Run: 2026-02-19-01KHSZ6VV2V98XTFYXNSX19ZCY

Run Details

Model:
Ministral 3B
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
2.5s
Cost:
$0.000066

Evaluation summary

Score Evaluator
Details Link
0.00% Adverbs in dialogue tags (details)
100.00% AI-ism adverb frequency (details)
100.00% AI-ism character names (details)
100.00% AI-ism location names (details)
0.00% 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)
32.35% 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)
90.94% Passive voice overuse (details)
87.01% Past progressive (was/were + -ing) overuse (details)
35.04% Em-dash & semicolon overuse (details)
100.00% Purple prose (modifier overload) (details)
100.00% Repeated phrase echo (details)
100.00% Sentence length variance (details)
61.64% Sentence opener variety (details)
100.00% Adverb-first sentence starts (details)
100.00% Pronoun-first sentence starts (details)
64.65% Subject-first sentence starts (details)
0.00% Subordinate conjunction sentence starts (details)
23.81% Technical jargon density (details)
0.00% Useless dialogue additions (details)
100.00% Dialogue tag variety (said vs. fancy) (details)
76.5146% 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 neon glow of the abandoned Tube station pulsed like a dying heartbeat. Detective Harlow Quinn stepped over the cracked tiles, her boots crunching on rusted metal. The air smelled of damp earth and something older—something that clung to the walls like a second skin. “You’re sure this is where it happened?” DS Morris’s voice cut through the silence, sharp as a blade. Quinn didn’t answer. She knelt, fingers brushing the bloodstained floorboards. The stain wasn’t fresh. Not by a long shot. It had dried in uneven patches, as if something had been dragged across it before the last rain. “Morris,” she said, voice low, “what’s the usual cause of death in a place like this?” Morris exhaled through his nose, rubbing his jaw. “Overdose. Suicide. Or someone who didn’t make it out in time.” Quinn’s gaze flicked to the broken glass at her feet. Not a suicide note. Not a note at all. Just a mess. A woman’s purse, half-buried under a heap of discarded clothes. The strap was torn, the contents spilled out—coins, a crumpled receipt, a single photograph. She picked it up. A man’s face stared back at her, gaunt and tired. Not the kind of man who’d take his own life. A low hum vibrated beneath her boots. Quinn froze. The Veil Compass lay on the floor, its brass casing dulled by time, the needle still pointing straight ahead. “Morris,” she said again, “what’s this?” Morris hesitated, then plucked the compass from the ground. His fingers trembled. “I don’t know. It’s not mine.” Quinn’s jaw tightened. She turned the compass over in her palm. The sigils on its face were worn smooth, but the patina on the casing told a different story. Verdigris. Not just old. *Crafted.* “You’re sure this isn’t a coincidence?” Quinn asked, voice tight. Morris’s eyes flickered to the photograph. “Coincidence? No.” His voice dropped. “This woman wasn’t here last week. Not in this station. Not anywhere near.” Quinn’s stomach twisted. She set the compass down. The needle didn’t move. Not yet. A distant shriek echoed through the station. Too high. Too sharp. Like a child’s. Morris’s face paled. “We need to move.” Quinn didn’t argue. She grabbed the compass, the weight of it familiar, almost *right.* The station was closing in on itself, the walls pressing in. The air thickened, the air itself seemed to hum. Then the lights flickered. And the Veil Market opened.
total_cost0.00006584

