NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHTR3S7PM2CGT9NDCTEZ0MZE
Run Details
Model:
GPT-4.1
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
1m 3s
Cost:
$0.023984
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
92.85%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
39.24%
AI-ism word frequency
(details)
66.67%
Cliché density
(details)
100.00%
Emotion telling (show vs. tell)
(details)
100.00%
Filter word density
(details)
100.00%
Gibberish response detection
(details)
100.00%
Markdown formatting overuse
(details)
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)
68.82%
Sentence opener variety
(details)
70.18%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
60.00%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
72.37%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
85.6707%
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
"Eva?"
The name leapt across the
tables before Aurora could stop herself.
The question hovered in the
air, brittle as a snapped twig.
The woman paused mid-pour, the
wine bottle cradled in her elegant brown hand, green glass tight against the rim of a chipped glass. Across the crowd, she hesitated, lips parted in surprise.
Her hair swung sharp and
angular, lighter than Aurora remembered, with honey ribbons curling over an ear weighted by three silver hoops. Aurora slipped off her barstool. Sticky floor, half-wiped, caught at the soles of her boots. Sidestepping a slouching city boy and his yawning date, she threaded through the maze of elbows and stuttered laughter. Every step brought her closer, but the gap refused to close. Four years had done strange things to Eva Ellis.
The freckles dusting her nose
hadn't changed, nor had the stubborn chin, but her smile
was gone
. "You going to stand there gawping or join me?" Eva’s voice, low and sardonic, chipped at Aurora’s composure. Aurora nodded. Sat down across from her.
Heart lodged tight in her
throat.
Eva filled the second glass
with a jerk, splashes of red dotting the ring-stained table. One skirted Aurora's hand, beading into her crescent scar. "A lifetime," Eva said. "Or just the slowest walk from Cardiff to Soho?" Aurora forced a smile, older, rusted at the edges. "Buses weren’t running."
The corner booth pressed warm
and close, all cracked green vinyl and gossip-muffled music. Overhead, a moth flailed in the lamp’s yellow glow. Beyond the booth’s edge, life
churned
on: a barman muttered his way through inventory, the slot machine moaned its electronic agony. Eva sipped. Watched Aurora with careful, deliberate eyes. "Didn’t think I’d see you here. Not since—well. Since we left everything in the smoking area behind Burger King." The air thickened. Aurora weighed every word. "Thought I’d find you in Paris. Painting murals on rich people’s walls. Or plotting a revolution." "Paint dries. Engines give out. Turns out ambition only gets you so far."
Eva tapped her glass
.
Her nails, chipped black, drummed
restless patterns. "You, though—how’s London? Stole your heart or just your rent money?" "Somewhere between."
Aurora fought the urge to
reach for old habits: a witty retort, some scrap of inside joke.
Instead, her fingers closed around
the cool stem of her wine glass. She
traced
the rim. "I work deliveries. Chinese. Cash in hand. Above Silas’s bar." "The infamous Raven’s Nest. Place smells of varnish and apologies."
Eva’s mouth curled almost into
a smile. "You always could sniff out a den, Carter. I bet they still call you Rory." "No one here knows Laila."
Aurora let the old nickname
slip like a stone in a well. Eva’s eyes darted, hungry. "Left that with the accent, yeah?" The
silence
that followed scuffed at the kernel of things neither of them wished to name. Aurora stared at Eva, at the hardness in her jaw, the soft pink groove beneath her eyes. "I heard about Evan," Eva said. The name carried a
weight
, a history printed in bruises and phone calls never returned. Aurora offered nothing. Eva leaned forward, elbows on the sticky wood. She towered over her memories, now all sharp edges and alcohol. "Did they ever find him?" Aurora met her gaze, refused to blink. "Not worth finding. I left. That’s the important part." "You got brave." A statement, simple as a verdict. "I ran. There’s a difference." Eva’s hands stilled. Between them, a pack of cigarettes. Eva nudged it over. Aurora,
reluctantly
, pulled one free and rolled it between her fingers. "Never thought you’d take up smoking," Aurora said. "Sometimes it’s the only thing that still burns," Eva replied. Her voice sounded different now, less callous, more brittle. "You’re thin," Aurora said before she could swallow the thought. "Hollow-eyed. You eating?" Eva snorted. "Mum would approve. She fed us like piglets. Still, I feed myself fine. The city runs on sugar, salt, and caffeine." "You still painting?" Eva shook her head. "I learn to wire houses now. Quiet work. No one asks for meaning. Just a steady hand on the right cable." "That sounds—" "Practical. Boring. Un-Rory-like, I know." "You always had plans." Eva leaned further in. "And you never believed in them." The accusation
flickered
under her words. Aurora stiffened. "That’s not—" Eva cut across. "You took his name. Wore it until it fit. Laila, Laila. I went looking, but you were already gone and he—I tried to call. Messages never came back." Aurora saw the cracked old friendship hover in the space between: two girls in a corner booth, voice-memos about exams, rescue plans scribbled on napkins. "Sorry," she said. "Back then, I let everything drop. Even you." Eva’s face didn’t soften. "Yeah. You did." From the bar, someone dropped a tray. Glass smashed. The jukebox switched to a tinny Motown classic, drowning out the sting. Eva reached for her lighter. The
etched
silver reflected Aurora’s face, ghostly, lopsided. "Best thing I did was leave Cardiff," Eva said. "Worst thing was forgetting why I left." Aurora matched her. "Worst thing I did was stay as long as I did." The
weight
of time deepened the lines around Eva’s eyes.
