NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBJTYHZGB7N369R9M1M6AZ2
Run Details
Model:
Qwen 3.5 Flash
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
52.2s
Cost:
$0.002786
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
89.88%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
62.89%
AI-ism word frequency
(details)
66.67%
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)
0.00%
Missing dialogue indicators (quotation marks)
(details)
50.00%
Name drop frequency
(details)
99.49%
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)
37.79%
Sentence opener variety
(details)
24.88%
Adverb-first sentence starts
(details)
14.03%
Pronoun-first sentence starts
(details)
2.91%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
95.24%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
78.1257%
Overall
Model input
System
You are an expert and award-winning novel writer in the dark Literary Fiction genre. Your readers are hooked on your stories and can't wait to read the book you have in store. <important> - MUST: Start each chapter in medias res (in the middle of action). AVOID talking about the weather, time of day, the position of the sun, or other boring stuff. - The instructions/summary are just a that, a summary. Feel free to add details, stretch sections and add interesting transitions/descriptions/fillers. - When called for it, have fast-paced action, but otherwise take things slow. This is an experience, and not for people with short attention spans. Enjoy the wine, not slurp Red Bull. - Add descriptions when transitioning places/times/etc, or when coming by new places (e.g. a corner shop, a cafe, etc.). But remember: NOT at the start or end of a chapter. - MUST: AVOID ending in internal monologue, reminiscing or waiting for the next day. A good chapter end is when we're ending right when shit hits the fan. We want to have the reader be excited for what comes next. So no reminiscing, contemplating or summarizing the day. It's popcorn time! </important>
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <codex> <character id="4412" name="Aurora Carter" aliases="Rory, Laila, Aurora, Carter, Malphora" pronouns="she/her" species="Human" storyRole="Protagonist"> <eyeColor>bright blue</eyeColor> <hair>straight shoulder-length black</hair> <height>5'6"</height> <age>25</age> <scar>small crescent-shaped scar on her left wrist from a childhood accident</scar> <description>Aurora, referred to by her friends as Rory, is cool-headed, intelligent, and known for quick out-of-the-box thinking.</description> <backstory>Born in Cardiff to an Irish barrister father (Brendan Carter) and Welsh teacher mother (Jennifer Carter née Ellis), Rory reluctantly pursued Pre-Law at Cardiff University. She fled to London at the behest of her childhood friend Eva after leaving an abusive ex named Evan. By day, Rory works part-time as a delivery person for Yu-Fei Cheung's Golden Empress restaurant. She lives in a flat above Silas' bar.</backstory> </character> <character id="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</backstory> </character> <location id="854" name="The Raven's Nest" aliases="the Nest, Raven, Silas' bar" realm="Earth"> <signColor>distinctive green neon sign above the entrance</signColor> <secretRoom>hidden back room accessible through a bookshelf, used for clandestine meetings</secretRoom> <description>A dimly lit bar in Soho, London. The walls are covered with old maps and black-and-white photographs.</description> </location> </codex> <proseGuidelines> <styleGuide> - Write in past tense and use British English spelling and grammar - Keep a Flesch reading ease score of 60 - Respect the the Royal Order of Adjectives: The order is: opinion, size, age, shape, color, origin, material, purpose, followed by the noun itself (e.g., "a lovely little old rectangular green French silver whittling knife") - Respect the ablaut reduplication rule (e.g. tick-tock, flip-flop) - Write in active voice - Passive voice: <bad>The book was read by Sarah.</bad> - Active voice: <good>Sarah read the book.</good> - Reduce the use of passive verbs - <bad>For a moment, I was tempted to throw in the towel.</bad> - <good>For a moment, I felt tempted to throw in the towel.</good> - Avoid misplaced modifiers that can cause confusion when starting with "-ing" words: - <bad>Considering going to the store, the empty fridge reflected in Betty's eyes.