Run: 2026-02-17-01KHNFMFCMTGFB1WJJR9KRNAFP

Run Details

Model:
DeepSeek V3 (2025-03-24)
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
27.0s
Cost:
$0.000761
Provider:
ModelRun

Evaluation summary

Score Evaluator
Details Link
100.00% Adverbs in dialogue tags (details)
90.97% AI-ism adverb frequency (details)
100.00% AI-ism character names (details)
100.00% AI-ism location names (details)
36.82% AI-ism word frequency (details)
100.00% Cliché density (details)
100.00% Emotion telling (show vs. tell) (details)
82.07% Filter word density (details)
100.00% Gibberish response detection (details)
100.00% Markdown formatting overuse (details)
100.00% Missing dialogue indicators (quotation marks) (details)
20.97% Name drop frequency (details)
100.00% Narrator intent-glossing (details)
15.16% "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)
0.00% Em-dash & semicolon overuse (details)
100.00% Purple prose (modifier overload) (details)
100.00% Repeated phrase echo (details)
100.00% Sentence length variance (details)
75.44% Sentence opener variety (details)
72.46% Adverb-first sentence starts (details)
100.00% Pronoun-first sentence starts (details)
14.35% 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)
80.2747% 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
The abandoned Tube station smelled of damp concrete and something older—the metallic tang of forgotten places. Detective Harlow Quinn descended the crumbling steps with military precision, her salt-and-pepper hair catching flickers of torchlight from above. The torn police tape at the entrance fluttered in an unfelt draft. Eva Kowalski stood near the platform's edge, shifting her weight between scuffed Oxfords. Her freckled hands fidgeted with the strap of her leather satchel. "They shouldn't have called you here," Eva said, tucking a curl behind her left ear for the third time since Quinn had arrived. "This isn't police jurisdiction." Quinn's sharp jaw tightened as she surveyed the scene—scorch marks radiating outward from the rail tracks in unnatural patterns, the air humming faintly like a struck tuning fork. She thumbed the worn leather band of her watch, timing the irregular vibrations. "Someone died here, Miss Kowalski." Quinn crouched, running gloved fingers over the blackened tiles. "That always makes it my business." Eva adjusted her round glasses. "Accidents happen down here. Especially near the Market." Quinn's brown eyes flicked upward. The Veil Market. She'd heard whispers—a place that only appeared to those who knew how to ask. The sort of story her late partner Morris would've chased with that boyish grin of his. The thought soured her stomach. She stood, brushing grit from her trousers. "Show me what you saw." Eva hesitated before leading her toward a service alcove where a figure lay sprawled beneath a tarp. Quinn lifted the covering with two fingers. The victim—male, late twenties—had burn patterns spiderwebbing from his sternum outward. No smell of charred flesh. The burns looked drawn onto his skin with white chalk. "No blistering." Quinn rotated his wrist. "Third-degree contact burns should've cooked the subcutaneous fat. This isn't thermal damage." Eva hugged her satchel tighter. "Told you. Not a police matter." Quinn examined Atlanta Police training kicked in—the way shadows pooled unnaturally beneath the corpse, the faint blue residue under his fingernails. And there, half-hidden beneath his sleeve, a small brass compass with verdigris patina. She slipped it into her evidence bag before Eva could react. "You knew him." Eva's breath hitched. "Research assistant. From the Museum." Sigils on the compass face caught the dim light. Quinn had seen similar etchings years ago—on a case file Morris had hidden in his flat after hours. A file that vanished with him. Her pulse hammered. "What did he stumble into?" Eva chewed her lip. "He was trying to track... disturbances. With that." She gestured toward the compass. Quinn flipped it open. The needle spun wildly before jerking northwest—toward the sealed tunnel where torchlight failed to penetrate. A drop of something viscous hit her shoe. Not water. She shone her flashlight upward. The ceiling pulsed with veins of bioluminescent fungus, pulsing brighter where they converged above the tracks. The scorch marks aligned perfectly beneath them—not random damage, but deliberate patterns. A shape Quinn recognized from Morris's stolen notes: intersecting arcs forming a sigil she couldn't pronounce. Eva grabbed her wrist. "Don't." But Quinn was already stepping onto the tracks, compass vibrating in her palm. Three years of unanswered questions coiled in her gut. The needle snapped straight. A sound like shattering glass filled the tunnel. Then the screaming began.
created_at"2026-02-17T09:42:17.939775+00:00" 2/17/2026, 9:42:17 AM
model"deepseek/deepseek-chat-v3-0324"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency863
moderation_latency(null)
generation_time21078
tokens_prompt923
tokens_completion931
native_tokens_prompt856
native_tokens_completion766
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached323
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"
usage0.00076102
router(null)
provider_responses
0
status(null)
is_byokfalse
latency5923
endpoint_id"3a816eb8-7a0b-4a9a-b497-e3a1efb349fc"
provider_name"Novita"
model_permaslug"deepseek/deepseek-chat-v3-0324"
1
id"chatcmpl-241b7ec4b75a483e92dc4a5bfec7010a"
status200
is_byokfalse
latency62
endpoint_id"a3938710-1b99-4a1f-85f4-2494f3f659d3"
provider_name"ModelRun"
model_permaslug"deepseek/deepseek-chat-v3-0324"
api_type"completions"
id"gen-1771321310-0UOuC1y5a0nC1BvOr4t5"
upstream_id"chatcmpl-241b7ec4b75a483e92dc4a5bfec7010a"
