Run: 2026-02-17-01KHNFZF34SQVV8S3B4HD04AMX

Run Details

Model:
DeepSeek V3 (2025-03-24)
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
33.4s
Cost:
$0.001731
Provider:
Crusoe

Evaluation summary

Score Evaluator
Details Link
100.00% Adverbs in dialogue tags (details)
82.99% AI-ism adverb frequency (details)
100.00% AI-ism character names (details)
100.00% AI-ism location names (details)
31.97% 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)
0.00% Name drop frequency (details)
100.00% Narrator intent-glossing (details)
0.00% "Not X but Y" pattern overuse (details)
100.00% Overuse of "that" (subordinate clause padding) (details)
100.00% Paragraph length variance (details)
98.52% 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)
78.54% Sentence opener variety (details)
100.00% Adverb-first sentence starts (details)
100.00% Pronoun-first sentence starts (details)
62.27% Subject-first sentence starts (details)
0.00% Subordinate conjunction sentence starts (details)
100.00% Technical jargon density (details)
41.67% Useless dialogue additions (details)
100.00% Dialogue tag variety (said vs. fancy) (details)
79.8653% 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 sharper underneath—ozone, maybe, or the metallic whisper of old magic. Detective Harlow Quinn stepped over a fallen chain-link barrier, the beam of her flashlight cutting through the gloom. The air was thick with the kind of quiet that set her teeth on edge. Too quiet for Camden, even underground. A flicker of movement caught her eye down the platform. Eva Kowalski stood near a spill of broken glass, her curly red hair haloed in the dim emergency lighting. She was frowning at something in her hands—a small brass compass whose needle spun in erratic circles. "Interesting place to do research," Quinn called, her voice echoing off the tiled walls. Eva startled, nearly dropping the compass. She tucked it into her satchel, then pushed her round glasses up her nose. "Detective. I could say the same to you." Quinn approached, scanning the debris—cracked vials, scorch marks on the concrete, the lingering scent of burnt sage. "Crime scene," she said. "Report of a disturbance. You wouldn’t know anything about that, would you?" Eva’s fingers twitched toward her left ear, tucking a curl behind it. "I was just following a lead." A lead, sure. Quinn crouched near the largest scorch mark, running a finger along the edge. The pattern wasn’t consistent with any accelerant she knew—too precise, too symmetrical. Almost like sigil work. Her jaw tightened. "Where’d you get that compass?" she asked. Eva hesitated. "Antique shop." "Funny. Looks like the kind of thing they sell at the Veil Market." She watched Eva’s pupils dilate, just slightly. Bingo. "You know dealing in enchanted artifacts is still illegal, right?" "It’s just a compass," Eva muttered. Quinn stood, dusting her hands on her slacks. "Then you won’t mind if I take a look." Eva clutched her satchel tighter. "It’s delicate." The flashlight beam caught the edge of something half-hidden beneath a chunk of plaster—a bone token, the kind used to get into the Market. Quinn nudged it with her shoe. "You were here last night." A beat of silence. Then Eva exhaled. "Fine. Yes. But not for whatever you think happened." "Enlighten me." Eva adjusted her glasses again. "There was a… negotiation. It went bad. Someone tried to call up something they couldn’t control." Quinn’s pulse kicked. "What kind of something?" "You wouldn’t believe me." "Try me." Eva bit her lip, then reached into her satchel—not for the compass, but for a folded scrap of paper. She handed it over. "This was left behind." The paper was covered in cramped, feverish script—not any language Quinn recognized, but the symbols made her skin prickle. At the bottom, a crude sketch: a door, half-open, with something hunched in the threshold. She looked back at the scorch marks. Not an accident. Not arson. A containment breach. Three years ago, Morris had been scribbling the same kind of symbols in his notebook before he vanished. Quinn’s voice dropped. "Who was here?" "I don’t know their names," Eva said. "But they were looking for a way in." "In where?" Eva met her eyes. "Somewhere they shouldn’t." The compass in Eva’s bag let out a thin, high whine. Quinn’s hand went to her sidearm. "You hear that?" Eva went very still. "We should leave." Too late. Down the tunnel, something scraped against the tracks—long, slow, like claws on steel. The emergency lights flickered. Then went out. In the dark, the compass’s needle stopped spinning. It pointed straight ahead.
created_at"2026-02-17T09:48:24.772779+00:00" 2/17/2026, 9:48:24 AM
model"deepseek/deepseek-chat-v3-0324"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency885
moderation_latency(null)
generation_time27430
tokens_prompt923
tokens_completion965
native_tokens_prompt857
native_tokens_completion868
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"
usage0.0017305
router(null)
provider_responses
0
status(null)
is_byokfalse
latency5923
endpoint_id"d562908f-c5eb-4a32-9a91-24d53b176fd8"
provider_name"SiliconFlow"
model_permaslug"deepseek/deepseek-chat-v3-0324"
1
id"cmpl-48e6346957945c7abea9e1aa4ab91315"
status200
is_byokfalse
latency687
endpoint_id"eb0625b2-17a1-492d-b3cc-e35091f1431d"
provider_name"Crusoe"
model_permaslug"deepseek/deepseek-chat-v3-0324"
api_type"completions"
id"gen-1771321670-OQgoAruHtrVwwyWgNjE2"
upstream_id"cmpl-48e6346957945c7abea9e1aa4ab91315"
total_cost0.0017305
cache_discount(null)
upstream_inference_cost0
provider_name"Crusoe"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags6
adverbTagCount0
adverbTags(empty)
dialogueSentences27
tagDensity0.222
leniency0.444