</bad> - <good>Betty stared into the empty fridge. It was time to go to the store.</good> - Avoid redundant adverbs that state the obvious meaning already contained in the verb: - <bad>She whispered quietly to her mom.</bad> - <good>She whispered to her mom.</good> - Use stronger, more descriptive verbs over weak ones: - <bad>Daniel drove quickly to his mother's house.</bad> - <good>Daniel raced to his mother's house.</good> - Omit adverbs that don't add solid meaning like "extremely", "definitely", "truly", "very", "really": - <bad>The movie was extremely boring.</bad> - <good>The movie was dull.</good> - Use adverbs to replace clunky phrasing when they increase clarity: - <bad>He threw the bags into the corner in a rough manner.</bad> - <good>He threw the bags into the corner roughly.</good> - Avoid making simple thoughts needlessly complex: - <bad>After I woke up in the morning the other day, I went downstairs, turned on the stove, and made myself a very good omelet.</bad> - <good>I cooked a delicious omelet for breakfast yesterday morning.</good> - Never backload sentences by putting the main idea at the end: - <bad>I decided not to wear too many layers because it's really hot outside.</bad> - <good>It's sweltering outside today, so I dressed light.</good> - Omit nonessential details that don't contribute to the core meaning: - <bad>It doesn't matter what kind of coffee I buy, where it's from, or if it's organic or not—I need to have cream because I really don't like how the bitterness makes me feel.</bad> - <good>I add cream to my coffee because the bitter taste makes me feel unwell.</good> - Always follow the "show, don't tell" principle. For instance: - Telling: <bad>Michael was terribly afraid of the dark.</bad> - Showing: <good>Michael tensed as his mother switched off the light and left the room.</good>- Telling: <bad>I walked through the forest. It was already Fall, and I was getting cold.</bad> - Showing: <good>Dry orange leaves crunched under my feet. I pulled my coat's collar up and rubbed my hands together.</good>- Add sensory details (sight, smell, taste, sound, touch) to support the "showing" (but keep an active voice) - <bad>The room was filled with the scent of copper.</bad> - <good>Copper stung my nostrils. Blood. Recent.</good> - Use descriptive language more sporadically. While vivid descriptions are engaging, human writers often use them in bursts rather than consistently throughout a piece. When adding them, make them count! Like when we transition from one location to the next, or someone is reminiscing their past, or explaining a concept/their dream... - Avoid adverbs and clichés and overused/commonly used phrases. Aim for fresh and original descriptions. - Avoid writing all sentences in the typical subject, verb, object structure. Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. Like so: <good>Locked. Seems like someone doesn't want his secrets exposed. I can work with that.</good> - Convey events and story through dialogue. It is important to keep a unique voice for every character and make it consistent. - Write dialogue that reveals characters' personalities, motivations, emotions, and attitudes in an interesting and compelling manner - Leave dialogue unattributed. If needed, only use "he/she said" dialogue tags and convey people's actions or face expressions through their speech. Dialogue always is standalone, never part of a paragraph. Like so: - <bad>"I don't know," Helena said nonchalantly, shrugging her shoulders</bad> - <good>"No idea" "Why not? It was your responsibility"</good> - Avoid boring and mushy dialog and descriptions, have dialogue always continue the action, never stall or include unnecessary fluff. Vary the descriptions to not repeat yourself. Avoid conversations that are just "Let's go" "yes, let's" or "Are you ready?" "Yes I'm ready". Those are not interesting. Think hard about every situtation and word of text before writing dialogue. If it doesn't serve a purpose and it's just people talking about their day, leave it. No one wants to have a normal dinner scene, something needs to happen for it to be in the story. Words are expensive to print, so make sure they count! - Put dialogue on its own paragraph to separate scene and action. - Use body language to reveal hidden feelings and implied accusations- Imply feelings and thoughts, never state them directly - NEVER use indicators of uncertainty like "trying" or "maybe" - NEVER use em-dashes, use commas for asides instead </styleGuide> <voiceGuide> Each character in the story needs to have distinct speech patterns: - Word choice preferences - Sentence length tendencies - Cultural/educational influences - Verbal tics and catchphrases Learn how each person talks and continue in their style, and use their Codex entries as reference. <examples> - <bad>"We need to go now." "Yes, we should leave." "I agree."