She flickered between the past
and present, as though haunted still by both. "You still dream in Welsh,"
Eva asked, low
. Aurora’s
jaw clenched
. "Nightmares, mostly. Voices from home. Mum’s sharp tongue. Da’s lectures about honour." "Odd, isn’t it? How what we fear follows us, no matter which street we walk." Eva blew a stream of smoke upwards. "Do you go back?" Eva laughed. Bitter, cracked. "Home’s a place for postcards. Not for returns." Aurora nodded. "I sometimes think about calling your mum. Just to hear her say my name again, before she asks if I’ve eaten." Eva smiled, first genuine, then folded
quickly
away. "She asks after you. Still has your birthday card taped to the fridge. Claims you wrote the best lines." "She was the only person who actually listened." Aurora caught herself, stopped. "Sorry. That sounded—" "True." Eva stared at her glass, swirling the wine. "I keep telling myself I haven't changed as much as I have." Aurora eyed the wine, the cigarettes, the scars vanished under rolled up sleeves. "We always wanted to change. That’s what we promised." "Yeah, well. Some promises run aground." Outside the booth, a group of regulars raised a toast to nothing in particular. Laughter ricocheted; it jarred against the hush between Aurora and Eva. Eva tensed, her gaze flicking to the door. "I should go." Aurora grabbed for her wrist. "Don’t. Not yet."
Her thumbnail brushed the old
silver
charm
on Eva’s bracelet. "Let’s not let it end with regrets." Eva hesitated. "Too late for that." Behind them, the distinctive green neon of The Raven’s Nest sign
flickered
, brighter for a half-beat. A shadow
loomed
in the doorway. Tall, broad-shouldered, with the unmistakable limp of an old wound. Silas Blackwood, eagle-eyed from the
gloom
, spotted Aurora. His gaze lingered on Eva. A long, appraising
look
. "Problem here, Rory?" Aurora didn’t flinch. "No problem. Old friend. Catching up." Silas studied the gap, the
charged
air, the half-finished drinks, the hunched posture of Eva at the table’s edge.
His fingers tapped his silver
signet ring, once, twice. Eva
let out a breath
. "I know when I’m not wanted." Aurora straightened. "Stay. Please." A door at the rear banged shut. Footfalls hammered up the cellar steps. Somewhere, a glass
shattered
. Silas’s voice cut across. "Aurora. The back room. Now."
His thumb pointed to the
hidden door behind the bookshelf, his tone brooked no argument. Eva slid from the booth, shoving the wine aside. "Same old, Carter. Magnet for trouble."
She paused, reached into her
pocket, and pressed a slip of paper into Aurora’s palm. Handwriting curled,
familiar
, sharp as glass. "Don’t lose this one," she whispered. Aurora stuffed it deep in her jacket.
She watched Eva disappear against
the flow of drinkers and noise, her shadow long amongst the neon.
She turned for the back
room, Silas’s limp already carrying him ahead. Behind her, the bar's laughter snapped into shouts. Someone screamed. The lights
flickered
, then died. The world shrank to a single door creaking open, a final
look
back at the empty space where Eva had been. And through the darkness, Aurora ran.
created_at
"2026-02-19T10:46:12.989Z"
2/19/2026, 10:46:12 AM
model
"openai/gpt-4.1-2025-04-14"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
486
moderation_latency
(null)
generation_time
63320
tokens_prompt
4618
tokens_completion
2241
native_tokens_prompt
4132
native_tokens_completion
1965
native_tokens_completion_images
0
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
"completed"
usage
0.023984
router
(null)
provider_responses
0
endpoint_id
"c235abe8-11cc-42d3-95ad-72f4d198287a"
id
"resp_01cad4d7d768f9b5016996e9f50fbc81978b21f964381b3400"
is_byok
false
latency
118
model_permaslug
"openai/gpt-4.1-2025-04-14"
provider_name
"OpenAI"
status
200
api_type
"completions"
id
"gen-1771497972-xfzpgQFdJJ2bx8O77cnP"
upstream_id
"resp_01cad4d7d768f9b5016996e9f50fbc81978b21f964381b3400"
total_cost
0.023984
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
19
adverbTagCount
1
adverbTags
0
"Eva’s mouth curled almost [almost]"
dialogueSentences
63
tagDensity
0.302
leniency
0.603
rawRatio
0.053
effectiveRatio
0.032
92.85%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1399
totalAiIsmAdverbs
2
found
0
adverb
"reluctantly"
count
1
1
adverb
"quickly"
count
1
highlights
0
"reluctantly"
1
"quickly"
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)
39.24%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1399
totalAiIsms
17
found
0
word
"churned"
count
1
1
word
"traced"
count
1
2
word
"silence"
count
1
3
word
"weight"
count
2
4
word
"flickered"
count
4
5
word
"etched"
count
1
6
word
"jaw clenched"
count
1
7
word
"charm"
count
1
8
word
"loomed"
count
1
9
word
"gloom"
count
1
10
word
"charged"
