Run: 2026-02-17-01KHNF6WEJJZ7VCSK36M6DT02N

Run Details

Model:
DeepSeek V3 (2025-03-24)
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
25.0s
Cost:
$0.000851
Provider:
AtlasCloud

Evaluation summary

Score Evaluator
Details Link
0.00% Adverbs in dialogue tags (details)
90.65% AI-ism adverb frequency (details)
100.00% AI-ism character names (details)
100.00% AI-ism location names (details)
15.89% 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)
51.53% Name drop frequency (details)
63.79% 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)
97.80% Passive voice overuse (details)
100.00% Past progressive (was/were + -ing) overuse (details)
0.00% Em-dash & semicolon overuse (details)
94.79% Purple prose (modifier overload) (details)
100.00% Repeated phrase echo (details)
100.00% Sentence length variance (details)
82.14% Sentence opener variety (details)
100.00% Adverb-first sentence starts (details)
100.00% Pronoun-first sentence starts (details)
79.05% Subject-first sentence starts (details)
0.00% Subordinate conjunction sentence starts (details)
100.00% Technical jargon density (details)
100.00% Useless dialogue additions (details)
100.00% Dialogue tag variety (said vs. fancy) (details)
82.5216% Overall

Model input

System
You are an expert novelist with a gift for vivid, immersive prose. You write in tight third-person limited point of view with a strong narrative voice. Your prose is clean, precise, and engaging — you favor strong verbs, concrete details, and natural-sounding dialogue. You will be given a story bible (codex) containing canonical details about characters, locations, items, and lore. Use these details to ground your writing in the established world. Stay consistent with the codex. Write only the prose of the scene. Do not include titles, chapter headings, markdown formatting, or any commentary before or after the scene.
User/Human
<codex> <character id="4416" name="Detective Harlow Quinn" aliases="Quinn, Detective Quinn, Harlow" pronouns="she/her" species="Human" storyRole="Antagonist"> <eyeColor>brown</eyeColor> <hair>closely cropped salt-and-pepper</hair> <height>5'9"</height> <age>41</age> <jawline>sharp jaw</jawline> <watch>worn leather watch on her left wrist</watch> <bearing>military precision</bearing> <description>A Metropolitan Police detective with 18 years of decorated service who suspects the clique is involved in criminal activity.</description> <backstory>She lost her partner, DS Morris, during a case three years ago under unexplained circumstances that had supernatural origins she doesn't yet understand.</backstory> </character> <character id="4414" name="Eva Kowalski" aliases="Eva, Evie" pronouns="she/her" species="Human" storyRole="Best Friend"> <eyeColor>green</eyeColor> <hair>curly red</hair> <height>5'4"</height> <age>26</age> <glasses>round glasses</glasses> <satchel>worn leather satchel full of books</satchel> <freckles>freckled complexion</freckles> <nervousHabit>tucking hair behind her left ear</nervousHabit> <description>Aurora's childhood friend and an occult researcher.</description> <backstory>Moved to London two years before Aurora and works as a research assistant at the British Museum's restricted archives. She holds a master's degree in Ancient History from Oxford.</backstory> </character> <location id="856" name="The Veil Market" aliases="Veil Market, the Market, underground market" realm="Earth"> <currentLocation>abandoned Tube station beneath Camden</currentLocation> <entryRequirement>bone token</entryRequirement> <schedule>moves locations every full moon</schedule> <description>A hidden supernatural black market that sells enchanted goods, banned alchemical substances, and information.</description> </location> <item id="2004" name="Veil Compass" aliases="the Compass, shadow compass" type="Tool" origin="The Veil Market"> <casingMaterial>small brass compass</casingMaterial> <faceMarkings>face etched with protective sigils</faceMarkings> <needle>points toward the nearest supernatural rift or portal</needle> <patina>casing has a patina of verdigris</patina> <creator>crafted by a Shade artisan</creator> <description>A compass attuned to supernatural energy.</description> </item> </codex> Write a fully fleshed out scene of at least 1000 words in the mystery genre. A detective arrives at a crime scene in an unusual location. Something is wrong — the evidence doesn't add up. A colleague is present, offering a different interpretation. Through careful observation and deduction, the detective begins to see what others have missed. 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.

