NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-12-01KKHZGX5YZ9K9DFMP3DH6ND2M
Run Details
Model:
Grok 4.20 (Beta, Reasoning)
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
30.3s
Cost:
$0.035264
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
90.91%
Adverbs in dialogue tags
(details)
82.12%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
55.30%
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)
19.69%
Name drop frequency
(details)
47.26%
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)
98.86%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
59.03%
Sentence opener variety
(details)
100.00%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
0.00%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
86.47%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
84.6546%
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
Aurora slammed her glass down.
Eva stood there at the
edge of the table, coat still buttoned against the Soho night.
The years had sharpened her
cheekbones and dulled her eyes to a flat grey. "Rory Carter. In a bar. I thought the universe had a
sense of
humour but this is ridiculous."
Aurora pushed the spare stool
out with her foot. "Sit before Silas throws you out for loitering. He has rules." Eva sat.
Her movements carried a new
stiffness, like someone accustomed to being watched.
The expensive wool coat fell
open to reveal a
silk
blouse that cost more than Aurora made in a month.
Time had dressed one of
them in armour and left the other in yesterday's delivery uniform. "You live here now."
Eva glanced at the staircase
visible behind the bar. "Above a pub. My father always said you'd end up in politics or prison. Never mentioned hospitality."
The words landed softly enough
but carried teeth.
Aurora felt her left wrist
twitch and resisted the urge to cover the small crescent scar. "Delivery work pays the rent. Keeps me moving. What about you? Still chasing briefs in Cardiff?" Eva signalled to the bar.
Silas appeared without hurry, his
slight limp more pronounced than usual tonight.
The silver signet ring caught
the light as he rested both palms on the counter. "Two more of whatever she's having."
Eva's voice carried the clipped
precision of courtrooms. "And whatever you're drinking yourself, Mr Blackwood. You look like a man who knows how to pour for trouble."
Silas studied her a moment
longer than necessary. "Two bitters. One water."
He slid the drinks across
without comment but his hazel eyes
flicked
to Aurora in silent question.
She gave the smallest shake
of her head.
He retreated to the other
end of the bar, polishing a glass that didn't need polishing. Eva lifted her drink. "Still collecting strays, I see." "He's not a stray. He's the reason I have a roof."
Aurora took a long swallow
. The bitterness suited her mood. "You didn't answer my question." "Senior counsel now. Specialise in family law. Irony isn't lost on me." Eva's laugh cracked at the edges. "I spend my days extracting women from men like Evan. Funny how that works." The name sat between them like a third presence. Aurora's fingers found the scar again,
tracing
the
familiar
ridge without thinking. Eva noticed. Of course she noticed. "Does it still ache when it rains?" "It never ached. That was your line, not mine." Aurora kept her tone light but the memory pressed close, the childhood accident on the rocks below Penarth pier, Eva's small hand gripping hers as the blood mixed with seawater. They had been nine. The world had
seemed simpler then, before university, before law, before Evan turned love into a cage
. Eva leaned forward. The green glow from the neon sign outside painted her face in sickly light. "You left without a proper goodbye. One text saying you were going to London. Then
silence
. I thought he'd killed you." "I needed to disappear. You knew that." "I knew you needed help. I didn't know you'd vanish
completely
." Eva's grip tightened around her glass until the knuckles showed white. "I drove past your parents' house every week for a year. Your mother still sets a place for you at Sunday lunch. Empty chair. Like you're dead but they can't bury you." The words landed harder than any blow. Aurora looked away, tracking Silas as he moved between tables.