count
1
11
word
"shattered"
count
1
12
word
"familiar"
count
1
highlights
0
"churned"
1
"traced"
2
"silence"
3
"weight"
4
"flickered"
5
"etched"
6
"jaw clenched"
7
"charm"
8
"loomed"
9
"gloom"
10
"charged"
11
"shattered"
12
"familiar"
66.67%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
2
maxInWindow
2
found
0
label
"let out a breath"
count
1
1
label
"jaw/fists clenched"
count
1
highlights
0
"let out a breath"
1
"jaw clenched"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
1
narrationSentences
113
matches
0
"d in surprise"
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
0
narrationSentences
113
filterMatches
0
"look"
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
155
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
29
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1386
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
17
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
80
wordCount
909
uniqueNames
9
maxNameDensity
4.07
worstName
"Eva"
maxWindowNameDensity
8
worstWindowName
"Eva"
discoveredNames
Aurora
33
Eva
37
Ellis
1
Motown
1
Raven
1
Nest
1
Blackwood
1
Handwriting
1
Silas
4
persons
0
"Aurora"
1
"Eva"
2
"Ellis"
3
"Raven"
4
"Blackwood"
5
"Handwriting"
6
"Silas"
places
(empty)
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
1386
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
155
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
75
mean
18.48
std
12.91
cv
0.698
sampleLengths
0
1
1
22
2
54
3
71
4
18
5
13
6
24
7
13
8
12
9
44
10
27
11
23
12
35
13
45
14
32
15
17
16
10
17
33
18
21
19
3
20
24
21
16
22
9
23
5
24
3
25
21
26
8
27
19
28
13
29
23
30
3
31
25
32
2
33
5
34
4
35
16
36
4
37
31
38
25
39
11
40
7
41
21
42
29
43
14
44
23
45
8
46
15
47
22
48
4
49
12
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
113
matches
0
"was gone"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
168
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
1
flaggedSentences
1
totalSentences
155
ratio
0.006
matches
0
"Laughter ricocheted; it jarred against the hush between Aurora and Eva."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
918
adjectiveStacks
0
stackExamples
(empty)
adverbCount
19
adverbRatio
0.020697167755991286
lyAdverbCount
3
lyAdverbRatio
0.0032679738562091504
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
155
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
155
mean
8.94
std
5.92
cv
0.663
sampleLengths
0
1
1
11
2
11
3
23
4
9
5
22
6
5
7
10
8
19
9
11
10
9
11
17
12
18
13
2
14
5
15
6
16
15
17
9
18
4
19
9
20
9
21
3
22
14
23
9
24
21
25
2
26
6
27
19
28
3
29
4
30
16
31
17
32
7
33
11
34
19
35
12
36
4
37
10
38
17
39
15
40
17
41
4
42
6
43
16
44
17
45
6
46
15
47
3
48
8
49
11
68.82%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
5
diversityRatio
0.432258064516129
totalSentences
155
uniqueOpeners
67
70.18%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
2
totalSentences
95
matches
0
"Instead, her fingers closed around"
1
"Somewhere, a glass shattered."
ratio
0.021
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
13
totalSentences
95
matches
0
"Her hair swung sharp and"
1
"Her nails, chipped black, drummed"
2
"She traced the rim."
3
"She towered over her memories,"
4
"Her voice sounded different now,"
5
"She flickered between the past"
6
"Her thumbnail brushed the old"
7
"His gaze lingered on Eva."
8
"His fingers tapped his silver"
9
"His thumb pointed to the"
10
"She paused, reached into her"
11
"She watched Eva disappear against"
12
"She turned for the back"
ratio
0.137
60.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
76
totalSentences
95
matches
0
"The name leapt across the"
1
"The question hovered in the"
2
"The woman paused mid-pour, the"
3
"Her hair swung sharp and"
4
"Aurora slipped off her barstool."
5
"Every step brought her closer,"
6
"The freckles dusting her nose"
7
"Eva’s voice, low and sardonic,"
8
"Heart lodged tight in her"
9
"Eva filled the second glass"
10
"Aurora forced a smile, older,"
11
"The corner booth pressed warm"
12
"The air thickened."
13
"Aurora weighed every word."
14
"Eva tapped her glass"
15
"Her nails, chipped black, drummed"
16
"Aurora fought the urge to"
17
"She traced the rim."
18
"Eva’s mouth curled almost into"
19
"Aurora let the old nickname"
ratio
0.8
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
95
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
31
technicalSentenceCount
0
matches
(empty)
72.37%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
19
uselessAdditionCount
2
matches
0
"Aurora fought, some scrap of inside joke"
1
"Eva asked, low"
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
9
fancyCount
1
fancyTags
0
"she whispered (whisper)"
dialogueSentences
63
tagDensity
0.143
leniency
0.286
rawRatio
0.111
effectiveRatio
0.032
85.6707%