Run: 2026-02-19-01KHTX46BG1MMKJE1PH3JSGW3E

Run Details

Model:
DeepSeek V3 (2025-03-24)
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
1m 2s
Cost:
$0.000819
Provider:
DeepInfra

Evaluation summary

Score Evaluator
Details Link
100.00% Adverbs in dialogue tags (details)
90.91% AI-ism adverb frequency (details)
100.00% AI-ism character names (details)
100.00% AI-ism location names (details)
18.18% 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)
25.62% Name drop frequency (details)
60.71% 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)
100.00% Passive voice overuse (details)
100.00% Past progressive (was/were + -ing) overuse (details)
0.00% Em-dash & semicolon overuse (details)
94.00% Purple prose (modifier overload) (details)
100.00% Repeated phrase echo (details)
100.00% Sentence length variance (details)
87.82% Sentence opener variety (details)
100.00% Adverb-first sentence starts (details)
100.00% Pronoun-first sentence starts (details)
38.95% Subject-first sentence starts (details)
100.00% Subordinate conjunction sentence starts (details)
100.00% Technical jargon density (details)
100.00% Useless dialogue additions (details)
94.44% Dialogue tag variety (said vs. fancy) (details)
87.0213% 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 smelled of damp concrete and something metallic underneath—copper and old pennies. Detective Harlow Quinn’s boots echoed against the cracked tiles as she stepped past the yellow police tape. The flickering emergency lights cast long shadows across the platform, illuminating the remnants of what should’ve been a straightforward crime scene. Uniforms had cordoned off a section near the rusted tracks, where a body lay sprawled in an unnatural position. A man—mid-thirties, dark hair matted with blood—his throat slit clean. But the blood pattern was wrong. Too little pooling, too much spatter in places that didn’t match the angle of the wound. Eva Kowalski stood near the edge of the platform, her round glasses catching the dim light as she scribbled notes into a battered leather-bound journal. She tucked a loose curl behind her ear when she noticed Quinn approaching. "You’re late." Quinn checked her watch—the leather strap worn smooth from years of use. "Got held up at the station. What’ve we got?" "John Doe. No ID, no wallet, but his clothes are high-end. Custom tailoring." Eva gestured to the body. "And this?" She pointed to the man’s left hand, where a faint mark glowed under the emergency lights—a sigil burned into his palm. Quinn crouched, gloved fingers hovering above the mark. "Not gang-related. Too precise." Eva shifted her satchel. "I’ve seen this before. In the archives. It’s a binding mark. Someone didn’t just kill him—they sealed something." Quinn’s jaw tightened. "Sealed what?" Eva hesitated, then pulled a small brass compass from her satchel. The verdigris-patinated casing caught the light, the needle twitching erratically despite being nowhere near true north. "This place isn’t just abandoned," Eva murmured. "It’s active." Quinn stood, scanning the platform. The shadows seemed deeper than they should’ve been. The air tasted electric, like before a storm. "You’re telling me this is supernatural." "I’m telling you the evidence doesn’t fit a normal homicide." Eva adjusted her glasses. "Look at the blood spatter. It arcs *upward*. Like something pulled it." Quinn exhaled sharply. Three years ago, Morris had vanished on a case with similar inconsistencies—blood where there shouldn’t have been, marks no coroner could explain. She’d buried the reports, told herself it was bad intel, bad luck. Now, standing in the flickering dark of the Veil Market’s threshold, the pieces clicked. "You knew about this place," Quinn said. Eva tucked the compass away. "I research the occult. Of course I knew." Quinn’s gaze flicked to the tracks, where something shimmered—a distortion in the air, like heat off asphalt. The compass needle jerked violently in Eva’s satchel. "Tell me you didn’t bring us here without backup." Eva’s fingers tightened around her journal. "I thought it was just a murder. But that mark?" She nodded to the body. "It’s a lock. And whatever was locked inside him is gone now." Quinn’s pulse thudded in her throat. The platform groaned—a sound too deep for old metal. Shadows pooled thicker near the tracks, twisting like smoke. "We need to go." Eva didn’t argue. They moved fast, footsteps sharp against the tiles. Behind them, the emergency lights flickered once, twice—then died. Darkness swallowed the platform whole. Only the whisper of something moving in the black remained.
created_at"2026-02-19T12:13:49.302Z" 2/19/2026, 12:13:49 PM
model"deepseek/deepseek-chat-v3-0324"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency649
moderation_latency(null)
generation_time62473
tokens_prompt1149
tokens_completion925
native_tokens_prompt1032
native_tokens_completion801
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached64
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"
usage0.00081901
router(null)
provider_responses
0
endpoint_id"820376cb-f110-4d56-ab52-5bd6ca269420"
id"chatcmpl-RhgXyH6miRD5UrdbLH4axHDc"
is_byokfalse
latency92
model_permaslug"deepseek/deepseek-chat-v3-0324"
provider_name"DeepInfra"
status200
api_type"completions"
id"gen-1771503229-B9puSjg4xDZ8KVmqDOdr"
upstream_id"chatcmpl-RhgXyH6miRD5UrdbLH4axHDc"
total_cost0.00081901
cache_discount0.00000416
upstream_inference_cost0
