NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBFMF4YEHJ3FCZ8J9RRX7NR
Run Details
Model:
Qwen 3.5 122B
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
10m 19s
Cost:
$0.271196
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
90.24%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
80.48%
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)
0.00%
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)
94.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
32.23%
Sentence opener variety
(details)
36.04%
Adverb-first sentence starts
(details)
44.86%
Pronoun-first sentence starts
(details)
0.00%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
82.5951%
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 door to The Raven's
Nest slammed shut behind her.
A gust of damp London
air followed Aurora Carter inside, carrying the scent of rain and exhaust fumes. She shook her umbrella hard, sending a spray of water across the dark wooden floorboards.
The bar smelled of stale
beer, old paper, and the sharp tang of lemon polish. Silas stood behind the counter, polishing a glass with a rag that looked older than the building itself. He did not look up.
Aurora walked to the corner
table.
She set her delivery bag
down with a heavy thud. The neon sign outside buzzed, casting a sickly green glow through the frosted glass of the window.
She needed a moment before
heading upstairs to her flat.
The shift at Golden Empress
had been long, and her feet
throbbed
inside her boots. "You look like you've seen a ghost, Rory." She froze.
The voice came from the
booth in the shadows.
A man sat there, half-hidden
by the dim light.
He wore a suit that
cost more than her monthly rent, but it hung on him
loosely
. His face had changed.
The sharp angles of his
jaw
were gone
, replaced by softness.
His eyes, once bright with
ambition, now looked tired and hollow. "Julian."
Aurora kept her voice steady
. "I didn't think you were in London." "London is a small place when you're running from something."
Julian stood up
.
He moved slowly, as if
his joints ached.
He walked around the table
and pulled out the chair opposite her. "Sit down. You look exhausted." Aurora hesitated.
She looked at Silas behind
the bar.
He had stopped polishing the
glass.
His hazel eyes were fixed
on the two of them. He knew Julian. The recognition was instant in the set of his jaw. "I have to work," Aurora said. "I can't stay." "Five minutes." Julian's voice was quiet. "Please. For old times' sake." Aurora sat.
She kept her bag on
her lap. The leather felt cool against her hands. Julian poured a drink from a bottle on the table. It was amber liquid. Whisky.
He slid the glass across
the wood. "I heard you left Cardiff," Julian said. "Heard you went to law school. Then I heard you dropped out." "I didn't drop out," Aurora said. "I left." "Same thing." Julian took a sip. "You always were better at running than fighting." Aurora felt the heat rise in her cheeks.
She touched the small crescent-shaped
scar on her left wrist.
It was a habit she
had developed since Evan. "Why are you here, Julian?" Julian leaned forward. The shadows deepened around his face. "I need your help." "My help?" Aurora laughed.
It was a dry, brittle
sound. "I deliver food for a living, Julian. I don't do favors anymore." "This isn't a favor." Julian's hand shook
slightly
as he set the glass down. "It's a debt. You remember the thesis?" Aurora remembered.
They had worked on it
together in the library. It
was supposed
to be about corporate law and human rights. It became something else. Something darker. She had walked away before the end. "I remember," Aurora said. "I didn't walk away." Julian looked at her. "I stayed. And now they want what we found." "Who?" Julian didn't answer. He reached into his jacket pocket. Aurora tensed. Her hand moved to the bag on her lap. "Relax," Julian said. "It's just a photo." He placed a photograph on the table. It was black and white. It showed a building. A warehouse on the docks. Aurora recognised the architecture. It was in Cardiff. "This was taken yesterday," Julian said. Aurora picked up the photo. The edges were worn. "Why show me this?" "Because you know the layout." Julian's voice dropped to a
whisper
. "You know the back entrance. You know the guard rotations." "I don't know anything anymore." "You know more than you think." Julian leaned back. "They're moving the shipment tonight." Aurora looked at the photo again. The warehouse looked empty. But she knew better. She had seen the blueprints once. Julian had shown her. "I'm not getting involved," Aurora said. She stood up. "I'm leaving." "You can't leave."