</bad> <good>"Time's up." "Indeed, our departure is rather overdue." "Whatever, let's bounce."</good> - Power Dynamic Example: <bad> "We need to discuss the contract." "Yes, let's talk about it." "I have concerns." </bad> <good> "A word about the contract." "Of course, Mr. Blackwood. Whatever you need." "The terms seem..." A manicured nail tapped the desk. "Inadequate." "I can explain every-" "Can you?" </good> </examples> </voiceGuide> <dialogueFlow> When writing dialogue, consider that it usually has a goal in mind, which gives it a certain flow. Make dialogue sections also quite snappy in the back and forth, and don't spread the lines out as much. It's good to have details before, after, or as a chunk in-between, but we don't want to have a trail of "dialogue breadcrumbs" spread throughout a conversation. <examples> - Pattern 1 - Question/Deflection/Revelation: <good> "Where were you last night?" "Work. The usual." "Lipstick's an interesting shade for spreadsheets." </good> - Pattern 2 - Statement/Contradiction/Escalation: <good> "Your brother's clean." "Tommy doesn't touch drugs." "I'm holding his tox screen." </good> - Pattern 3 - Observation/Denial/Truth: <good> "That's a new watch." "Birthday gift." "We both know what birthdays mean in this business." </good> - Example - A Simple Coffee Order: <bad> "I'll have a coffee." "What size?" "Large, please." </bad> <good> "Black coffee.""Size?""Large. Been a long night." "That bodega shooting?" "You watch too much news." "My brother owns that store." </good> This short exchange: - Advances plot (reveals connection to crime) - Shows character (cop working late) - Creates tension (unexpected connection) - Sets up future conflict (personal stake) - Example - Dinner Scene: <bad> "Pass the salt." "Here you go." "Thanks." </bad> <good> "Salt?" "Perfect as is. Mother's recipe." "Mother always did prefer... bland things." "Unlike your first wife?" </good> - Example - Office Small Talk: <bad> "Nice weather today." "Yes, very nice." "Good for golf." </bad> <good> "Perfect golf weather." "Shame about your membership." "Temporary suspension. Board meets next week." "I know. I called the vote." </good> </examples> </dialogueFlow> <subtextGuide> - Layer dialogue with hidden meaning: <bad>"I hate you!" she yelled angrily.</bad> <good>"I made your favorite dinner." The burnt pot sat accusingly on the stove.</good> - Create tension through indirect communication: <bad>"Are you cheating on me?"</bad> <good>"Late meeting again?" The lipstick stain on his collar caught the light.</good> <examples> - Example 1 - Unspoken Betrayal: <bad> "Did you tell them about our plans?" "No, I would never betray you." "I don't believe you." </bad> <good> "Funny. Johnson mentioned our expansion plans today." "The market's full of rumors." "Mentioned the exact numbers, actually." The pen in his hand snapped. </good> - Example 2 - Failed Marriage: <bad> "You're never home anymore." "I have to work late." "I miss you." </bad> <good> "Your dinner's in the microwave. Again." "Meetings ran long." "They always do." She folded the same shirt for the third time. </good> - Example 3 - Power Struggle: <bad> "You can't fire me." "I'm the boss." "I'll fight this." </bad> <good> "That's my father's nameplate you're sitting behind." "Was." "The board meeting's on Thursday." </good> </examples> </subtextGuide> <sceneDetail> While writing dialogue makes things more fun, sometimes we need to add detail to not have it be a full on theatre piece. <examples> - Example A (Power Dynamic Scene) <good> "Where's my money?" The ledger snapped shut. "I need more time." "Interesting." He pulled out a familiar gold pocket watch. My mother's. "Time is exactly what you bargained with last month." "That was different-" "Was it?" The watch dangled between us. "Four generations of O'Reillys have wound