His grey-streaked auburn hair caught
the light from the old maps on the walls. The Raven's Nest had become her refuge, its walls covered in black-and-white photographs of places she would never visit. Safe. Predictable. Nothing like the life she had fled. "You changed your number," Aurora said finally. "Three times. I tried." "Work. New clients. New life." Eva waved a hand
as if brushing away the lie
. "The truth is I was angry. Still am, a bit. You got out and I stayed behind cleaning up the mess you left." The sentence carried more
weight
than its words. Aurora waited. The bar's low hum filled the
silence
between them, the clink of bottles, the murmur of other people's problems. Someone laughed too loudly near the door. Both women flinched at the sound. "Clean up how?" Aurora asked. Eva looked into her drink as if the answer floated there. "Evan came to see me six months after you left. Said you stole money. Said you owed him. He had that look in his eye. The one that used to make you shrink." Aurora's
stomach
tightened.
She remembered that look too
well. The way the room would grow smaller, the way her own voice would fade until it became nothing. "What did you do?" "Gave him what he wanted. Then I made sure he understood that if he ever came near me or your family again, I'd bury him in so much legal paperwork he'd never see daylight." Eva's smile was thin and sharp. "Turns out I'm quite good at destruction when I put my mind to it." The confession should have brought relief.
Instead it settled between them
like ash. Aurora studied the woman across from her, searching for the girl who had once smuggled cigarettes and dreams down to the bay. That girl had soft edges and louder laughs. This version moved like someone who had learned the exact price of survival. "You became him to beat him." "I became necessary." Eva's voice dropped. "That's the part no one tells you about growing up. Someone has to be the monster sometimes. I got tired of waiting for you to come back and do it." Silas appeared again, setting down a bowl of peanuts neither woman had asked for.
His limp made the movement
awkward but his hands remained steady. The signet ring clicked against the bowl. "Conversation looks heavy. Need the back room?" "Not yet." Aurora managed a small smile. "Thanks, Si."
He nodded once and moved
on, but not before giving Eva another measuring look. The Spymaster didn't miss much. Aurora suspected he already had her name, her profession, and her blood type filed away somewhere. Eva watched him go. "He knows, doesn't he? About Evan. About everything." "Some. Not all. Silas collects pieces of people. Never the whole puzzle unless he needs to." "Smart." Eva pushed the peanuts away untouched. "I came to London for a case. Corporate nonsense. But I asked around. Golden Empress restaurant. The girl who delivers their food. Small world." "You could have called first." "Would you have answered?" The question hung there. Aurora wanted to say yes. The word stuck in her throat like all the other unsaid things, the letters never sent, the nights she had picked up the phone only to set it down again. Time had built walls between them that neither knew how to dismantle. "I thought about you," Aurora admitted. "Every time I passed a law firm. Every time someone mentioned Cardiff. I wondered if you were married. If you'd kept playing the piano. If you still hated mushrooms." "I still hate mushrooms." Eva's laugh came out shaky. "Never married. Who has time? The job eats everything. Some days I wake up and can't remember what my own flat looks like. Just hotel rooms and court documents." The admission cost her. Aurora saw it in the way Eva's shoulders dropped a fraction, the way her fingers
trembled
slightly
around the glass. This was the closest either of them had come to saying the truth: that neither had built the life they had promised each other at eighteen. "We were supposed to change the world," Aurora said quietly. "You were going to be the youngest QC in Wales. I was going to... God knows. Something that made my father proud." "Instead I destroy families for money and you deliver Chinese food." Eva's voice cracked on the last word. "Brilliant." The bitterness in it surprised them both. Silence stretched. The bar had grown quieter around them, the evening crowd thinning to the dedicated drinkers who preferred shadows. One of the black-and-white photographs on the wall caught Aurora's eye, an old image of Prague that Silas refused to explain. Another city. Another set of regrets. Eva reached across the table
suddenly
.
Her hand hovered above Aurora's
wrist,
not quite touching the scar
. "I missed you. Every single day. Even when I hated you." The words should have healed something.