Julian stood up
too. He was taller than her. He
loomed
over the table. "If you leave, they'll find you." "Who?" Aurora asked again. "Who is they?" Julian smiled. It was a terrible smile. It didn't reach his eyes. "The people who paid for my suit." Silas moved from behind the bar. He walked with a slight limp in his left leg. He stopped at the edge of their table. He looked at Julian. "Julian," Silas said. "You shouldn't be here." Julian turned to Silas. "You know him too, Si?" "I know what you do." Silas's voice was calm. "And I know you're dangerous." "I'm not dangerous." Julian laughed. "I'm desperate." Aurora looked between them. The air in the bar felt heavy. The
silence
stretched. The neon sign buzzed louder. "Give me the photo," Aurora said. Julian hesitated. Then he handed it over. "Go," Silas said. "Take the back door." "I'm not going anywhere," Aurora said. "You have to." Silas's hand moved to his pocket. He pulled out a small key. He tossed it to Aurora. "It opens the safe in the back room. Take what's inside. It's yours." Aurora caught the key. It was cold in her hand. "What's in the safe?" "Proof," Silas said. "Proof of what Julian did." Julian's face went pale. "You wouldn't." "I would." Silas looked at Julian. "You betrayed us once. You won't do it again." Aurora looked at the key. Then she looked at Julian. He looked small. He
looked afraid
. "I'm going upstairs," Aurora said. "No," Julian said. "You can't go upstairs." "Why?" Aurora asked. "Because they're waiting for you." Aurora stopped. She looked at the door. The green neon sign
flickered
. "Who?" she asked. Julian didn't answer. He turned and walked toward the door. He opened it. The wind howled inside. Aurora looked at Silas. He nodded. "Go," he said. "Now." Aurora ran. She ran toward the back door. She pushed it open. The alley was dark. A black car idled at the end. Two men stood by the door. They turned as she ran. Aurora stopped. She looked at the car. The engine hummed. One of the men pulled a gun. Aurora ran. She ran toward the car. She didn't look back. The door slammed shut behind her. The sound
echoed
in the alley. She reached the car. She opened the door. A man sat in the back. He looked up. "Get in," he said. Aurora looked at him. She looked at the gun in the other man's hand. "Who are you?" she asked. "Someone who can help," the man said. "Get in." Aurora looked at the alley. She looked at the men. She looked at the car. She got in. The door slammed shut. The car moved. The alley faded. Aurora looked at the man. He smiled. "Welcome to London," he said. Aurora looked out the window. The city blurred past. The neon sign of The Raven's Nest disappeared. The car turned a corner. The man handed her a phone. "Call Julian," he said. Aurora looked at the phone. She looked at the man. "Why?" she asked. "Because he's the only one who can stop them," the man said. Aurora dialled the number. It rang once. "Hello?" Julian's voice came through. "Julian," Aurora said. "I'm in the car." "Good," Julian said. "Now run." The line went dead. Aurora looked at the man. He smiled. "Run," he said. Aurora ran. She ran toward the back of the car. She opened the door. She jumped out. The car skidded. The man inside shouted. Aurora ran. She ran into the night. The city lights blurred. The sound of the car faded. She stopped. She looked at the street. It was empty. She took a breath. She looked at the key in her hand. She walked. She walked toward the lights. The car engine roared behind her. Aurora ran. The door slammed shut. The car moved. The alley faded. Aurora looked at the man. He smiled. "Welcome to London," he said. Aurora looked out the window. The city blurred past. The neon sign of The Raven's Nest disappeared. The car turned a corner. The man handed her a phone. "Call Julian," he said. Aurora looked at the phone. She looked at the man. "Why?" she asked. "Because he's the only one who can stop them," the man said. Aurora dialled the number. It rang once. "Hello?" Julian's voice came through. "Julian," Aurora said. "I'm in the car." "Good," Julian said. "Now run." The line went dead. Aurora looked at the man. He smiled. "Run," he said. Aurora ran. She ran toward the back of the car. She opened the door. She jumped out. The car skidded. The man inside shouted. Aurora ran. She ran into the night. The city lights blurred. The sound of the car faded. She stopped. She looked at the street. It was empty. She took a breath. She looked at the key in her hand. She walked. She walked toward the lights. The car engine roared behind her. Aurora ran.
created_at
"2026-02-25T22:45:07.876Z"
2/25/2026, 10:45:07 PM
model
"qwen/qwen3.5-122b-a10b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
811
moderation_latency
(null)
generation_time
618567
tokens_prompt
4618
tokens_completion
78477
native_tokens_prompt
4477
native_tokens_completion
84189
native_tokens_completion_images
(null)
native_tokens_reasoning
81920
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
0.2711956
router
(null)
provider_responses
0
endpoint_id
"33d466d1-d2f7-45ed-8ff3-fda7d2e32351"
id
"chatcmpl-717bbb73-e02c-96e9-a2f7-8c35f9cfc8cf"
is_byok
false
latency
811
model_permaslug
"qwen/qwen3.5-122b-a10b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772059507-ANTXgXVWNRnFGssBGO1k"
upstream_id
"chatcmpl-717bbb73-e02c-96e9-a2f7-8c35f9cfc8cf"
total_cost