Model response

AI
Detective Harlow Quinn stepped through the crime scene tape, the familiar weight of her service weapon pressing against her ribcage. The abandoned Tube station beneath Camden smelled of damp concrete and something sharper—ozone, maybe, or the metallic tang of old blood. Her sharp jaw tightened as she took in the scene: shattered glass, overturned tables, and a dark stain spreading across the cracked tile floor. Three uniforms milled about, casting nervous glances at the shadows that pooled unnaturally in the corners. The station wasn’t supposed to exist. The maps didn’t list it. Yet here it was, cloaked in the kind of quiet that pressed against the ears like a threat. "Another one, then." A voice at her shoulder—Eva Kowalski, clutching her worn leather satchel like a shield, round glasses catching the uneven glow of the forensic lights. The freckles across her nose stood out stark against her pale skin. "Same as the last two." Harlow didn’t answer right away. She crouched, gloved fingers hovering just above the stain. Not blood. Too dark, too viscous. Ink? No. She’d seen enough crime scenes to recognize when something was off. This wasn’t blood, but it wasn’t anything else she could name, either. "You shouldn’t be here, Kowalski." Eva tucked a curl behind her ear—her nervous habit, one Harlow had clocked within minutes of meeting her. "You called me in." "Not to a potential homicide." "Homicide?" Eva scoffed, crouching beside her, satchel bumping against her knee. "Look around, Detective. No body. No bullets. And this—" she gestured to the stain—"isn’t human. It’s residue. Something came through. Violently." Harlow’s gaze flicked to the shadows again. Something moved—just a trick of the light, maybe. Or maybe not. She straightened, adjusting the worn leather watch on her wrist. "Explain." "You won’t believe me." "Try me." Eva pulled a small brass compass from her satchel, its face etched with sigils Harlow didn’t recognize. The needle spun wildly before jerking to a stop, pointing toward the farthest wall. Toward the stain. "This used to be one of the entrances to the Veil Market," Eva said quietly. "A black market. For things that shouldn’t exist." Harlow clenched her jaw. Fairy tales. But then—there was the stain. The missing body. The way the shadows curled like smoke where there was no wind. And three years ago, Morris had vanished from a scene just like this one. No blood. No bullet casings. Just a half-empty cup of coffee and a void no forensics team could explain. "You think something came through," Harlow said slowly, testing the words. Eva exhaled, glancing around as if expecting the walls to listen. "I think something was taken." A chill skittered down Harlow’s spine. The uniforms by the tape shifted, their radios crackling with static. A headache pressed behind her eyes, sudden and sharp. "Show me," she said finally, nodding to the compass. Eva hesitated, then turned, leading the way toward the darkest part of the station. The air thickened. The compass needle trembled. And for the first time in eighteen years on the force, Harlow Quinn had the uneasy feeling she was about to step into a world she couldn’t bulletproof her way out of.
created_at"2026-02-17T09:34:50.45244+00:00" 2/17/2026, 9:34:50 AM
model"deepseek/deepseek-chat-v3-0324"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2059
moderation_latency(null)
generation_time24974
tokens_prompt923
tokens_completion860
native_tokens_prompt857
native_tokens_completion757
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.000851272
router(null)
provider_responses
0
id"7877c84617f0466d954ae0a84f87dfcb"
status200
is_byokfalse
latency2059
endpoint_id"5bb598f5-fd97-4f8b-91e4-ceab3743a03b"
provider_name"AtlasCloud"
model_permaslug"deepseek/deepseek-chat-v3-0324"
api_type"completions"
id"gen-1771320865-XidVryWexl8xob7pZXW8"
upstream_id"7877c84617f0466d954ae0a84f87dfcb"
total_cost0.000851272
cache_discount(null)
upstream_inference_cost0
provider_name"AtlasCloud"