total_cost0.00076102
cache_discount(null)
upstream_inference_cost0
provider_name"ModelRun"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags4
adverbTagCount0
adverbTags(empty)
dialogueSentences14
tagDensity0.286
leniency0.571
rawRatio0
effectiveRatio0
90.97% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount554
totalAiIsmAdverbs1
found
0
adverb"perfectly"
count1
highlights
0"perfectly"
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)
36.82% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount554
totalAiIsms7
found
0
word"fluttered"
count1
1
word"weight"
count1
2
word"flicked"
count1
3
word"stomach"
count1
4
word"pulse"
count1
5
word"pulsed"
count1
6
word"aligned"
count1
highlights
0"fluttered"
1"weight"
2"flicked"
3"stomach"
4"pulse"
5"pulsed"
6"aligned"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches0
maxInWindow0
found(empty)
highlights(empty)
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences47
matches(empty)
82.07% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences47
filterMatches
0"watch"
hedgeMatches
0"appeared to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences57
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen29
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords541
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions4
unquotedAttributions0
matches(empty)
20.97% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions32
wordCount465
uniqueNames11
maxNameDensity2.58
worstName"Quinn"
maxWindowNameDensity3.5
worstWindowName"Quinn"
discoveredNames
Tube1
Harlow1
Quinn12
Kowalski1
Oxfords1
Eva9
Veil1
Market1
Morris3
Atlanta1
Police1
persons
0"Harlow"
1"Quinn"
2"Kowalski"
3"Eva"
4"Morris"
places
0"Atlanta"
globalScore0.21
windowScore0.5
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences30
glossingSentenceCount0
matches(empty)
15.16% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords1.848
wordCount541
matches
0"not random damage, but deliberate patterns"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences57
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs28
mean19.32
std14.25
cv0.738
sampleLengths
047
124
227
341
420
513
638
75
812
950
1018
1111
1234
1311
143
158
1633
178
1817
1919
2010
215
2244
235
2422
254
268
274
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences47
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs85
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount9
semicolonCount0
flaggedSentences8
totalSentences57
ratio0.14
matches
0"The abandoned Tube station smelled of damp concrete and something older—the metallic tang of forgotten places."
1"Quinn's sharp jaw tightened as she surveyed the scene—scorch marks radiating outward from the rail tracks in unnatural patterns, the air humming faintly like a struck tuning fork."
2"She'd heard whispers—a place that only appeared to those who knew how to ask."
3"The victim—male, late twenties—had burn patterns spiderwebbing from his sternum outward."
4"Quinn examined Atlanta Police training kicked in—the way shadows pooled unnaturally beneath the corpse, the faint blue residue under his fingernails."
5"Quinn had seen similar etchings years ago—on a case file Morris had hidden in his flat after hours."
6"The needle spun wildly before jerking northwest—toward the sealed tunnel where torchlight failed to penetrate."
7"The scorch marks aligned perfectly beneath them—not random damage, but deliberate patterns."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount477
adjectiveStacks0
stackExamples(empty)
adverbCount11
adverbRatio0.023060796645702306
lyAdverbCount5
lyAdverbRatio0.010482180293501049
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences57
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences57
mean9.49
std5.82
cv0.613
sampleLengths
016
119
212
313
411
523
64
728
813
914
106
115
128
135
143
1514
1616
175
187
195
2017
217
2211
235
2410
256
2612
275
286
2921
3013
3111
323
333
345
359
3618
376
383
395
404
4113
424
4315
448
452
465
4716
4812
4916
75.44% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats2
diversityRatio0.47368421052631576
totalSentences57
uniqueOpeners27
72.46% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences46
matches
0"Then the screaming began."
ratio0.022
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount8
totalSentences46
matches
0"Her freckled hands fidgeted with"
1"She thumbed the worn leather"
2"She'd heard whispers—a place that"
3"She stood, brushing grit from"
4"She slipped it into her"
5"Her pulse hammered."
6"She gestured toward the compass"
7"She shone her flashlight upward."
ratio0.174
14.35% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount41
totalSentences46
matches
0"The abandoned Tube station smelled"
1"Detective Harlow Quinn descended the"
2"The torn police tape at"
3"Eva Kowalski stood near the"
4"Her freckled hands fidgeted with"
5"Eva said, tucking a curl"
6"Quinn's sharp jaw tightened as"
7"She thumbed the worn leather"
8"Quinn crouched, running gloved fingers"
9"Eva adjusted her round glasses."
10"Quinn's brown eyes flicked upward."
11"The Veil Market."
12"She'd heard whispers—a place that"
13"The sort of story her"
14"The thought soured her stomach."
15"She stood, brushing grit from"
16"Eva hesitated before leading her"
17"Quinn lifted the covering with"
18"The victim—male, late twenties—had burn"
19"The burns looked drawn onto"
ratio0.891
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences46
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences21
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags4
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags1
fancyCount0
fancyTags(empty)
dialogueSentences14
tagDensity0.071
leniency0.143
rawRatio0
effectiveRatio0
80.2747%