
41
7
42
19
43
4
44
2
45
17
46
3
47
4
48
7
49
1
54.91%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
13
diversityRatio
0.3671497584541063
totalSentences
207
uniqueOpeners
76
0.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
0
totalSentences
127
matches
(empty)
ratio
0
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
22
totalSentences
127
matches
0
"She drove her elbow into"
1
"Its fingers left a dark"
2
"He had arrived before her"
3
"Their light pulsed across the"
4
"His throat bore a narrow"
5
"She removed the bag, held"
6
"She looked at the corpse’s"
7
"He gave her a humourless"
8
"She leaned closer."
9
"It had not rested there"
10
"It looked like ink until"
11
"It had the shape of"
12
"Its tip aimed across the"
13
"She crossed to the edge"
14
"It reflected the lamps, but"
15
"He pointed beside the third"
16
"It had no heel."
17
"It looked like crushed glass."
18
"She turned the hand over."
19
"She pulled it free and"
ratio
0.173
26.93%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
110
totalSentences
127
matches
0
"The dead man’s hand snapped"
1
"She drove her elbow into"
2
"The corpse jerked once, teeth"
3
"Its fingers left a dark"
4
"Quinn stepped back, drew her"
5
"Sergeant Vale called"
6
"Vale stood beside the rusted"
7
"He had arrived before her"
8
"Blood spotted his collar."
9
"A row of red lamps"
10
"Their light pulsed across the"
11
"Quinn kept the pistol trained"
12
"The abandoned station crouched beneath"
13
"Someone had painted over the"
14
"The body lay in the"
15
"His throat bore a narrow"
16
"A black glass shard rested"
17
"Quinn lowered her pistol by"
18
"Vale pointed towards the tracks."
19
"A woman in a disposable"
ratio
0.866
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
127
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
41
technicalSentenceCount
0
matches
(empty)
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
8
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
8
fancyCount
0
fancyTags
(empty)
dialogueSentences
68
tagDensity
0.118
leniency
0.235
rawRatio
0
effectiveRatio
0
87.4700%