Run: 2026-02-19-01KHTRM8R0NFSWHD0TW7QBCR6M

Run Details

Model:
Ministral 3B
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
2.5s
Cost:
$0.000071

Evaluation summary

Score Evaluator
Details Link
82.35% Adverbs in dialogue tags (details)
70.70% AI-ism adverb frequency (details)
100.00% AI-ism character names (details)
100.00% AI-ism location names (details)
41.41% 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)
68.03% Name drop frequency (details)
66.67% 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)
90.33% Passive voice overuse (details)
17.35% 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)
71.35% Sentence opener variety (details)
75.76% Adverb-first sentence starts (details)
100.00% Pronoun-first sentence starts (details)
0.00% Subject-first sentence starts (details)
0.00% Subordinate conjunction sentence starts (details)
47.62% Technical jargon density (details)
0.00% Useless dialogue additions (details)
100.00% Dialogue tag variety (said vs. fancy) (details)
74.3856% 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 station was a tomb of rusted metal and flickering fluorescent tubes, the air thick with the scent of damp earth and something older—something that clung like sweat to the back of Harlow Quinn’s neck. She stepped through the cracked glass doors, her boots crunching on shattered glass, and the weight of the case pressing down on her shoulders. The Veil Market. She’d been expecting this for weeks, but not like this. A figure sat cross-legged in the dim glow of a flickering LED bulb, their back to her, hunched over a ledger. The ink was smudged, the pages yellowed with age, but the numbers didn’t make sense. A single bone token lay discarded beside them, its hollow eye socket filled with soot. “Morris’s report,” she said, voice low, sharp. “They found this place under Camden. Some kind of black market.” The figure turned slowly, their face half-lit by the sickly light. A woman with curly red hair and round glasses, her freckles dusted across a pale complexion. She tucked a strand behind her ear, her fingers trembling just slightly. “Aurora,” Eva Kowalski said, voice steady. “You’re not supposed to be here.” Harlow didn’t wait for an answer. She moved closer, her military precision kicking in. The ledger lay open to a page where figures scribbled in what looked like cipher, but the numbers didn’t add up. A transaction for a “Veil Compass” listed at an impossible price—twenty times what the market had ever paid for such a thing. “You’re selling it,” she said, her fingers hovering over the page. “But why?” Eva exhaled sharply, rubbing the bridge of her nose. “Because it’s not just a compass. It’s a tool for something bigger.” Harlow’s jaw tightened. “Then why’s the needle pointing at nothing?” Eva didn’t answer. Instead, she gestured to the ledger. “Because it’s not pointing anywhere. It’s broken.” Harlow’s pulse spiked. Broken. That wasn’t how the compass worked. The needle should always point—toward the rift, toward the danger. Unless… She turned to the wall behind Eva, where a series of sigils had been carved into the concrete. Not just any sigils—these were the kind that bound, the kind that sealed. The kind that kept things in. “Who’s keeping what in?” she asked, voice cutting through the silence. Eva’s hands clenched around the edge of the ledger. “The Veil Market doesn’t just sell things. It *collects* them.” Harlow’s mind raced. The case files had mentioned a “clique,” a group pulling strings from the shadows. But this? This was different. This was *systematic*. Someone was hoarding supernatural energy, hoarding power, and selling it like it was a commodity. A sharp knock at the door made them both freeze. “Detective Quinn?” A voice, rough with exhaustion. “You in there?” Harlow turned just as the door creaked open. A uniformed officer stood there, their face pale. “Sir, we found another body.” Eva’s breath hitched. “Another?” Harlow didn’t answer. She already knew. The Veil Market didn’t just deal in goods. It dealt in lives. And now, it was taking hers.
total_cost0.00007144