Instead they opened the wound
wider. Aurora felt the
weight
of every missed birthday, every Christmas she had spent alone in the flat upstairs, listening to the sounds of the bar below. The girl she had
been died
in Cardiff. The woman she became still carried the body. "I missed you too." The confession came out rough. "But I can't go back. Not to that person. She was terrified all the time." "I know." Eva withdrew her hand. "Neither of us can. That's the worst part. We survived and now we have to live with who survival made us." The neon sign outside
flickered
once, casting their faces in momentary darkness. When the light returned Eva looked older, more exhausted. The expensive clothes
suddenly
seemed like costume. Aurora opened her mouth to respond but Eva's phone buzzed against the table. The screen lit up with a name that made Aurora's blood freeze. Evan. Eva saw it too. Her face went
very
still. "He's been calling again. Left messages. Says he wants to talk about old times. About you." The words dropped between them like a blade. Aurora stared at the phone, at the name she had spent years trying to forget. Silas watched from behind the bar, his expression
unreadable
. The slight limp forgotten as he straightened, ready for whatever came next. Eva didn't answer the call. She simply looked at Aurora, all the years and the regrets and the versions of themselves they had lost laid bare in that single glance. "What do we do now?" The phone kept ringing.
created_at
"2026-03-12T21:33:56.804Z"
3/12/2026, 9:33:56 PM
model
"x-ai/grok-4.20-beta-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
18416
moderation_latency
(null)
generation_time
30171
tokens_prompt
4618
tokens_completion
2525
native_tokens_prompt
4174
native_tokens_completion
5734
native_tokens_completion_images
0
native_tokens_reasoning
3686
native_tokens_cached
4160
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
"completed"
usage
0.035264
router
(null)
provider_responses
0
endpoint_id
"33f49f24-a0de-4dcf-872d-ca514e83fbae"
id
"f500eb81-fc61-522c-8e04-ef059d0edb0d"
is_byok
false
latency
270
model_permaslug
"x-ai/grok-4.20-beta-20260309"
provider_name
"xAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773351236-Gz2xOIGkWcgk9MJvwSGa"
upstream_id
"f500eb81-fc61-522c-8e04-ef059d0edb0d"
total_cost
0.035264
cache_discount
0.007488
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
90.91%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
19
adverbTagCount
3
adverbTags
0
"Eva's grip tightened around [around]"
1
"Aurora said finally [finally]"
2
"Aurora said quietly [quietly]"
dialogueSentences
55
tagDensity
0.345
leniency
0.691
rawRatio
0.158
effectiveRatio
0.109
82.12%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1678
totalAiIsmAdverbs
6
found
0
adverb
"softly"
count
1
1
adverb
"completely"
count
1
2
adverb
"slightly"
count
1
3
adverb
"suddenly"
count
2
4
adverb
"very"
count
1
highlights
0
"softly"
1
"completely"
2
"slightly"
3
"suddenly"
4
"very"
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)
55.30%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1678
totalAiIsms
15
found
0
word
"sense of"
count
1
1
word
"silk"
count
1
2
word
"flicked"
count
1
3
word
"tracing"
count
1
4
word
"familiar"
count
1
5
word
"silence"
count
3
6
word
"predictable"
count
1
7
word
"weight"
count
2
8
word
"stomach"
count
1
9
word
"trembled"
count
1
10
word
"flickered"
count
1
11
word
"unreadable"
count
1
highlights
0
"sense of"
1
"silk"
2
"flicked"
3
"tracing"
4
"familiar"
5
"silence"
6
"predictable"
7
"weight"
8
"stomach"
9
"trembled"
10
"flickered"
11
"unreadable"
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
109
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
109
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
144
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
40
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1678
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
16
unquotedAttributions
0
matches
(empty)
19.69%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
70
wordCount
1036
uniqueNames
12
maxNameDensity
2.61
worstName
"Aurora"
maxWindowNameDensity
3.5
worstWindowName
"Aurora"