0.2711956
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
49
adverbTagCount
3
adverbTags
0
"Julian's hand shook slightly [slightly]"
1
"Julian leaned back [back]"
2
"Aurora asked again [again]"
dialogueSentences
92
tagDensity
0.533
leniency
1
rawRatio
0.061
effectiveRatio
0.061
90.24%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1537
totalAiIsmAdverbs
3
found
0
adverb
"loosely"
count
1
1
adverb
"slowly"
count
1
2
adverb
"slightly"
count
1
highlights
0
"loosely"
1
"slowly"
2
"slightly"
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)
80.48%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1537
totalAiIsms
6
found
0
word
"throbbed"
count
1
1
word
"whisper"
count
1
2
word
"loomed"
count
1
3
word
"silence"
count
1
4
word
"flickered"
count
1
5
word
"echoed"
count
1
highlights
0
"throbbed"
1
"whisper"
2
"loomed"
3
"silence"
4
"flickered"
5
"echoed"
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
1
narrationSentences
246
matches
0
"looked afraid"
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
246
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
287
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
18
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1537
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
35
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
103
wordCount
1184
uniqueNames
11
maxNameDensity
4.22
worstName
"Aurora"
maxWindowNameDensity
6.5
worstWindowName
"Aurora"
discoveredNames
Raven
3
Nest
3
London
1
Aurora
50
Carter
1
Golden
1
Empress
1
Julian
30
Silas
11
Evan
1
Cardiff
1
persons
0
"Raven"
1
"Nest"
2
"Aurora"
3
"Carter"
4
"Empress"
5
"Julian"
6
"Silas"
7
"Evan"
places
0
"London"
1
"Golden"
2
"Cardiff"
globalScore
0
windowScore
0
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
68
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
1537
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
287
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
117
mean
13.14
std
12.31
cv
0.937
sampleLengths
0
81
1
58
2
8
3
63
4
13
5
38
6
38
7
9
8
11
9
38
10
19
11
8
12
14
13
32
14
13
15
22
16
21
17
35
18
4
19
17
20
1
21
20
22
7
23
29
24
6
25
13
26
21
27
5
28
14
29
24
30
11
31
23
32
7
33
19
34
28
35
7
36
9
37
14
38
7
39
19
40
6
41
7
42
7
43
6
44
33
45
14
46
8
47
6
48
15
49
16
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
3
totalSentences
246
matches
0
"were gone"
1
"were fixed"
2
"was supposed"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
262
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
287
ratio
0
matches
(empty)
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1186
adjectiveStacks
1
stackExamples
0
"small crescent-shaped scar"
adverbCount
17
adverbRatio
0.01433389544688027
lyAdverbCount
5
lyAdverbRatio
0.0042158516020236085
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
287
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
287
mean
5.36
std
3.05
cv
0.57
sampleLengths
0
10
1
18
2
15
3
15
4
18
5
5
6
6
7
10
8
17
9
10
10
15
11
8
12
2
13
9
14
9
15
17
16
4
17
11
18
11
19
6
20
7
21
13
22
8
23
12
24
5
25
2
26
7
27
6
28
10
29
3
30
10
31
6
32
3
33
6
34
5
35
2
36
7
37
7
38
10
39
4
40
1
41
7
42
7
43
12
44
6
45
2
46
6
47
8
48
8
49
10
32.23%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
51
diversityRatio
0.16376306620209058
totalSentences
287
uniqueOpeners
47
36.04%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
2
totalSentences
185
matches
0
"Then he handed it over."
1
"Then she looked at Julian."
ratio
0.011
44.86%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
81
totalSentences
185
matches
0
"She shook her umbrella hard,"
1
"He did not look up."
2
"She set her delivery bag"
3
"She needed a moment before"
4
"He wore a suit that"
5
"His face had changed."
6
"His eyes, once bright with"
7
"He moved slowly, as if"
8
"He walked around the table"
9
"She looked at Silas behind"
10
"He had stopped polishing the"
11
"His hazel eyes were fixed"
12
"He knew Julian."
13
"She kept her bag on"
14
"It was amber liquid."
15
"He slid the glass across"
16
"She touched the small crescent-shaped"
17
"It was a habit she"
18
"It was a dry, brittle"
19
"They had worked on it"
ratio
0.438
0.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
180
totalSentences
185
matches
0
"The door to The Raven's"
1
"A gust of damp London"
2
"She shook her umbrella hard,"
3
"The bar smelled of stale"
4
"Silas stood behind the counter,"
5
"He did not look up."
6
"Aurora walked to the corner"
7
"She set her delivery bag"
8
"The neon sign outside buzzed,"
9
"She needed a moment before"
10
"The shift at Golden Empress"
11
"The voice came from the"
12
"A man sat there, half-hidden"
13
"He wore a suit that"
14
"His face had changed."
15
"The sharp angles of his"
16
"His eyes, once bright with"
17
"Aurora kept her voice steady"
18
"Julian stood up"
19
"He moved slowly, as if"
ratio
0.973
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
185
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
21
technicalSentenceCount
1
matches
0
"Silas stood behind the counter, polishing a glass with a rag that looked older than the building itself."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
49
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
37
fancyCount
2
fancyTags
0
"Aurora laughed (laugh)"
1
"Julian laughed (laugh)"
dialogueSentences
92
tagDensity
0.402
leniency
0.804
rawRatio
0.054
effectiveRatio
0.043
82.5951%