Run: 2026-02-19-01KHT0BM734ZQWQ52GF7BSWNYJ

Run Details

Model:
DeepSeek V3 (2024-12-26)
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
30.4s
Cost:
$0.001528
Provider:
Novita

Evaluation summary

Score Evaluator
Details Link
100.00% Adverbs in dialogue tags (details)
81.98% AI-ism adverb frequency (details)
100.00% AI-ism character names (details)
100.00% AI-ism location names (details)
36.94% 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)
8.25% 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)
99.32% Passive voice overuse (details)
100.00% Past progressive (was/were + -ing) overuse (details)
8.40% Em-dash & semicolon overuse (details)
100.00% Purple prose (modifier overload) (details)
100.00% Repeated phrase echo (details)
100.00% Sentence length variance (details)
75.29% Sentence opener variety (details)
100.00% Adverb-first sentence starts (details)
100.00% Pronoun-first sentence starts (details)
22.50% Subject-first sentence starts (details)
0.00% Subordinate conjunction sentence starts (details)
100.00% Technical jargon density (details)
62.50% Useless dialogue additions (details)
100.00% Dialogue tag variety (said vs. fancy) (details)
83.1727% Overall

Model input

System
You are an expert fiction writer. Always keep the following rules in mind: - Write in past tense and use General English spelling, grammar, and colloquialisms/slang. - Write in active voice - Always follow the "show, don't tell" principle. - Avoid adverbs and cliches and overused/commonly used phrases. Aim for fresh and original descriptions. - Convey events and story through dialogue. - Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. - Skip "he/she said said" dialogue tags and convey people's actions or face expressions through their speech - Avoid mushy dialog and descriptions, have dialogue always continue the action, never stall or add unnecessary fluff. Vary the descriptions to not repeat yourself. - Put dialogue on its own paragraph to separate scene and action. - Reduce indicators of uncertainty like "trying" or "maybe" When writing text: - NEVER conclude the scene on your own, follow the beat instructions very closely. - NEVER end with foreshadowing. - NEVER write further than what I prompt you with. - AVOID imagining possible endings, NEVER deviate from the instructions. - STOP EARLY if the continuation contains what was required in the instructions. You do not need to fill out the full amount of words possible.
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <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> Continue the story using the following instructions: <instructions> 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. </instructions>