Evaluation details

Result Evaluator Details Meta Data
0.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags4
adverbTagCount1
adverbTags
0"she said again [again]"
dialogueSentences9
tagDensity0.444
leniency0.889
rawRatio0.25
effectiveRatio0.222
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount406
totalAiIsmAdverbs0
found(empty)
highlights(empty)
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)
0.00% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount406
totalAiIsms11
found
0
word"pulsed"
count1
1
word"silence"
count1
2
word"flicked"
count1
3
word"vibrated"
count1
4
word"trembled"
count1
5
word"flickered"
count2
6
word"stomach"
count1
7
word"echoed"
count1
8
word"weight"
count1
9
word"familiar"
count1
highlights
0"pulsed"
1"silence"
2"flicked"
3"vibrated"
4"trembled"
5"flickered"
6"stomach"
7"echoed"
8"weight"
9"familiar"
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
narrationSentences49
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount1
narrationSentences49
filterMatches(empty)
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences53
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen22
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans2
markdownWords2
totalWords404
ratio0.005
matches
0"Crafted."
1"right."
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions5
unquotedAttributions0
matches(empty)
32.35% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions19
wordCount340
uniqueNames7
maxNameDensity2.35
worstName"Quinn"
maxWindowNameDensity3
worstWindowName"Quinn"
discoveredNames
Tube1
Harlow1
Quinn8
Morris5
Veil2
Compass1
Market1
persons
0"Harlow"
1"Quinn"
2"Morris"
3"Compass"
4"Market"
places(empty)
globalScore0.324
windowScore0.667
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences21
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount404
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences53
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs19
mean21.26
std12.86
cv0.605
sampleLengths
046
118
237
316
419
546
624
728
86
918
1034
1110
1224
1314
1414
157
1634
174
185
90.94% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences49
matches
0"been dragged"
1"was torn"
87.01% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount1
totalVerbs59
matches
0"was closing"
35.04% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount2
semicolonCount0
flaggedSentences2
totalSentences53
ratio0.038
matches
0"The air smelled of damp earth and something older—something that clung to the walls like a second skin."
1"The strap was torn, the contents spilled out—coins, a crumpled receipt, a single photograph."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount342
adjectiveStacks0
stackExamples(empty)
adverbCount11
adverbRatio0.03216374269005848
lyAdverbCount0
lyAdverbRatio0
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences53
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences53
mean7.62
std5.43
cv0.712
sampleLengths
014
114
218
318
43
57
64
75
818
916
108
1111
1210
134
145
153
1610
1714
184
1910
2010
217
222
2319
246
259
263
276
283
298
3018
311
323
331
3410
356
365
3713
383
395
404
412
427
432
442
453
463
474
483
4922
61.64% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats4
diversityRatio0.41509433962264153
totalSentences53
uniqueOpeners22
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences43
matches
0"Just a mess."
1"Then the lights flickered."
ratio0.047
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount10
totalSentences43
matches
0"She knelt, fingers brushing the"
1"It had dried in uneven"
2"she said, voice low"
3"She picked it up."
4"she said again"
5"His fingers trembled."
6"She turned the compass over"
7"His voice dropped"
8"She set the compass down."
9"She grabbed the compass, the"
ratio0.233
64.65% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount34
totalSentences43
matches
0"The flickering neon glow of"
1"Detective Harlow Quinn stepped over"
2"The air smelled of damp"
3"DS Morris’s voice cut through"
4"Quinn didn’t answer."
5"She knelt, fingers brushing the"
6"The stain wasn’t fresh."
7"It had dried in uneven"
8"she said, voice low"
9"Morris exhaled through his nose,"
10"Quinn’s gaze flicked to the"
11"A woman’s purse, half-buried under"
12"The strap was torn, the"
13"She picked it up."
14"A man’s face stared back"
15"A low hum vibrated beneath"
16"The Veil Compass lay on"
17"she said again"
18"Morris hesitated, then plucked the"
19"His fingers trembled."
ratio0.791
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences43
matches(empty)
ratio0
23.81% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences12
technicalSentenceCount2
matches
0"The air smelled of damp earth and something older—something that clung to the walls like a second skin."
1"The Veil Compass lay on the floor, its brass casing dulled by time, the needle still pointing straight ahead."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags4
uselessAdditionCount2
matches
0"she said, voice low,"
1"Quinn asked, voice tight"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags3
fancyCount0
fancyTags(empty)
dialogueSentences9
tagDensity0.333
leniency0.667
rawRatio0
effectiveRatio0
76.5146%