rawRatio0
effectiveRatio0
82.99% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount588
totalAiIsmAdverbs2
found
0
adverb"slightly"
count1
1
adverb"very"
count1
highlights
0"slightly"
1"very"
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)
31.97% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount588
totalAiIsms8
found
0
word"whisper"
count1
1
word"gloom"
count1
2
word"flicker"
count1
3
word"echoing"
count1
4
word"scanning"
count1
5
word"silence"
count1
6
word"pulse"
count1
7
word"flickered"
count1
highlights
0"whisper"
1"gloom"
2"flicker"
3"echoing"
4"scanning"
5"silence"
6"pulse"
7"flickered"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"air was thick with"
count1
highlights
0"The air was thick with"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences52
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences52
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences73
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen26
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords577
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions6
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions31
wordCount426
uniqueNames9
maxNameDensity3.29
worstName"Eva"
maxWindowNameDensity5.5
worstWindowName"Eva"
discoveredNames
Tube1
Harlow1
Quinn10
Camden1
Kowalski1
Eva14
Bingo1
Market1
Morris1
persons
0"Harlow"
1"Quinn"
2"Kowalski"
3"Eva"
4"Morris"
places
0"Market"
globalScore0
windowScore0
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences27
glossingSentenceCount0
matches(empty)
0.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches2
per1kWords3.466
wordCount577
matches
0"not for the compass, but for a folded scrap of paper"
1"not any language Quinn recognized, but the symbols made her skin prickle"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences73
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs35
mean16.49
std13.71
cv0.832
sampleLengths
059
146
214
328
433
518
635
77
84
931
106
1117
127
1335
1416
152
1621
177
184
192
2027
2134
2215
2318
246
2515
262
277
2811
299
307
312
3220
338
344
98.52% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences52
matches
0"was covered"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount1
totalVerbs72
matches
0"was frowning"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount8
semicolonCount0
flaggedSentences8
totalSentences73
ratio0.11
matches
0"The abandoned Tube station smelled of damp concrete and something sharper underneath—ozone, maybe, or the metallic whisper of old magic."
1"She was frowning at something in her hands—a small brass compass whose needle spun in erratic circles."
2"Quinn approached, scanning the debris—cracked vials, scorch marks on the concrete, the lingering scent of burnt sage."
3"The pattern wasn’t consistent with any accelerant she knew—too precise, too symmetrical."
4"The flashlight beam caught the edge of something half-hidden beneath a chunk of plaster—a bone token, the kind used to get into the Market."
5"Eva bit her lip, then reached into her satchel—not for the compass, but for a folded scrap of paper."
6"The paper was covered in cramped, feverish script—not any language Quinn recognized, but the symbols made her skin prickle."
7"Down the tunnel, something scraped against the tracks—long, slow, like claws on steel."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount437
adjectiveStacks0
stackExamples(empty)
adverbCount15
adverbRatio0.034324942791762014
lyAdverbCount3
lyAdverbRatio0.006864988558352402
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences73
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences73
mean7.9
std5.84
cv0.738
sampleLengths
020
118
215
36
410
519
617
714
86
914
108
1117
124
1312
1412
156
163
1713
1812
194
203
217
222
232
2420
251
2610
276
288
299
305
312
3224
336
345
354
363
379
382
395
4016
413
424
434
442
4519
464
474
4819
4915
78.54% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.4794520547945205
totalSentences73
uniqueOpeners35
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount4
totalSentences44
matches
0"Too quiet for Camden, even"
1"Almost like sigil work."
2"Then Eva exhaled."
3"Then went out."
ratio0.091
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount7
totalSentences44
matches
0"She was frowning at something"
1"She tucked it into her"
2"Her jaw tightened."
3"She watched Eva’s pupils dilate,"
4"She handed it over."
5"She looked back at the"
6"It pointed straight ahead."
ratio0.159
62.27% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount35
totalSentences44
matches
0"The abandoned Tube station smelled"
1"Detective Harlow Quinn stepped over"
2"The air was thick with"
3"A flicker of movement caught"
4"Eva Kowalski stood near a"
5"She was frowning at something"
6"Quinn called, her voice echoing"
7"Eva startled, nearly dropping the"
8"She tucked it into her"
9"Quinn approached, scanning the debris—cracked"
10"Eva’s fingers twitched toward her"
11"A lead, sure."
12"Quinn crouched near the largest"
13"The pattern wasn’t consistent with"
14"Her jaw tightened."
15"She watched Eva’s pupils dilate,"
16"Quinn stood, dusting her hands"
17"Eva clutched her satchel tighter."
18"The flashlight beam caught the"
19"Quinn nudged it with her"
ratio0.795
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences44
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences18
technicalSentenceCount0
matches(empty)
41.67% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount1
matches
0"Quinn called, her voice echoing off the tiled walls"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags5
fancyCount1
fancyTags
0"Eva muttered (mutter)"
dialogueSentences27
tagDensity0.185
leniency0.37
rawRatio0.2
effectiveRatio0.074
79.8653%