this every night. Your mother. Your grandmother. Your great-grandmother.Shall we see who winds it next?" </good> - Example B (Action Chase) It's much better to be in the head of the character experiencing it, showing a bit of their though-process, mannerisms and personality: <good> Three rules for surviving a goblin chase in Covent Garden: Don't run straight. Don't look back. Don't let them herd you underground. I broke the first rule at Drury Lane. Rookie mistake. The fruit cart I dodged sailed into the wall behind me. Glass shattered. Someone screamed about insurance. *Tourist season's getting rough*, the scream seemed to say. Londoners adapt fast. "Oi! Market's closed!" The goblin's accent was pure East End. They're evolving. Learning. I spotted the Warren Street tube station sign ahead. *Shit.* There went rule three. </good> - Example C (Crime Scene Investigation) <good> "Greek." Davies snapped photos of the symbols. "No, wait. Reverse Greek." "Someone's been watching too many horror films." I picked up a receipt from the floor. Occult supply shop in Camden. Paid by credit card. *Amateur hour*. "Could be dangerous though," Davies said. "Remember Bristol?" "Bristol was Sanskrit. And actual cultists." I pointed to the nearest symbol. "This genius wrote 'darkness' backwards but used a Sigma instead of an S. It's summoning Instagram followers at best." "Speaking of followers..." Davies pointed to heavy foot traffic in the dust. Multiple sets. All new trainers. *Ah.* "Anyone check local uni paranormal societies?" </good> - Example D (Dialogue-heavy) <good> "Found your card in her wallet." The detective slid it across the table. Worn edges. Folded corner. Three years old at least. "Standard practice. I work missing persons." "Funny thing about missing persons.Eventually they stop being missing. Turn up in the Thames. Under motorways. In pieces." "I don't-" "You found four last year. All breathing." She opened a file. "This would've been your first dead one. If we hadn't found her first." The card felt heavier somehow. </good> </examples> </sceneDetail> <sceneOpenings> KEY RULE: Never open with more than one paragraph of description, no matter how beautiful. Description should be earned through action and dialogue. Instead of opening with setting description, open with: - A character doing something specific - A line of dialogue that raises questions - An unexpected observation - A moment of tension or conflict - Start with a hook that's 1-2 sentences maximum - Follow with a smaller paragraph that provides immediate context - Vary paragraph size from the start to create visual interest </sceneOpenings> </proseGuidelines> Write a chapter based on the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the literary fiction genre. Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret. Use the codex entries above as your world reference for characters and setting. Only include the prose of the scene without any markdown or commentary. </instructions>
Model response
Messages
Meta
AI
The brass knocker bit into
Aurora’s left palm. She hesitated.
Her key was cold against
the wood, smelling of damp wool and old polish. She turned the lock anyway.
The hinges screamed, a high-pitched
protest that cut through the low hum of conversation inside. The neon sign buzzed overhead. Green light bled through the frosted glass and painted the rain-slicked pavement in Soho with sickly, fluorescent sludge. Aurora didn’t check the sky.
She kept her eyes on
the floor.
The creak from the stairs
still lingered. The flat above remained silent.
She pushed the door open
and stepped into The Raven’s Nest.
The air inside smelled of
stale ale and polished mahogany.
Cigars lingered in the corners
where the smokers gathered.
Shadows stretched long against the
dark wood.
Aurora moved past the bar
counter.
The usual faces were there
but they looked dull under the dim bulbs. Then she saw him.
Silas sat in the shadowed
corner. The leather stool looked worn.
His coat was draped over
the seat.
He held a glass of
amber liquid. It hadn’t moved in minutes.
His grey-streaked auburn beard was
longer now.
It framed a face etched
with deep lines.
His hazel eyes locked onto
hers. They didn’t blink. Aurora swallowed. Her throat felt dry. She shouldn’t have come here.
She didn’t need to see
anyone tonight. She just needed a walk. The rain in Soho was relentless.
