NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ7QRFMJ0N1MHR7PTE1S266
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
39.7s
Cost:
$0.001878
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
77.92%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
74.25%
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)
100.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
44.54%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
99.18%
Subject-first sentence starts
(details)
51.55%
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)
91.5811%
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 knife stopped just short
of the apple’s core. Aurora exhaled. One smooth twist, and the blade came free, slick with juice.
She wiped it clean on
her jeans, eyes fixed on the exit of The
Raven’s Nest
. Ten past midnight. Last call had come and gone, the final stragglers nudged
gently
toward the street by Silas’ calm but unyielding presence.
Now only the hum of
the fridge behind the bar and the occasional creak of old floorboards kept her company.
She had delivered for the
Golden Empress earlier, parked her scooter out back, and stayed for one drink. Just one. That was the rule. But Silas had looked her in the eye, poured a single measure of Islay into a tumbler, and said nothing. So she stayed.
The bookshelf shifted with a
soft grind. She didn’t turn. Knew the sound too well.
The hidden door only opened
for two reasons: business or blood. “You’re up late,” Silas said. “So are you.”
He limped in, right hand
resting briefly on the edge of the bar.
The signet ring caught the
low light—silver, worn smooth on one side, the crest barely legible.
He poured himself the same
drink, same glass, same
silence
.
Then he placed a folded
square of paper beside her hand. She didn’t touch it. “Found it slipped into the till drawer,” he said. “No name. No message. Just your postcode.” Aurora unfolded it. A phone number. Neat handwriting. Rounded letters.
She hadn’t seen that hand
in five years. She folded the paper again. Slow. Precise. Placed it in her jacket pocket. “Still running?” he asked. “No.”
She tapped the crescent scar
on her wrist. “Just walking.” “Eva?” She gave a single nod. Silas sat, folded his hands. “The last I heard, she was in Berlin. Tech firm. Good money. Clean cut.” “She called me this morning.” “And?” “She said, *I’m back. Let’s have tea like we used to.*” Silas took a slow sip. “That’s not why you’re here.” “No.”
She pulled the tumbler closer
. “She’s not coming for tea.” He waited. “She’s staying at the Langham.” Silas exhaled through his nose. “You’ve seen her?” “Not yet. I told her I’d call.” “And you haven’t.” “No.” Silas stood, walked to the jukebox in the corner. Flipped through the worn sleeves. Chose one. A low, smoky Billie Holiday number filled the air, the kind that clung to the walls like damp. “Five years is a long time to avoid a friend,” he said. “She wasn’t a friend five years ago.” “She was.” “She left.” “She saved her own skin.” Aurora laughed, quiet and sharp. “Funny. That’s what Evan used to say. *She saved herself. You should’ve done the same.*” Silas turned. “And you didn’t.” “I didn’t run fast enough.” “You’re here now.” “Because of you.” “No.”
He pointed at her with
the neck of his glass. “Because of that scooter out back. Because you learned how to disappear mid-turn. Because you check your mirrors
not for traffic, but for faces
.” She didn’t answer. “You’ve changed,” he said. “So have you.” “Not
really
.” “Retired spymasters don’t run dive bars with back rooms for arms dealers and runaway daughters.” “The bar’s real,” he said. “The rest is just foot traffic.” She looked at him. Really looked. The grey in his hair. The deeper lines around his eyes. The way his left leg braced before he shifted his
weight
. He’d aged, but not softened. Still coiled. Still sharp. “You’re different too,” he said. “Used to you talk too much. Over-explain. Now you ration words like bullets.” “I learned
silence
keeps you alive.” “And Eva?” “She talks like nothing ever happened.” “Maybe nothing did.” “She knows.” “Then she’s lying.” “Or she’s chosen to forget.” “People do.” “Not me.” “No. You remember everything.” He paused. “Even the things that weren’t true.”
She set the glass down
hard enough to make the ice jump. “What does that mean?” Silas didn’t flinch. “Evan didn’t control you because you were weak. He controlled you because you believed you were.” “I didn’t—” “You stayed. For two years after the first mark.”
He nodded at her wrist
. “That wasn’t from a childhood accident. It was from the first time he slammed your hand in the car door.” Her breath caught. Just once. “You told me it was a bicycle,” he said. “I wanted to.” “Why?” “Because I didn’t want to be that woman.” “And now?” “Now I am.” Silas leaned forward, voice low. “No. You’re the woman who walked out. Who changed her name. Who learned to ride fast, look sharp, and never sleep with the lights off. You’re the one who survived.” “Survival’s not the same as living.” “No. But it’s a start.” The jukebox clicked. Silence returned. She stared at her hands. “She wants to meet tomorrow. Eleven. At the Wolseley.” “Fancy.” “She always liked feeling important.” Silas stood, took both glasses. “Then go. See what’s left.” “I don’t want to.” “But you will.” “She’ll look at me and see a ghost.” “And you’ll look at her and see a coward.” “Or worse. A mirror.” Silas paused at the edge of the light. “You think she doesn’t feel it? The guilt? The distance? The way she never called, never wrote, never showed up with a suitcase and a *
I’m so sorry
*?” “She could’ve tried.” “She did. She called me. Last year. Asked about you.” Aurora froze. “You didn’t tell her.” “No.” “Why not?” “Because some ghosts need space to settle.” She looked up, eyes bright. “And now?” “Now she’s standing in the rain at your doorstep, metaphorically speaking. And you’ve got the chain on.” Silence.