Model response

AI
The abandoned Tube station beneath Camden reeked of damp concrete and something metallic—blood, maybe, or rust. Detective Harlow Quinn ducked under the police tape, her boots crunching on broken glass. The flickering emergency lights cast long shadows across the platform, turning the graffiti into writhing shapes. "Quinn." DS Carter stood by the body, his flashlight beam cutting through the gloom. "You're late." She adjusted the worn leather watch on her wrist. "Traffic." The victim lay sprawled near the tracks, a man in his forties with a gash across his throat. No wallet, no ID. Just a dark stain spreading beneath him. Quinn crouched, gloved fingers hovering over the wound. "Clean cut. Almost surgical." Carter snorted. "Or a pissed-off vamp with a knife." She shot him a look. "Vampires don’t leave bodies." "Maybe this one was sloppy." Quinn ignored him, scanning the scene. The blood spatter didn’t match the angle of the wound. Too high, too wide. "He was moved." Carter folded his arms. "Or he staggered before he dropped." "No drag marks. No smears." She pointed to the tracks. "Look at the dust. Someone swept it." A glint caught her eye—a small brass compass near the victim’s hand, its face etched with strange symbols. The needle spun lazily, then jerked toward the tunnel’s mouth. Quinn picked it up. The casing was cool, patinaed with verdigris. "Another tourist trinket," Carter said. "This place is full of junk." She turned it over. "Not this kind." Eva Kowalski’s voice cut through the dark. "That’s a Veil Compass." Quinn turned. The redhead stood at the edge of the tape, her round glasses reflecting the dim light. Her satchel bulged with books, and she tucked a loose curl behind her ear. Carter frowned. "Who let her in?" "I did." Quinn pocketed the compass. "Kowalski’s a consultant." Eva stepped closer, her freckled face pale. "It points to rifts. Supernatural weak spots." Carter rolled his eyes. "Right. Because ghosts did this." Quinn ignored him. "Why would the victim have it?" "Maybe he was looking for something." Eva’s gaze darted to the tunnel. "Or running from it." Quinn studied the body again. The man’s shoes were scuffed, the soles worn thin. A traveler. But his clothes were cheap, ill-fitting. Stolen? She moved toward the tunnel. The compass needle twitched. "Quinn," Carter warned. "We’re not paid to chase fairy tales." She kept walking. The air grew colder, thick with the scent of ozone. The beam of her flashlight caught something on the wall—a symbol, freshly carved. Eva inhaled sharply. "That’s a warding mark. Someone tried to seal this place." Quinn traced the grooves with her finger. "It didn’t work." The compass needle spun wildly. A sound echoed from the darkness—a whisper, or the scrape of claws on concrete. Carter’s radio crackled. "All units, we’ve got another body. Two blocks south." Quinn didn’t move. "Same MO?" "Throat cut. No ID." She glanced at Eva, then back at the tunnel. The pieces didn’t fit. Two kills, same night. But the second one was sloppy. A distraction. "Tell forensics to bag everything," she said. "And get a team down here. I want this tunnel swept." Carter scoffed. "For what? More hocus-pocus?" Quinn held up the compass. The needle pointed straight at him. "For starters," she said, "how about a motive?"
created_at"2026-02-19T03:51:04.171Z" 2/19/2026, 3:51:04 AM
model"deepseek/deepseek-chat-v3"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1762
moderation_latency(null)
generation_time30356
tokens_prompt1149
tokens_completion922
native_tokens_prompt1032
native_tokens_completion858
native_tokens_completion_images0
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"
usage0.0015282
router(null)
provider_responses
0
endpoint_id"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
id"99acc5c1715a42c24fa8562afb2911ed"
is_byokfalse
latency1762
model_permaslug"deepseek/deepseek-chat-v3"
provider_name"Novita"
status200
api_type"completions"
id"gen-1771473064-hgRtxZWot4c9ByA4eKj3"
upstream_id"99acc5c1715a42c24fa8562afb2911ed"
total_cost0.0015282
cache_discount(null)
upstream_inference_cost0
provider_name"Novita"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags8
adverbTagCount0
adverbTags(empty)
dialogueSentences34
tagDensity0.235
leniency0.471
rawRatio0
effectiveRatio0
81.98% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount555
totalAiIsmAdverbs2
found
0
adverb"lazily"
count1
1
adverb"sharply"
count1
highlights
0"lazily"
1"sharply"
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)
36.94% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount555
totalAiIsms7
found
0
word"gloom"
count1
1
word"scanning"
count1
2
word"glint"
count1
3
word"etched"
count1
4
word"traced"
count1
5
word"echoed"
count1
6
word"whisper"
count1
highlights
0"gloom"
1"scanning"
2"glint"
3"etched"
4"traced"
5"echoed"
6"whisper"
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
narrationSentences59
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences59
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences85
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen19
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords548
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions4
unquotedAttributions0
matches(empty)
8.25% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions29
wordCount388
uniqueNames7
maxNameDensity2.84
worstName"Quinn"
maxWindowNameDensity3.5
worstWindowName"Quinn"
discoveredNames
Tube1
Camden1
Harlow1
Quinn11
Carter9
Kowalski1
Eva5
persons
0"Camden"
1"Harlow"
2"Quinn"
3"Carter"
4"Kowalski"
5"Eva"
places(empty)
globalScore0.082
windowScore0.5
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences27
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount548
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences85
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs37
mean14.81
std10.32
cv0.697
sampleLengths
046
116
210
341
49
59
65
723
810
917
1039
1111
127
1311
1432
156
169
1714
189
199
2016
2123
229
2310
2426
2513
2610
275
2814
2912
305
314
3225
3318
346
3511
368
99.32% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences59
matches
0"were scuffed"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs66
matches(empty)
8.40% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount4
semicolonCount0
flaggedSentences4
totalSentences85
ratio0.047
matches
0"The abandoned Tube station beneath Camden reeked of damp concrete and something metallic—blood, maybe, or rust."
1"A glint caught her eye—a small brass compass near the victim’s hand, its face etched with strange symbols."
2"The beam of her flashlight caught something on the wall—a symbol, freshly carved."
3"A sound echoed from the darkness—a whisper, or the scrape of claws on concrete."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount393
adjectiveStacks0
stackExamples(empty)
adverbCount12
adverbRatio0.030534351145038167
lyAdverbCount4
lyAdverbRatio0.010178117048346057
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences85
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences85
mean6.45
std4.07
cv0.632
sampleLengths
016
114
216
314
42
59
61
718
84
97
108
114
122
137
145
154
165
176
1810
194
203
214
226
2310
247
2518
2610
274
287
295
306
314
323
337
344
352
3616
3714
382
394
406
413
427
437
444
455
463
476
4812
494
75.29% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.4588235294117647
totalSentences85
uniqueOpeners39
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences48
matches
0"Just a dark stain spreading"
1"Too high, too wide."
ratio0.042
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount8
totalSentences48
matches
0"She adjusted the worn leather"
1"She shot him a look."
2"She pointed to the tracks"
3"She turned it over."
4"Her satchel bulged with books,"
5"She moved toward the tunnel."
6"She kept walking."
7"She glanced at Eva, then"
ratio0.167
22.50% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount42
totalSentences48
matches
0"The abandoned Tube station beneath"
1"Detective Harlow Quinn ducked under"
2"The flickering emergency lights cast"
3"DS Carter stood by the"
4"She adjusted the worn leather"
5"The victim lay sprawled near"
6"Quinn crouched, gloved fingers hovering"
7"She shot him a look."
8"Quinn ignored him, scanning the"
9"The blood spatter didn’t match"
10"Carter folded his arms."
11"She pointed to the tracks"
12"A glint caught her eye—a"
13"The needle spun lazily, then"
14"Quinn picked it up."
15"The casing was cool, patinaed"
16"She turned it over."
17"Eva Kowalski’s voice cut through"
18"The redhead stood at the"
19"Her satchel bulged with books,"
ratio0.875
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences48
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences12
technicalSentenceCount0
matches(empty)
62.50% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags8
uselessAdditionCount1
matches
0"DS Carter stood, his flashlight beam cutting through the gloom"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags4
fancyCount1
fancyTags
0"Carter warned (warn)"
dialogueSentences34
tagDensity0.118
leniency0.235
rawRatio0.25
effectiveRatio0.059
83.1727%