It washed the city in
oil and grease. She took a step forward. Her shoulder brushed the doorframe. The neon hummed louder. Silas set the glass down. The
crystal
base hit the wood with a sharp clink. You’re late, Silas said. His voice sounded gravel. Roughened. It’s been two days, Aurora replied. She didn’t move closer. The floor behind her creaked. Dust motes danced in the beam of light from the back office. Two days is a lifetime when the game is already won. And yet. He raised a hand. Slow. Deliberate. A silver signet ring gleamed on his right finger. The metal caught the light. It looked like ice. You came down. I had to deliver the papers. The delivery box sat on her shoulder. Heavy. Wrapped in brown paper tied with twine. Silas stood up. His left leg dragged
slightly
. He didn’t limp. He just dragged the
weight
of the injury like a ghost. He moved around the table. The chairs scraped against the floorboards. Wood groaned under the friction. You
look
tired, he said. He stopped three feet away. Close enough to smell the smoke on his coat. Close enough to see the scar tissue on his wrist. I haven’t slept in three weeks, Aurora said. She tightened her grip on the box. Her
knuckles turned white
. The crescent on her wrist ached. You should have called. I didn’t want to bother you. Silas chuckled. A low sound that died
quickly
. You never used to bother me. Not once. The chair scraped. He sat back down. The leather squeaked. It
sounded like an animal dying
. I thought you were in Prague. He looked at the empty glass. The amber liquid had evaporated. Dust swirled in the air. I returned last week. The operation finished. Finished? Aurora felt the room tilt. The walls closed in. The old maps on the wall
seemed to
shift. Faces on the photographs turned to watch them. Finished means it’s over. Or it means I’ve lost you, Aurora said. Her voice shook. She
hated that it
shook. She
hated that she
meant every word. Silas looked up. His hazel eyes were sharp. Cold. He reached into his jacket pocket. His movements were fluid. Smooth. He pulled out a small package. He placed it on the table. Open it, he said. Aurora didn’t move. The package
was wrapped
in silver foil. She knew what it
felt like
. It
felt like
a key. Like a trigger. I don’t
want that, she
said. Take it or leave it, Silas said. His voice dropped. Dangerous. She reached out. Her hand hovered. She took it. The foil crinkled. It felt heavy. Cold. She unwrapped the corner. Inside was a photograph. A black-and-white print. She flipped it over. It showed a woman. Blonde hair. Blue eyes. The woman wasn’t her. Who is this? Aurora asked. It’s who you
were meant
to save, Silas said. He watched the smoke from the corner of the room. It curled upwards. Stagnant air. I’m not saving people for you anymore. My life is separate. The delivery job is separate. The bar is separate. Your life is a lie, Silas said. He leaned forward. The chair creaked. You
think
you hid behind that name. That flat. I watched the door. I watched the people. They follow you. Aurora stared at the photo. The woman in it wore a coat. A red coat. Who follows me? The ones from the Prague job, Silas said. He didn’t
look
afraid. He looked tired. The kind of tired that sleep couldn’t fix. The ones I left behind. I thought I was the last one. You were the last one until I needed a hand, Aurora. Silas reached into his pocket again. Aurora braced herself. Her feet shifted. She backed away. I didn’t ask for help. Help isn’t a request. It’s a necessity. The package felt lighter in her hand. The
weight
of the photo made her chest tight. There was a noise. The bell above the door chimed. It was a bright sound. Clear. It cut through the
silence
of the room. Aurora turned. A man stood in the doorway. He wore a dark trench coat. A hat pulled low over his eyes. Rain dripped from the brim onto the floor. The puddle grew. The man didn’t move. He just looked at Silas. He reached into his pocket. His hand was steady. The man looked at Aurora. He smiled. It wasn’t a nice smile. Silas looked up. His
eyes narrowed
. The silver ring gleamed again. He didn’t stand up. He didn’t call him. The man stepped inside. He pulled the door shut. The latch clicked. The sound
echoed
in the empty bar. The neon sign
flickered
. One second on. One second off. He took off his hat. His face
was unshaven
. Rough. I’ve been waiting a while, the man said. He pointed at the table. At the photo. At Silas. Silas didn’t move. He just looked at the man. He knows about Eva, Silas said. He kept his voice low. Dangerous. Aurora looked at him. Eva wasn’t in the room. Eva was the childhood friend who brought her to London. You said no one knows, Aurora said. Her voice
