Run: 2026-02-19-01KHSZAMVASXY7F15MDRZ11XB2

Run Details

Model:
Ministral 8B
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
4.5s
Cost:
$0.000193

Evaluation summary

Score Evaluator
Details Link
100.00% Adverbs in dialogue tags (details)
100.00% AI-ism adverb frequency (details)
80.00% AI-ism character names (details)
100.00% AI-ism location names (details)
59.61% 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)
68.37% Name drop frequency (details)
0.00% 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)
91.23% 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)
57.44% Sentence opener variety (details)
100.00% Adverb-first sentence starts (details)
100.00% Pronoun-first sentence starts (details)
60.00% Subject-first sentence starts (details)
0.00% Subordinate conjunction sentence starts (details)
18.63% Technical jargon density (details)
25.00% Useless dialogue additions (details)
100.00% Dialogue tag variety (said vs. fancy) (details)
78.6759% 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 rain had stopped, but the air still clung to the damp like a second skin, slick under Quinn’s boots as she stepped into the abandoned Tube station. The flickering fluorescent lights above buzzed weakly, casting long shadows that stretched like fingers across the cracked concrete. The station’s name—*Camden Road*—was peeling from the sign, letters flaking away as if the place itself had been eroded by time. She adjusted the strap of her satchel, fingers brushing the worn leather of her watch. The time read 3:17 AM, but the station felt like midnight. No trains rumbled below, no commuters shuffled through the turnstiles. Just the hum of something else—something that didn’t belong in the mundane world above. Detective DS Marcus Vale stood near the far wall, his back to her, arms crossed over his chest. His uniform was immaculate, the lapels pressed sharp as a blade. He didn’t turn when she entered, didn’t even acknowledge her presence. Quinn let the silence stretch between them, watching as his jaw tightened. “You’re late,” he said at last, his voice low. “Traffic,” she replied, though she knew he wasn’t talking about the roads. She moved closer, her boots making no sound on the wet floor. The air smelled of rust and something sharper—ozone, maybe, or the faint metallic tang of blood. Vale finally turned, his expression unreadable. “You think this is a normal break-in?” Quinn crouched beside the body, her gloved fingers brushing the cold metal of the victim’s wrist. No pulse. No breath. Just the hollow click of her pen against the concrete as she pulled out her notebook. “Looks like it,” she said. “But the timing’s off.” The body lay sprawled near the old ticket booth, arms splayed as if reaching for something just out of reach. The victim—a man in his late thirties, dressed in a cheap suit—had a neat puncture wound at the base of his throat. No struggle marks. No signs of a fight. Vale exhaled through his nose. “No forced entry. No alarms. Just… gone.” Quinn flipped open her notebook, her pen hovering over the page. “Who is he?” “Daniel Mercer. Worked at the museum. Curator of restricted archives.” Quinn’s fingers stilled. *Restricted archives.* That name rang a bell—someone she’d heard of, but not in the way a detective should. She stood, brushing dust from her knees. “Alone?” “So he said.” “Did he say *where* he was going?” Vale’s lips thinned. “He didn’t get the chance.” Quinn stepped back, her gaze sweeping the station. The walls were lined with graffiti—some recent, some faded by years. But there, near the old escalator, the freshest of them all. A symbol. A spiral, twisted into something that looked like a key. She crouched again, her fingers tracing the outline. “This wasn’t just a robbery.” Vale’s voice was flat. “You think it was supernatural?” Quinn didn’t answer. She stood, her eyes flicking to the far corner where a single bone token lay half-buried in the dirt. The kind you’d find at the Veil Market. “You ever hear of the Veil Market?” she asked. Vale’s expression darkened. “You’re not serious.” “Then explain this.” She gestured to the body, then to the symbol. “This isn’t a mugging. This isn’t even a killing. This is a *taking*.” Vale’s jaw clenched. “You’re jumping to conclusions.” “Am I?” Quinn’s voice was sharp. “Because if this man was taken by something that moves beneath the city, then we’re not dealing with a crime scene. We’re dealing with a *threshold*.” She turned, her boots crunching over the broken glass. The station stretched around her, hollow and waiting. Somewhere in this labyrinth, something had slipped through. And it wasn’t alone.
total_cost0.00019319999999999998