provider_name"DeepInfra"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags6
adverbTagCount0
adverbTags(empty)
dialogueSentences18
tagDensity0.333
leniency0.667
rawRatio0
effectiveRatio0
90.91% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount550
totalAiIsmAdverbs1
found
0
adverb"sharply"
count1
highlights
0"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)
18.18% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount550
totalAiIsms9
found
0
word"echoed"
count1
1
word"scanning"
count1
2
word"electric"
count1
3
word"flicked"
count1
4
word"shimmered"
count1
5
word"pulse"
count1
6
word"footsteps"
count1
7
word"flickered"
count1
8
word"whisper"
count1
highlights
0"echoed"
1"scanning"
2"electric"
3"flicked"
4"shimmered"
5"pulse"
6"footsteps"
7"flickered"
8"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
narrationSentences40
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences40
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences52
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen26
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans1
markdownWords1
totalWords535
ratio0.002
matches
0"upward"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions8
unquotedAttributions0
matches(empty)
25.62% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions26
wordCount402
uniqueNames8
maxNameDensity2.49
worstName"Quinn"
maxWindowNameDensity4
worstWindowName"Quinn"
discoveredNames
Tube1
Harlow1
Quinn10
Kowalski1
Morris1
Veil1
Market1
Eva10
persons
0"Harlow"
1"Quinn"
2"Kowalski"
3"Morris"
4"Market"
5"Eva"
places(empty)
globalScore0.256
windowScore0.333
60.71% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences28
glossingSentenceCount1
matches
0"seemed deeper than they should’ve been"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount535
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences52
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs26
mean20.58
std14.45
cv0.702
sampleLengths
053
151
238
32
421
541
612
722
85
927
109
1127
1226
1337
1414
157
1613
1725
189
1933
2024
214
223
2317
245
2510
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences40
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs73
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount10
semicolonCount0
flaggedSentences8
totalSentences52
ratio0.154
matches
0"The abandoned Tube station smelled of damp concrete and something metallic underneath—copper and old pennies."
1"A man—mid-thirties, dark hair matted with blood—his throat slit clean."
2"Quinn checked her watch—the leather strap worn smooth from years of use."
3"\"And this?\" She pointed to the man’s left hand, where a faint mark glowed under the emergency lights—a sigil burned into his palm."
4"Three years ago, Morris had vanished on a case with similar inconsistencies—blood where there shouldn’t have been, marks no coroner could explain."
5"Quinn’s gaze flicked to the tracks, where something shimmered—a distortion in the air, like heat off asphalt."
6"The platform groaned—a sound too deep for old metal."
7"Behind them, the emergency lights flickered once, twice—then died."
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount414
adjectiveStacks1
stackExamples
0"battered leather-bound journal."
adverbCount16
adverbRatio0.03864734299516908
lyAdverbCount4
lyAdverbRatio0.00966183574879227
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences52
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences52
mean10.29
std5.84
cv0.568
sampleLengths
015
117
221
319
410
56
616
725
813
92
1012
119
1218
1323
148
154
164
1718
183
192
2011
2116
227
232
245
258
268
276
2814
2912
303
3122
3212
3314
347
355
368
3717
388
399
406
4115
4212
436
449
459
464
473
488
499
87.82% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.5384615384615384
totalSentences52
uniqueOpeners28
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences38
matches
0"Too little pooling, too much"
1"Only the whisper of something"
ratio0.053
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount5
totalSentences38
matches
0"She tucked a loose curl"
1"She pointed to the man’s"
2"She’d buried the reports, told"
3"She nodded to the body"
4"They moved fast, footsteps sharp"
ratio0.132
38.95% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount32
totalSentences38
matches
0"The abandoned Tube station smelled"
1"Detective Harlow Quinn’s boots echoed"
2"The flickering emergency lights cast"
3"Uniforms had cordoned off a"
4"A man—mid—thirties, dark hair matted"
5"Eva Kowalski stood near the"
6"She tucked a loose curl"
7"Quinn checked her watch—the leather"
8"Eva gestured to the body"
9"She pointed to the man’s"
10"Quinn crouched, gloved fingers hovering"
11"Eva shifted her satchel."
12"Quinn’s jaw tightened."
13"Eva hesitated, then pulled a"
14"The verdigris-patinated casing caught the"
15"Quinn stood, scanning the platform."
16"The shadows seemed deeper than"
17"The air tasted electric, like"
18"Eva adjusted her glasses"
19"Quinn exhaled sharply."
ratio0.842
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences38
matches
0"Now, standing in the flickering"
ratio0.026
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences18
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount0
matches(empty)
94.44% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount1
fancyTags
0"Eva murmured (murmur)"
dialogueSentences18
tagDensity0.111
leniency0.222
rawRatio0.5
effectiveRatio0.111
87.0213%