trembled
. Silas closed his eyes for a second. He opened them. They were full of fear. Real fear. He had never
looked afraid
before. That was before, Silas said. The man took a step. His boot cracked the wet leather of the bar. He looked at Aurora. You’re Aurora Carter. Or Rory. He said the name
slowly
. He said it like a curse. I don’t
know
who you are, Aurora says. She held the photo. Her hands shook. She gripped the edges until they tore. The man reached into his coat. Metal glinted. Aurora lunged. She threw the box. She threw it at the man. He didn’t flinch. The box hit his shoulder and bounced. It hit the floor with a thud. Aurora turned to Silas. Do something, she said. Silas stood up. His leg groaned. He held his hand out. A gun appeared. It was small. Black. He aimed it at the man. The man laughed. He pulled a knife. It was long. Silver. The two men circled. Like wolves. Like men who knew each other’s moves. Aurora didn’t run. She stepped back into the shadows. Behind the bar. The bottles clinked behind her. The reflection in the glass showed her wide blue eyes. The man looked at Silas. Then he looked at Aurora. Run, Silas said. The man swung his knife. Silas fired. The shot rang out. It
shattered
a bottle behind the bar. Glass rained down. Silence followed. The rain hammered on the roof. The bar light
flickered
. The man didn’t fall. He didn’t run. He just looked at the wound. He didn’t stop smiling. The man took another step. He ignored Silas. The knife was steady in his hand. No, the man said. He looked at Aurora. You’re not leaving this bar. He pointed the knife at her. Silas didn’t shoot again. He lowered the gun. The man stepped forward. Aurora backed up until her spine hit the shelf. Bottles rattled against the metal. Silas said nothing. He just watched. The man stopped. He tilted his head. You
know
why we’re here, Aurora said. The man nodded. Yes, the man said. He stepped forward. He raised the knife. The light went out. The bar plunged into darkness. The green neon died. Someone screamed.
created_at
"2026-02-25T23:41:05.992Z"
2/25/2026, 11:41:05 PM
model
"qwen/qwen3.5-flash-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
697
moderation_latency
(null)
generation_time
52093
tokens_prompt
4618
tokens_completion
6098
native_tokens_prompt
4477
native_tokens_completion
5847
native_tokens_completion_images
(null)
native_tokens_reasoning
3778
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0027865
router
(null)
provider_responses
0
endpoint_id
"5f6b71b5-8672-4b27-8b2d-f674429f9e63"
id
"chatcmpl-abe6f124-c381-93f3-b97f-87cb22778ad3"
is_byok
false
latency
697
model_permaslug
"qwen/qwen3.5-flash-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772062866-GlCRF1ag9V4JSTWzIxy9"
upstream_id
"chatcmpl-abe6f124-c381-93f3-b97f-87cb22778ad3"
total_cost
0.0027865
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
0
89.88%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1482
totalAiIsmAdverbs
3
found
0
adverb
"slightly"
count
1
1
adverb
"quickly"
count
1
2
adverb
"slowly"
count
1
highlights
0
"slightly"
1
"quickly"
2
"slowly"
100.00%
AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0
"Blackwood"
found
(empty)
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
62.89%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1482
totalAiIsms
11
found
0
word
"etched"
count
1
1
word
"crystal"
count
1
2
word
"weight"
count
2
3
word
"silence"
count
2
4
word
"echoed"
count
1
5
word
"flickered"
count
2
6
word
"trembled"
count
1
7
word
"shattered"
count
1
highlights
0
"etched"
1
"crystal"
2
"weight"
3
"silence"
4
"echoed"
5
"flickered"
6
"trembled"
7
"shattered"
66.67%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
2
maxInWindow
2
found
0
label
"eyes widened/narrowed"
count
1
1
label
"knuckles turned white"
count
1
highlights
0
"eyes narrowed"
1
"knuckles turned white"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
1
narrationSentences
303
matches
0
"looked afraid"
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
3
hedgeCount
1
narrationSentences
303
filterMatches
0
"look"
1
"think"
2
"know"
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
303
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
19
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1482
ratio
0
matches
(empty)
0.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
20
unquotedAttributions
10
matches
0
"You look tired, he said."
1
"Open it, he said."
2
"Take it or leave it, Silas said."
3
"Your life is a lie, Silas said."
4
"The ones from the Prague job, Silas said."
5
"He knows about Eva, Silas said."
6
"You said no one knows, Aurora said."
7
"That was before, Silas said."
8
"Do something, she said."
9
"Run, Silas said."
