Run: 2026-02-20-01KHYA1ETQXFB2BX43KRMF1BET

Run Details

Model:
Ministral 3 8B
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
4.4s
Cost:
$0.000271
Provider:
Mistral

Evaluation summary

Score Evaluator
Details Link
33.33% Adverbs in dialogue tags (details)
90.31% AI-ism adverb frequency (details)
100.00% AI-ism character names (details)
100.00% AI-ism location names (details)
51.55% AI-ism word frequency (details)
100.00% Cliché density (details)
100.00% Emotion telling (show vs. tell) (details)
49.69% Filter word density (details)
100.00% Gibberish response detection (details)
100.00% Markdown formatting overuse (details)
100.00% Missing dialogue indicators (quotation marks) (details)
62.47% 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)
90.01% Passive voice overuse (details)
100.00% Past progressive (was/were + -ing) overuse (details)
0.00% Em-dash & semicolon overuse (details)
93.51% Purple prose (modifier overload) (details)
100.00% Repeated phrase echo (details)
100.00% Sentence length variance (details)
60.00% Sentence opener variety (details)
100.00% Adverb-first sentence starts (details)
100.00% Pronoun-first sentence starts (details)
18.14% Subject-first sentence starts (details)
0.00% Subordinate conjunction sentence starts (details)
58.82% Technical jargon density (details)
0.00% Useless dialogue additions (details)
66.67% Dialogue tag variety (said vs. fancy) (details)
75.8169% 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 flickering sodium lights of the abandoned Tube station cast jagged shadows across the damp concrete, their glow barely piercing the thick haze of cigarette smoke and the acrid tang of something older—something that clung to the air like rust. Detective Quinn stepped over the yellow tape, her boots crunching on broken glass and the occasional brittle bone. The station’s nameplate, *Camden Road*, was long since peeled away, the letters swallowed by graffiti that slithered like veins across the walls. “You’re late,” DS Carter muttered, his voice tight. He stood near the far end of the platform, arms crossed, his breath curling in the cold. His flashlight cut through the gloom, illuminating the scattered debris—clothes, a shattered mirror, and something darker, glistening under the light. Quinn didn’t answer. She let her gaze drift over the scene, her sharp jaw tightening. The body lay near the tracks, half-hidden beneath a tangle of rusted metal. A woman, if the shape was anything to go by. Her skin had that unnatural pallor, the kind that didn’t fade even in the dim light. Too still. Too *wrong*. “Suicide,” Carter said, stepping forward. “Found her like this. Note in her pocket—*‘I can’t stop it.’* Classic signs.” Quinn crouched, her leather watch ticking against the concrete. The woman’s fingers were curled around something small, tucked into her palm. A bone token. Not the kind sold at the Veil Market—these were rougher, carved from something organic, still damp with residue. She pried it loose with a gloved finger. The moment it left the woman’s grip, the air around it *shifted*, like a ripple in water. Carter’s flashlight flickered. “What the hell?” Quinn didn’t look up. “Not a suicide.” The token pulsed faintly, then dissolved into ash between her fingers. The woman’s body twitched—just once—and her head lolled back, the neck making a wet, sickening sound. Her eyes, when they finally opened, weren’t human. They were black, bottomless, reflecting nothing. Carter stumbled back. “Jesus Christ.” Quinn stood, her military precision sharp as a blade. “She wasn’t dead when we got here.” The station’s walls seemed to breathe, the air thick with the scent of ozone and something metallic. Carter’s radio crackled to life, static hissing before a voice cut through—DS Morris’s, though his voice was distorted, layered with something else. “*Quinn… don’t trust the shadows.*” The line went dead. Quinn’s fingers twitched toward her watch. The last time she’d heard Morris’s voice like that, he’d been standing in the middle of a ritual circle, his skin stretched too tight over his bones. She’d never found his body. Carter swallowed hard. “You think this is connected?” She didn’t answer. Instead, she knelt again, this time examining the tracks. The woman’s boots were scuffed, the soles worn thin. Not someone who’d come here by choice. And the tracks—*fresh*. Too fresh. “She was dragged,” Quinn said quietly. Carter exhaled sharply. “By who?” Quinn stood, brushing dirt from her knees. “By something that doesn’t leave footprints.” The station’s ventilation grates groaned, metal screeching against metal. Somewhere in the dark, something *moved*.
created_at"2026-02-20T19:57:14.475Z" 2/20/2026, 7:57:14 PM
model"mistralai/ministral-8b-2512"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency206
moderation_latency(null)
generation_time3921
tokens_prompt1149
tokens_completion876
native_tokens_prompt1062
native_tokens_completion742
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"
usage0.0002706
router(null)
provider_responses
0
endpoint_id"c85d26e1-1e0c-449b-9775-2afce7ae510b"
id"7e52d59e71c844489e94e46492234bbb"
is_byokfalse
latency206
model_permaslug"mistralai/ministral-8b-2512"
provider_name"Mistral"
status200
api_type"completions"
id"gen-1771617434-z9umtdHvzS3qRBDgqYQ8"
upstream_id"7e52d59e71c844489e94e46492234bbb"
total_cost0.0002706
cache_discount(null)
upstream_inference_cost0
provider_name"Mistral"

