NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHTRKDVRAEPDR3WXQ1V1C09H
Run Details
Model:
Claude 3.5 Sonnet
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
34.7s
Cost:
$0.062592
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
93.32%
AI-ism adverb frequency
(details)
60.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
59.89%
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)
95.77%
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)
98.38%
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)
91.58%
Sentence opener variety
(details)
0.00%
Adverb-first sentence starts
(details)
15.56%
Pronoun-first sentence starts
(details)
0.00%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
47.62%
Technical jargon density
(details)
69.44%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
81.0520%
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 glass slipped from Aurora's
grip, but Silas' hand shot out, catching it before it
shattered
. Old habits.
Her eyes fixed on the
man who'd just walked into the Raven's Nest, broad-shouldered and
familiar
in all the wrong ways. "You alright there, Rory?"
Silas set the glass back
on the counter, his hazel eyes following her gaze. "Fine."
She grabbed a rag and
wiped invisible spots off the bar top. "Just thought I saw someone."
The man settled at the
far end, ordering something she couldn't hear.
The neon green sign outside
cast shadows across his face, but she knew those shoulders, that way of leaning against the bar like he owned it. "Another gin and tonic?" Silas asked. "Stronger." He poured her whiskey neat, no commentary needed.
The amber liquid caught the
light as she lifted it, and that's when the man turned. Their eyes met. Recognition
flickered
across his face, followed by something else. Something harder. "Carter?"
His voice carried across the
nearly empty bar. "Aurora Carter?" She knocked back the whiskey. "
Marcus
."
He gathered his drink and
moved closer, claiming the stool next to hers.
The expensive suit couldn't hide
the softness that had crept into his jaw, the grey threading through his temples. "Didn't expect to find you in a place like this." "I live here."
She gestured vaguely upward
. "Above." "You always said you'd end up in New York." "Things change."
Silas drifted to the other
end of the bar, close enough to watch but far enough to grant privacy.
His limp was barely noticeable
tonight. "They do."
Marcus
ran a finger around the rim of his glass. "Heard you left law school." "Heard you made partner." "Junior partner."
He smiled, but it didn't
reach his eyes. "The hours are killing me.
Sarah
hates it." "
Sarah
?" "My wife."
He twisted a gold band
she hadn't noticed. "Two years now. She's pregnant." Aurora's fingers found the crescent scar on her wrist,
tracing
its
familiar
curve. "Congratulations." "What about you? Anyone special?" "Not anymore." The
silence
stretched between them like old gum, sticky with things unsaid.
She could still taste the
whiskey on her tongue, sharp and honest. "Remember that summer in Cardiff?" he asked. "The one before university?" "
Marcus
-" "We were going to change the world. You were going to argue before the Supreme Court. I was going to defend the little guy." "Now you defend corporations." "Someone has to pay the mortgage."
He took a long drink
. "We were naive." "We were right." His laugh held no humor. "Look at you, Carter. Bartending in Soho? This is what you call being right?" "I deliver food too."
She smiled, all teeth
. "Very diverse skill set." "You were brilliant. Top of our class. You could've-" "Could've what? Sold my soul like you?" "That's not fair." "Life rarely is."
She pushed away from the
bar. "Ask your corporate clients."
He grabbed her wrist, fingers
brushing the scar.
She yanked back like his
touch burned. "I looked for you," he said. "After you left school. No one knew where you'd gone." "That was the point." "Was it because of what happened with Evan?" The name hit like a slap. Aurora's hands clenched, knuckles white against the dark wood. "You don't get to say his name." "I should've believed you. When you told me-" "But you didn't." The words tasted like ash. "Your best friend since primary, running to you for help, and you sided with him." "I was wrong." "Yes."
She met his gaze
. "You were."
Marcus
reached into his jacket, pulled out a business card. The firm's name
was embossed
in gold. "If you ever need anything-" "I don't."
He set the card on
the bar anyway. "The offer stands." "Goodbye,
Marcus
." He stood, straightening his tie. The suit probably cost more than her monthly rent. "Take care of yourself, Carter." "Always do." She watched him leave, the door closing behind him with a soft click. The card sat on the bar like an accusation. Silas appeared, wordlessly replacing her empty glass with a full one. "Friend of yours?" "Once." Aurora picked up the card, ran her thumb across the raised letters. "A lifetime ago." She tore it in half, then quarters, then eighths, letting the pieces fall like confetti. Silas swept them into his palm without comment. "Some things," she said, "are better left in Cardiff." The whiskey burned going down, but not as much as the memory of who she used to be.