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags5
adverbTagCount0
adverbTags(empty)
dialogueSentences21
tagDensity0.238
leniency0.476
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount619
totalAiIsmAdverbs0
found(empty)
highlights(empty)
80.00% AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions(empty)
found
0"Marcus"
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
59.61% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount619
totalAiIsms5
found
0
word"silence"
count1
1
word"unreadable"
count1
2
word"pulse"
count1
3
word"tracing"
count1
4
word"jaw clenched"
count1
highlights
0"silence"
1"unreadable"
2"pulse"
3"tracing"
4"jaw clenched"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"jaw/fists clenched"
count1
highlights
0"jaw clenched"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences50
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences50
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences65
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen28
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans5
markdownWords7
totalWords611
ratio0.011
matches
0"Camden Road"
1"Restricted archives."
2"where"
3"taking"
4"threshold"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions9
unquotedAttributions0
matches(empty)
68.37% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions19
wordCount490
uniqueNames6
maxNameDensity1.63
worstName"Quinn"
maxWindowNameDensity2.5
worstWindowName"Quinn"
discoveredNames
Quinn8
Tube1
Marcus1
Vale7
Veil1
Market1
persons
0"Quinn"
1"Marcus"
2"Vale"
places
0"Veil"
globalScore0.684
windowScore0.833
0.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences34
glossingSentenceCount3
matches
0"felt like midnight"
1"as if reaching for something just out of reach"
2"looked like a key"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount611
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences65
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs27
mean22.63
std17.6
cv0.778
sampleLengths
067
150
252
39
440
513
636
79
850
912
1014
1110
1229
133
147
158
1642
1713
189
1930
209
216
2225
237
2432
2525
264
91.23% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences50
matches
0"been eroded"
1"were lined"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount1
totalVerbs82
matches
0"wasn’t talking"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount8
semicolonCount0
flaggedSentences6
totalSentences65
ratio0.092
matches
0"The station’s name—*Camden Road*—was peeling from the sign, letters flaking away as if the place itself had been eroded by time."
1"Just the hum of something else—something that didn’t belong in the mundane world above."
2"The air smelled of rust and something sharper—ozone, maybe, or the faint metallic tang of blood."
3"The victim—a man in his late thirties, dressed in a cheap suit—had a neat puncture wound at the base of his throat."
4"*Restricted archives.* That name rang a bell—someone she’d heard of, but not in the way a detective should."
5"The walls were lined with graffiti—some recent, some faded by years."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount497
adjectiveStacks0
stackExamples(empty)
adverbCount17
adverbRatio0.03420523138832998
lyAdverbCount2
lyAdverbRatio0.004024144869215292
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences65
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences65
mean9.4
std6.17
cv0.656
sampleLengths
028
118
221
315
411
510
614
718
811
911
1012
119
1212
1312
1416
156
167
1716
182
192
2016
215
224
2320
2422
253
265
275
287
2911
303
3110
323
3318
347
351
363
377
383
395
408
4111
4211
432
4410
458
465
474
485
493
57.44% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats6
diversityRatio0.4
totalSentences65
uniqueOpeners26
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences45
matches
0"Just the hum of something"
1"Just the hollow click of"
2"Somewhere in this labyrinth, something"
ratio0.067
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount11
totalSentences45
matches
0"She adjusted the strap of"
1"His uniform was immaculate, the"
2"He didn’t turn when she"
3"he said at last, his"
4"she replied, though she knew"
5"She moved closer, her boots"
6"She stood, brushing dust from"
7"She crouched again, her fingers"
8"She stood, her eyes flicking"
9"She gestured to the body,"
10"She turned, her boots crunching"
ratio0.244
60.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount36
totalSentences45
matches
0"The rain had stopped, but"
1"The flickering fluorescent lights above"
2"The station’s name—*Camden Road*—was peeling"
3"She adjusted the strap of"
4"The time read 3:17 AM,"
5"Detective DS Marcus Vale stood"
6"His uniform was immaculate, the"
7"He didn’t turn when she"
8"Quinn let the silence stretch"
9"he said at last, his"
10"she replied, though she knew"
11"She moved closer, her boots"
12"The air smelled of rust"
13"Vale finally turned, his expression"
14"Quinn crouched beside the body,"
15"The body lay sprawled near"
16"The victim—a man in his"
17"Vale exhaled through his nose."
18"Quinn flipped open her notebook,"
19"Quinn’s fingers stilled."
ratio0.8
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences45
matches(empty)
ratio0
18.63% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences23
technicalSentenceCount4
matches
0"The flickering fluorescent lights above buzzed weakly, casting long shadows that stretched like fingers across the cracked concrete."
1"The station’s name—*Camden Road*—was peeling from the sign, letters flaking away as if the place itself had been eroded by time."
2"Just the hum of something else—something that didn’t belong in the mundane world above."
3"The body lay sprawled near the old ticket booth, arms splayed as if reaching for something just out of reach."
25.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags5
uselessAdditionCount1
matches
0"he said, his voice low"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags4
fancyCount0
fancyTags(empty)
dialogueSentences21
tagDensity0.19
leniency0.381
rawRatio0
effectiveRatio0
78.6759%