discoveredNames
Soho
1
Aurora
27
Silas
6
Penarth
1
Eva
27
Evan
2
Raven
1
Nest
1
Spymaster
1
Prague
1
Christmas
1
Cardiff
1
persons
0
"Aurora"
1
"Silas"
2
"Eva"
3
"Evan"
4
"Raven"
5
"Nest"
6
"Spymaster"
places
0
"Soho"
1
"Prague"
2
"Cardiff"
globalScore
0.197
windowScore
0.5
47.26%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
73
glossingSentenceCount
3
matches
0
"seemed simpler then, before university, before law, before Evan turned love into a cage"
1
"as if brushing away the lie"
2
"not quite touching the scar"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1678
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
1
totalSentences
144
matches
0
"remembered that look"
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
68
mean
24.68
std
16.94
cv
0.686
sampleLengths
0
5
1
30
2
18
3
9
4
11
5
50
6
30
7
24
8
16
9
32
10
33
11
8
12
45
13
4
14
5
15
26
16
32
17
27
18
7
19
60
20
17
21
21
22
7
23
54
24
59
25
11
26
38
27
42
28
5
29
11
30
33
31
27
32
4
33
54
34
56
35
6
36
36
37
32
38
7
39
9
40
35
41
4
42
8
43
16
44
31
45
5
46
4
47
51
48
35
49
38
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
109
matches
0
"been died"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
185
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
144
ratio
0
matches
(empty)
98.86%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1041
adjectiveStacks
0
stackExamples
(empty)
adverbCount
43
adverbRatio
0.04130643611911623
lyAdverbCount
10
lyAdverbRatio
0.009606147934678195
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
144
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
144
mean
11.65
std
8.01
cv
0.687
sampleLengths
0
5
1
16
2
14
3
18
4
9
5
11
6
2
7
12
8
20
9
16
10
13
11
17
12
8
13
16
14
16
15
5
16
12
17
15
18
14
19
19
20
8
21
21
22
8
23
16
24
4
25
5
26
16
27
5
28
5
29
18
30
14
31
9
32
12
33
2
34
4
35
7
36
39
37
4
38
17
39
3
40
14
41
21
42
7
43
22
44
32
45
7
46
10
47
14
48
19
49
1
59.03%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
5
diversityRatio
0.375
totalSentences
144
uniqueOpeners
54
100.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
3
totalSentences
99
matches
0
"Of course she noticed."
1
"Instead it settled between them"
2
"Instead they opened the wound"
ratio
0.03
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
12
totalSentences
99
matches
0
"Her movements carried a new"
1
"He slid the drinks across"
2
"She gave the smallest shake"
3
"He retreated to the other"
4
"They had been nine."
5
"His grey-streaked auburn hair caught"
6
"She remembered that look too"
7
"His limp made the movement"
8
"He nodded once and moved"
9
"Her hand hovered above Aurora's"
10
"Her face went very still."
11
"She simply looked at Aurora,"
ratio
0.121
0.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
94
totalSentences
99
matches
0
"Aurora slammed her glass down."
1
"Eva stood there at the"
2
"The years had sharpened her"
3
"Aurora pushed the spare stool"
4
"Her movements carried a new"
5
"The expensive wool coat fell"
6
"Time had dressed one of"
7
"Eva glanced at the staircase"
8
"The words landed softly enough"
9
"Aurora felt her left wrist"
10
"Eva signalled to the bar."
11
"Silas appeared without hurry, his"
12
"The silver signet ring caught"
13
"Eva's voice carried the clipped"
14
"Silas studied her a moment"
15
"He slid the drinks across"
16
"She gave the smallest shake"
17
"He retreated to the other"
18
"Eva lifted her drink."
19
"Aurora took a long swallow"
ratio
0.949
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
99
matches
(empty)
ratio
0
86.47%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
38
technicalSentenceCount
3
matches
0
"He retreated to the other end of the bar, polishing a glass that didn't need polishing."
1
"Eva looked into her drink as if the answer floated there."
2
"The bar had grown quieter around them, the evening crowd thinning to the dedicated drinkers who preferred shadows."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
19
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
4
fancyCount
1
fancyTags
0
"Aurora admitted (admit)"
dialogueSentences
55
tagDensity
0.073
leniency
0.145
rawRatio
0.25
effectiveRatio
0.036
84.6546%