Then the door to the
street opened. A gust of damp night air slipped in. A woman stood in the doorway. Hair dyed platinum, pulled into a high knot. A cream coat, tailored to precision. Gloves. One hand clutching a leather clutch, the other hovering near the frame, uncertain. She didn’t step inside. Her eyes landed on Aurora. Time didn’t just slow. It split. Five years vanished and returned all at once. Eva. But not Eva. The girl who once shared chips with Rory behind Taff’s Well had
been polished
into something sharper, colder. Jewelry subtle but expensive. Posture rigid. Eyes wide, searching, scared. Aurora didn’t move. “Rory,” Eva said. Voice softer than memory. “I wasn’t sure you’d come.” “I didn’t.” “I saw your scooter.” “I was leaving.” Eva stepped forward. Just one step. The door clicked shut behind her. Silas watched.
Then turned, slowly, to the
back room. The bookshelf whispered closed. Left alone. The air thickened. Eva’s gaze dropped to Aurora’s wrist. The scar, pale under the dim light. “I didn’t know,” she said. “You knew enough.” “I didn’t understand.” “You ran.” “I thought—” “What? That I’d follow? That I’d show up at your hostel with a backpack and a smile and we’d take a train to Paris?” “I left you a number.” “You left me a city.” Eva swallowed. “I thought you’d be free.” Aurora stood. Taller now. Calmer. “I am.” Eva reached into her clutch. Pulled out a small bottle. Dark glass. “Found this in my things. From before. You used to love it.” Aurora looked at the label. *
Chanel No. 5
*. The scent she wore the night Evan first broke her finger. She took the bottle. Held it in her palm.
Then dropped it to the
floor. It
shattered
. The scent bloomed—rose, vanilla, regret. “You don’t get to bring that back,” Aurora said. Eva’s face tightened. Not tears. Not anger. Something worse. Recognition. “I didn’t come to fix it,” she said. “No.” Aurora stepped closer. “You came to see if I was broken.” Eva didn’t answer. The
silence
cracked like glass. Then— “I am,” Aurora said. “But not how you think.” She turned, reached behind the bar. Pulled out a spare tumbler. Poured two fingers of whisky. Held it out. “Drink.” Eva stared at the glass. Then at Aurora. Slowly, she took it. Their fingers didn’t touch. Outside, the neon *
Raven’s Nest
* buzzed
softly
in the rain. And for the first time in five years, the past stopped chasing them long enough to sit down.
created_at
"2026-03-25T10:13:12.008Z"
3/25/2026, 10:13:12 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
883
moderation_latency
(null)
generation_time
39248
tokens_prompt
4618
tokens_completion
2476
native_tokens_prompt
4216
native_tokens_completion
2086
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.00187772
router
(null)
provider_responses
0
endpoint_id
"043eb28f-fc28-4b0d-9800-b249fcfcfbf9"
is_byok
false
latency
17
model_permaslug
"qwen/qwen3-235b-a22b-07-25"
provider_name
"Parasail"
status
429
1
endpoint_id
"813ce28a-1334-47e3-881e-a7f8833b34b4"
id
"chatcmpl-73cb847e-d1f2-9dfa-bf6e-f25ad2ac59ea"
is_byok
false
latency
883
model_permaslug
"qwen/qwen3-235b-a22b-07-25"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774433592-sfo3ouXVcjDtE3FnBQkL"
upstream_id
"chatcmpl-73cb847e-d1f2-9dfa-bf6e-f25ad2ac59ea"
total_cost
0.00187772
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
20
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
106
tagDensity
0.189
leniency
0.377
rawRatio
0
effectiveRatio
0
77.92%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1359
totalAiIsmAdverbs
6
found
0
adverb
"gently"
count
1
1
adverb
"really"
count
2
2
adverb
"slowly"
count
2
3
adverb
"softly"
count
1
highlights
0
"gently"
1
"really"
2
"slowly"
3
"softly"
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)
74.25%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1359
totalAiIsms
7
found
0
word
"silence"
count
5
1
word
"weight"
count
1
2
word
"shattered"
count
1
highlights
0
"silence"
1
"weight"
2
"shattered"
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
146
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
146
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
233
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
30
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
5
markdownWords
25
totalWords
1357
ratio
0.018
matches
0
"I’m back. Let’s have tea like we used to."