Evaluation details

Result Evaluator Details Meta Data
0.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags6
adverbTagCount3
adverbTags
0"Eva said quietly [quietly]"
1"Harlow said slowly [slowly]"
2"she said finally [finally]"
dialogueSentences15
tagDensity0.4
leniency0.8
rawRatio0.5
effectiveRatio0.4
90.65% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount535
totalAiIsmAdverbs1
found
0
adverb"slowly"
count1
highlights
0"slowly"
100.00% AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions(empty)
found(empty)
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
15.89% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount535
totalAiIsms9
found
0
word"familiar"
count1
1
word"weight"
count1
2
word"shattered"
count1
3
word"stark"
count1
4
word"potential"
count1
5
word"flicked"
count1
6
word"etched"
count1
7
word"chill"
count1
8
word"trembled"
count1
highlights
0"familiar"
1"weight"
2"shattered"
3"stark"
4"potential"
5"flicked"
6"etched"
7"chill"
8"trembled"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"clenched jaw/fists"
count1
highlights
0"clenched her jaw"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences47
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences47
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences56
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen32
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords529
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions6
unquotedAttributions0
matches(empty)
51.53% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions22
wordCount457
uniqueNames7
maxNameDensity1.97
worstName"Harlow"
maxWindowNameDensity3
worstWindowName"Harlow"
discoveredNames
Harlow9
Quinn2
Tube1
Camden1
Eva7
Kowalski1
Morris1
persons
0"Harlow"
1"Quinn"
2"Camden"
3"Eva"
4"Kowalski"
5"Morris"
places(empty)
globalScore0.515
windowScore0.667
63.79% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences29
glossingSentenceCount1
matches
0"as if expecting the walls to listen"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount529
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences56
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs20
mean26.45
std17.89
cv0.676
sampleLengths
065
145
244
345
45
522
65
732
829
94
102
1134
1223
1359
1411
1516
1626
179
1821
1932
97.80% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences47
matches
0"was, cloaked"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs77
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount6
semicolonCount0
flaggedSentences6
totalSentences56
ratio0.107
matches
0"The abandoned Tube station beneath Camden smelled of damp concrete and something sharper—ozone, maybe, or the metallic tang of old blood."
1"\"Another one, then.\" A voice at her shoulder—Eva Kowalski, clutching her worn leather satchel like a shield, round glasses catching the uneven glow of the forensic lights."
2"Eva tucked a curl behind her ear—her nervous habit, one Harlow had clocked within minutes of meeting her."
3"\"Look around, Detective. No body. No bullets. And this—\" she gestured to the stain—\"isn’t human. It’s residue. Something came through. Violently.\""
4"Something moved—just a trick of the light, maybe."
5"But then—there was the stain."
94.79% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount457
adjectiveStacks0
stackExamples(empty)
adverbCount21
adverbRatio0.045951859956236324
lyAdverbCount5
lyAdverbRatio0.010940919037199124
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences56
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences56
mean9.45
std7.03
cv0.744
sampleLengths
020
121
224
316
46
55
618
727
812
95
105
119
122
134
141
151
1611
1712
185
1918
204
215
2211
2321
247
258
263
2710
281
294
302
3117
3214
333
3415
358
364
372
385
393
4012
4114
422
433
4414
4511
4611
475
486
4911
82.14% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats4
diversityRatio0.5357142857142857
totalSentences56
uniqueOpeners30
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences42
matches
0"Too dark, too viscous."
1"Just a half-empty cup of"
ratio0.048
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount6
totalSentences42
matches
0"Her sharp jaw tightened as"
1"She crouched, gloved fingers hovering"
2"She’d seen enough crime scenes"
3"she gestured to the stain—\"isn’t"
4"She straightened, adjusting the worn"
5"she said finally, nodding to"
ratio0.143
79.05% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount32
totalSentences42
matches
0"Detective Harlow Quinn stepped through"
1"The abandoned Tube station beneath"
2"Her sharp jaw tightened as"
3"The station wasn’t supposed to"
4"The maps didn’t list it."
5"A voice at her shoulder—Eva"
6"The freckles across her nose"
7"Harlow didn’t answer right away."
8"She crouched, gloved fingers hovering"
9"She’d seen enough crime scenes"
10"This wasn’t blood, but it"
11"Eva tucked a curl behind"
12"Eva scoffed, crouching beside her,"
13"she gestured to the stain—\"isn’t"
14"Harlow’s gaze flicked to the"
15"Something moved—just a trick of"
16"She straightened, adjusting the worn"
17"Eva pulled a small brass"
18"The needle spun wildly before"
19"Eva said quietly"
ratio0.762
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences42
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences19
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags3
fancyCount0
fancyTags(empty)
dialogueSentences15
tagDensity0.2
leniency0.4
rawRatio0
effectiveRatio0
82.5216%