created_at
"2026-02-19T10:54:45.631Z"
2/19/2026, 10:54:45 AM
model
"anthropic/claude-3.5-sonnet"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1235
moderation_latency
195
generation_time
34433
tokens_prompt
4618
tokens_completion
1181
native_tokens_prompt
4717
native_tokens_completion
1143
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
0.062592
router
(null)
provider_responses
0
endpoint_id
"d4fb79bd-9786-4932-af81-b83040e9f4e4"
id
"861c6ce1-82db-4455-9d3f-2d5b4abaa10d"
is_byok
false
latency
1235
model_permaslug
"anthropic/claude-3.5-sonnet"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771498485-3Jsp89pFNNmUjBeLrKdc"
upstream_id
"861c6ce1-82db-4455-9d3f-2d5b4abaa10d"
total_cost
0.062592
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
18
adverbTagCount
3
adverbTags
0
"She gestured vaguely [vaguely]"
1
"She pushed away [away]"
2
"The words tasted like [like]"
dialogueSentences
61
tagDensity
0.295
leniency
0.59
rawRatio
0.167
effectiveRatio
0.098
93.32%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
748
totalAiIsmAdverbs
1
found
0
adverb
"very"
count
1
highlights
0
"very"
60.00%
AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0
"Blackwood"
found
0
"Marcus"
1
"Sarah"
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
59.89%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
748
totalAiIsms
6
found
0
word
"shattered"
count
1
1
word
"familiar"
count
2
2
word
"flickered"
count
1
3
word
"tracing"
count
1
4
word
"silence"
count
1
highlights
0
"shattered"
1
"familiar"
2
"flickered"
3
"tracing"
4
"silence"
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
51
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
51
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
95
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
26
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
747
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
10
unquotedAttributions
0
matches
(empty)
95.77%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
14
wordCount
461
uniqueNames
6
maxNameDensity
1.08
worstName
"Silas"
maxWindowNameDensity
1.5
worstWindowName
"Aurora"
discoveredNames
Aurora
4
Old
1
Raven
1
Nest
1
Silas
5
Marcus
2
persons
0
"Aurora"
1
"Silas"
2
"Marcus"
places
0
"Raven"
globalScore
0.958
windowScore
1
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
36
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
747
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
95
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
56
mean
13.34
std
10.5
cv
0.787
sampleLengths
0
39
1
18
2
18
3
38
4
6
5
1
6
38
7
11
8
6
9
42
10
8
11
9
12
2
13
25
14
17
15
4
16
18
17
1
18
15
19
14
20
5
21
2
22
24
23
11
24
1
25
24
26
4
27
14
28
3
29
19
30
12
31
9
32
7
33
3
34
13
35
15
36
16
37
4
38
8
39
22
40
8
41
23
42
3
43
7
44
22
45
2
46
11
47
2
48
19
49
2
98.38%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
51
matches
0
"was embossed"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
82
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
0
flaggedSentences
0
totalSentences
95
ratio
0
matches
(empty)
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
171
adjectiveStacks
0
stackExamples
(empty)
adverbCount
3
adverbRatio
0.017543859649122806
lyAdverbCount
1
lyAdverbRatio
0.005847953216374269
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
95
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
95
mean
7.86
std
5.34
cv
0.68
sampleLengths
0
16
1
2
2
21
3
18
4
13
5
5
6
12
7
26
8
6
9
1
10
8
11
16
12
3
13
9
14
2
15
9
16
2
17
5
18
1
19
13
20
19
21
10
22
7
23
1
24
9
25
2
26
19
27
6
28
12
29
5
30
4
31
10
32
8
33
1
34
10
35
5
36
13
37
1
38
5
39
2
40
12
41
12
42
7
43
4
44
1
45
24
46
4
47
11
48
3
49
3
91.58%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
3
diversityRatio
0.5684210526315789
totalSentences
95
uniqueOpeners
54
0.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
0
totalSentences
45
matches
(empty)
ratio
0
15.56%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
23
totalSentences
45
matches
0
"Her eyes fixed on the"
1
"She grabbed a rag and"
2
"He poured her whiskey neat,"
3
"Their eyes met."
4
"His voice carried across the"
5
"She knocked back the whiskey."
6
"He gathered his drink and"
7
"She gestured vaguely upward"
8
"His limp was barely noticeable"
9
"He smiled, but it didn't"
10
"He twisted a gold band"
11
"She could still taste the"
12
"He took a long drink"
13
"His laugh held no humor."
14
"She smiled, all teeth"
15
"She pushed away from the"
16
"He grabbed her wrist, fingers"
17
"She yanked back like his"
18
"She met his gaze"
19
"He set the card on"
ratio
0.511
0.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
45
totalSentences
45
matches
0
"The glass slipped from Aurora's"
1
"Her eyes fixed on the"
2
"Silas set the glass back"
3
"She grabbed a rag and"
4
"The man settled at the"
5
"The neon green sign outside"
6
"He poured her whiskey neat,"
7
"The amber liquid caught the"
8
"Their eyes met."
9
"Recognition flickered across his face,"
10
"His voice carried across the"
11
"She knocked back the whiskey."
12
"He gathered his drink and"
13
"The expensive suit couldn't hide"
14
"She gestured vaguely upward"
15
"Silas drifted to the other"
16
"His limp was barely noticeable"
17
"Marcus ran a finger around"
18
"He smiled, but it didn't"
19
"He twisted a gold band"
ratio
1
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
45
matches
(empty)
ratio
0
47.62%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
15
technicalSentenceCount
2
matches
0
"Her eyes fixed on the man who'd just walked into the Raven's Nest, broad-shouldered and familiar in all the wrong ways."
1
"The expensive suit couldn't hide the softness that had crept into his jaw, the grey threading through his temples."
69.44%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
18
uselessAdditionCount
2
matches
0
"The glass slipped, but Silas' hand shot out, catching it before it shattered"
1
"Silas set, his hazel eyes following her gaze"
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
4
fancyCount
0
fancyTags
(empty)
dialogueSentences
61
tagDensity
0.066
leniency
0.131
rawRatio
0
effectiveRatio
0
81.0520%