1
"She saved herself. You should’ve done the same."
2
"I’m so sorry"
3
"Chanel No. 5"
5/1/2001, 12:00:00 AM
4
"Raven’s Nest"
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
25
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
49
wordCount
748
uniqueNames
15
maxNameDensity
1.74
worstName
"Aurora"
maxWindowNameDensity
5
worstWindowName
"Eva"
discoveredNames
Raven
2
Nest
2
Golden
1
Empress
1
Silas
12
Islay
1
Aurora
13
Billie
1
Holiday
1
Eva
10
Rory
1
Taff
1
Well
1
Voice
1
Evan
1
persons
0
"Raven"
1
"Nest"
2
"Silas"
3
"Aurora"
4
"Billie"
5
"Holiday"
6
"Eva"
7
"Rory"
8
"Taff"
9
"Well"
10
"Evan"
places
(empty)
globalScore
0.631
windowScore
0
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
40
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.737
wordCount
1357
matches
0
"not for traffic, but for faces"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
233
matches
0
"seen that hand"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
148
mean
9.17
std
10.21
cv
1.114
sampleLengths
0
9
1
72
2
47
3
7
4
19
5
5
6
3
7
39
8
11
9
4
10
16
11
18
12
13
13
4
14
11
15
1
16
5
17
19
18
5
19
1
20
11
21
10
22
11
23
2
24
5
25
8
26
7
27
3
28
1
29
34
30
12
31
7
32
2
33
2
34
5
35
20
36
5
37
5
38
3
39
3
40
35
41
3
42
4
43
3
44
2
45
15
46
11
47
37
48
18
49
6
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
146
matches
0
"been polished"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
148
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
3
semicolonCount
0
flaggedSentences
3
totalSentences
233
ratio
0.013
matches
0
"The signet ring caught the low light—silver, worn smooth on one side, the crest barely legible."
1
"The scent bloomed—rose, vanilla, regret."
2
"Then—"
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
462
adjectiveStacks
0
stackExamples
(empty)
adverbCount
11
adverbRatio
0.023809523809523808
lyAdverbCount
2
lyAdverbRatio
0.004329004329004329
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
233
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
233
mean
5.82
std
5.02
cv
0.863
sampleLengths
0
9
1
2
2
11
3
16
4
3
5
20
6
20
7
18
8
2
9
4
10
20
11
3
12
7
13
3
14
5
15
11
16
5
17
3
18
13
19
16
20
10
21
11
22
4
23
9
24
7
25
3
26
3
27
2
28
2
29
8
30
5
31
1
32
1
33
6
34
4
35
9
36
2
37
1
38
5
39
5
40
14
41
5
42
1
43
11
44
5
45
5
46
6
47
5
48
2
49
5
44.54%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
15
diversityRatio
0.30603448275862066
totalSentences
232
uniqueOpeners
71
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
7
totalSentences
97
matches
0
"Then he placed a folded"
1
"Then the door to the"
2
"Just one step."
3
"Then turned, slowly, to the"
4
"Then dropped it to the"
5
"Then at Aurora."
6
"Slowly, she took it."
ratio
0.072
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
25
totalSentences
97
matches
0
"She wiped it clean on"
1
"She had delivered for the"
2
"She didn’t turn."
3
"He limped in, right hand"
4
"He poured himself the same"
5
"She didn’t touch it."
6
"She hadn’t seen that hand"
7
"She folded the paper again."
8
"She tapped the crescent scar"
9
"She gave a single nod."
10
"She pulled the tumbler closer"
11
"He pointed at her with"
12
"She didn’t answer."
13
"She looked at him."
14
"He’d aged, but not softened."
15
"She set the glass down"
16
"He nodded at her wrist"
17
"Her breath caught."
18
"She stared at her hands."
19
"She looked up, eyes bright."
ratio
0.258
99.18%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
70
totalSentences
97
matches
0
"The knife stopped just short"
1
"She wiped it clean on"
2
"She had delivered for the"
3
"That was the rule."
4
"The bookshelf shifted with a"
5
"She didn’t turn."
6
"The hidden door only opened"
7
"He limped in, right hand"
8
"The signet ring caught the"
9
"He poured himself the same"
10
"She didn’t touch it."
11
"Aurora unfolded it."
12
"A phone number."
13
"She hadn’t seen that hand"
14
"She folded the paper again."
15
"She tapped the crescent scar"
16
"She gave a single nod."
17
"Silas sat, folded his hands."
18
"Silas took a slow sip."
19
"She pulled the tumbler closer"
ratio
0.722
51.55%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
97
matches
0
"Now only the hum of"
ratio
0.01
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
18
technicalSentenceCount
0
matches
(empty)
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
20
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
13
fancyCount
0
fancyTags
(empty)
dialogueSentences
106
tagDensity
0.123
leniency
0.245
rawRatio
0
effectiveRatio
0
91.5811%