50.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
79
wordCount
1482
uniqueNames
12
maxNameDensity
1.82
worstName
"Aurora"
maxWindowNameDensity
3.5
worstWindowName
"Aurora"
discoveredNames
Aurora
27
Soho
2
Raven
1
Nest
1
Silas
26
Prague
2
Eva
3
London
1
Carter
1
Rory
1
You
11
Like
3
persons
0
"Aurora"
1
"Silas"
2
"Eva"
3
"Carter"
4
"Rory"
5
"You"
places
0
"Soho"
1
"Raven"
2
"Prague"
3
"London"
globalScore
0.589
windowScore
0.5
99.49%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
99
glossingSentenceCount
2
matches
0
"sounded like an animal dying"
1
"felt like"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1482
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
3
totalSentences
303
matches
0
"hated that it"
1
"hated that she"
2
"want that, she"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
88
mean
16.84
std
11.1
cv
0.659
sampleLengths
0
44
1
47
2
11
3
45
4
4
5
30
6
24
7
37
8
14
9
15
10
9
11
27
12
37
13
3
14
21
15
38
16
29
17
25
18
4
19
6
20
32
21
6
22
23
23
27
24
4
25
23
26
32
27
4
28
24
29
6
30
11
31
27
32
16
33
5
34
24
35
20
36
33
37
15
38
3
39
28
40
7
41
11
42
15
43
5
44
23
45
24
46
2
47
30
48
18
49
12
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
4
totalSentences
303
matches
0
"was draped"
1
"was wrapped"
2
"were meant"
3
"was unshaven"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
332
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
303
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1487
adjectiveStacks
0
stackExamples
(empty)
adverbCount
29
adverbRatio
0.019502353732347006
lyAdverbCount
4
lyAdverbRatio
0.0026899798251513113
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
303
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
303
mean
4.89
std
2.47
cv
0.506
sampleLengths
0
8
1
2
2
14
3
5
4
15
5
5
6
18
7
5
8
7
9
7
10
5
11
11
12
10
13
9
14
7
15
6
16
13
17
4
18
6
19
5
20
7
21
7
22
5
23
7
24
8
25
6
26
3
27
2
28
4
29
5
30
7
31
5
32
6
33
8
34
5
35
5
36
4
37
5
38
10
39
4
40
4
41
1
42
6
43
4
44
5
45
12
46
11
47
2
48
4
49
1
37.79%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
37
diversityRatio
0.2145214521452145
totalSentences
303
uniqueOpeners
65
24.88%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
2
totalSentences
268
matches
0
"Then she saw him."
1
"Then he looked at Aurora."
ratio
0.007
14.03%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
138
totalSentences
268
matches
0
"Her key was cold against"
1
"She turned the lock anyway."
2
"She kept her eyes on"
3
"She pushed the door open"
4
"His coat was draped over"
5
"He held a glass of"
6
"It hadn’t moved in minutes."
7
"His grey-streaked auburn beard was"
8
"It framed a face etched"
9
"His hazel eyes locked onto"
10
"They didn’t blink."
11
"Her throat felt dry."
12
"She shouldn’t have come here."
13
"She didn’t need to see"
14
"She just needed a walk."
15
"It washed the city in"
16
"She took a step forward."
17
"Her shoulder brushed the doorframe."
18
"You’re late, Silas said."
19
"His voice sounded gravel."
ratio
0.515
2.91%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
245
totalSentences
268
matches
0
"The brass knocker bit into"
1
"Her key was cold against"
2
"She turned the lock anyway."
3
"The hinges screamed, a high-pitched"
4
"The neon sign buzzed overhead."
5
"Aurora didn’t check the sky."
6
"She kept her eyes on"
7
"The creak from the stairs"
8
"The flat above remained silent."
9
"She pushed the door open"
10
"The air inside smelled of"
11
"Cigars lingered in the corners"
12
"Shadows stretched long against the"
13
"Aurora moved past the bar"
14
"The usual faces were there"
15
"Silas sat in the shadowed"
16
"The leather stool looked worn."
17
"His coat was draped over"
18
"He held a glass of"
19
"It hadn’t moved in minutes."
ratio
0.914
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
268
matches
(empty)
ratio
0
95.24%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
15
technicalSentenceCount
1
matches
0
"Eva was the childhood friend who brought her to London."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
0
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
0
78.1257%