Evaluation details

Result Evaluator Details Meta Data
33.33% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags3
adverbTagCount1
adverbTags
0"Quinn said quietly [quietly]"
dialogueSentences12
tagDensity0.25
leniency0.5
rawRatio0.333
effectiveRatio0.167
90.31% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount516
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)
51.55% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount516
totalAiIsms5
found
0
word"gloom"
count1
1
word"shattered"
count1
2
word"glistening"
count1
3
word"flickered"
count1
4
word"pulsed"
count1
highlights
0"gloom"
1"shattered"
2"glistening"
3"flickered"
4"pulsed"
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
narrationSentences46
matches(empty)
49.69% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount2
hedgeCount1
narrationSentences46
filterMatches
0"watch"
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences55
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen41
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans7
markdownWords15
totalWords509
ratio0.029
matches
0"Camden Road"
1"wrong"
2"‘I can’t stop it.’"
3"shifted"
4"Quinn… don’t trust the shadows."
5"fresh"
6"moved"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions9
unquotedAttributions0
matches(empty)
62.47% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions20
wordCount457
uniqueNames6
maxNameDensity1.75
worstName"Quinn"
maxWindowNameDensity2.5
worstWindowName"Quinn"
discoveredNames
Tube1
Quinn8
Carter7
Veil1
Market1
Morris2
persons
0"Quinn"
1"Carter"
2"Morris"
places
0"Veil"
globalScore0.625
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences30
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount509
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences55
matches
0"like that, he’d"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs20
mean25.45
std22.7
cv0.892
sampleLengths
080
145
258
318
467
56
67
741
85
916
1039
115
124
1338
148
1533
166
175
1813
1915
90.01% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences46
matches
0"were curled"
1"were scuffed"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs75
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount7
semicolonCount0
flaggedSentences6
totalSentences55
ratio0.109
matches
0"The flickering sodium lights of the abandoned Tube station cast jagged shadows across the damp concrete, their glow barely piercing the thick haze of cigarette smoke and the acrid tang of something older—something that clung to the air like rust."
1"His flashlight cut through the gloom, illuminating the scattered debris—clothes, a shattered mirror, and something darker, glistening under the light."
2"Not the kind sold at the Veil Market—these were rougher, carved from something organic, still damp with residue."
3"The woman’s body twitched—just once—and her head lolled back, the neck making a wet, sickening sound."
4"Carter’s radio crackled to life, static hissing before a voice cut through—DS Morris’s, though his voice was distorted, layered with something else."
5"And the tracks—*fresh*."
93.51% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount464
adjectiveStacks0
stackExamples(empty)
adverbCount22
adverbRatio0.04741379310344827
lyAdverbCount5
lyAdverbRatio0.010775862068965518
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences55
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences55
mean9.25
std7.42
cv0.802
sampleLengths
040
118
222
38
417
520
63
712
813
910
1016
112
122
135
1413
159
1612
173
1818
198
2017
213
223
234
243
2511
2616
278
286
293
302
319
327
3317
3422
355
364
376
3827
395
403
415
423
439
449
457
463
472
486
493
60.00% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats2
diversityRatio0.38181818181818183
totalSentences55
uniqueOpeners21
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences43
matches
0"Instead, she knelt again, this"
1"Somewhere in the dark, something"
ratio0.047
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount9
totalSentences43
matches
0"He stood near the far"
1"His flashlight cut through the"
2"She let her gaze drift"
3"Her skin had that unnatural"
4"She pried it loose with"
5"Her eyes, when they finally"
6"They were black, bottomless, reflecting"
7"She’d never found his body."
8"She didn’t answer."
ratio0.209
18.14% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount38
totalSentences43
matches
0"The flickering sodium lights of"
1"Detective Quinn stepped over the"
2"The station’s nameplate, *Camden Road*,"
3"DS Carter muttered, his voice"
4"He stood near the far"
5"His flashlight cut through the"
6"Quinn didn’t answer."
7"She let her gaze drift"
8"The body lay near the"
9"A woman, if the shape"
10"Her skin had that unnatural"
11"Carter said, stepping forward"
12"Quinn crouched, her leather watch"
13"The woman’s fingers were curled"
14"A bone token."
15"She pried it loose with"
16"The moment it left the"
17"Carter’s flashlight flickered."
18"Quinn didn’t look up."
19"The token pulsed faintly, then"
ratio0.884
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences43
matches(empty)
ratio0
58.82% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences17
technicalSentenceCount2
matches
0"The flickering sodium lights of the abandoned Tube station cast jagged shadows across the damp concrete, their glow barely piercing the thick haze of cigarette …"
1"The station’s nameplate, *Camden Road*, was long since peeled away, the letters swallowed by graffiti that slithered like veins across the walls."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags3
uselessAdditionCount1
matches
0"DS Carter muttered, his voice tight"
66.67% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags3
fancyCount1
fancyTags
0"DS Carter muttered (mutter)"
dialogueSentences12
tagDensity0.25
leniency0.5
rawRatio0.333
effectiveRatio0.167
75.8169%