Evaluation details

Result Evaluator Details Meta Data
82.35% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags6
adverbTagCount1
adverbTags
0"the market had ever [ever]"
dialogueSentences17
tagDensity0.353
leniency0.706
rawRatio0.167
effectiveRatio0.118
70.70% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount512
totalAiIsmAdverbs3
found
0
adverb"slowly"
count1
1
adverb"slightly"
count1
2
adverb"sharply"
count1
highlights
0"slowly"
1"slightly"
2"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)
41.41% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount512
totalAiIsms6
found
0
word"shattered"
count1
1
word"weight"
count1
2
word"pulse"
count1
3
word"silence"
count1
4
word"raced"
count1
5
word"systematic"
count1
highlights
0"shattered"
1"weight"
2"pulse"
3"silence"
4"raced"
5"systematic"
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
narrationSentences47
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences47
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences57
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen36
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans2
markdownWords2
totalWords506
ratio0.004
matches
0"collects"
1"systematic"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions8
unquotedAttributions0
matches(empty)
68.03% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions19
wordCount427
uniqueNames6
maxNameDensity1.64
worstName"Harlow"
maxWindowNameDensity2.5
worstWindowName"Harlow"
discoveredNames
Harlow7
Quinn1
Veil2
Market2
Kowalski1
Eva6
persons
0"Harlow"
1"Quinn"
2"Market"
3"Kowalski"
4"Eva"
places(empty)
globalScore0.68
windowScore0.833
66.67% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences30
glossingSentenceCount1
matches
0"looked like cipher, but the numbers didn’"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount506
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences57
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs20
mean25.3
std17.77
cv0.702
sampleLengths
072
151
218
339
412
557
613
721
810
916
1021
1137
1211
1319
1440
1510
1610
1721
184
1924
90.33% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences47
matches
0"was smudged"
1"been carved"
17.35% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs73
matches
0"was hoarding"
1"was taking"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount4
semicolonCount0
flaggedSentences4
totalSentences57
ratio0.07
matches
0"The station was a tomb of rusted metal and flickering fluorescent tubes, the air thick with the scent of damp earth and something older—something that clung like sweat to the back of Harlow Quinn’s neck."
1"A transaction for a “Veil Compass” listed at an impossible price—twenty times what the market had ever paid for such a thing."
2"The needle should always point—toward the rift, toward the danger."
3"Not just any sigils—these were the kind that bound, the kind that sealed."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount433
adjectiveStacks0
stackExamples(empty)
adverbCount13
adverbRatio0.03002309468822171
lyAdverbCount5
lyAdverbRatio0.011547344110854504
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences57
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences57
mean8.88
std6.6
cv0.744
sampleLengths
035
124
23
310
421
515
615
77
811
911
1016
1112
126
136
146
158
1621
1722
1811
192
209
2112
223
237
243
256
267
273
281
296
3010
311
3218
3313
346
3511
369
3710
383
3914
402
413
423
4315
4410
457
463
478
488
495
71.35% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.43859649122807015
totalSentences57
uniqueOpeners25
75.76% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences44
matches
0"Instead, she gestured to the"
ratio0.023
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount10
totalSentences44
matches
0"She stepped through the cracked"
1"She’d been expecting this for"
2"she said, voice low, sharp"
3"She tucked a strand behind"
4"She moved closer, her military"
5"she said, her fingers hovering"
6"She turned to the wall"
7"she asked, voice cutting through"
8"She already knew."
9"It dealt in lives."
ratio0.227
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount41
totalSentences44
matches
0"The station was a tomb"
1"She stepped through the cracked"
2"The Veil Market."
3"She’d been expecting this for"
4"A figure sat cross-legged in"
5"The ink was smudged, the"
6"A single bone token lay"
7"she said, voice low, sharp"
8"The figure turned slowly, their"
9"A woman with curly red"
10"She tucked a strand behind"
11"Eva Kowalski said, voice steady"
12"Harlow didn’t wait for an"
13"She moved closer, her military"
14"The ledger lay open to"
15"A transaction for a listed"
16"she said, her fingers hovering"
17"Eva exhaled sharply, rubbing the"
18"Harlow’s jaw tightened."
19"Eva didn’t answer."
ratio0.932
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences44
matches(empty)
ratio0
47.62% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences15
technicalSentenceCount2
matches
0"The station was a tomb of rusted metal and flickering fluorescent tubes, the air thick with the scent of damp earth and something older—something that clung lik…"
1"She stepped through the cracked glass doors, her boots crunching on shattered glass, and the weight of the case pressing down on her shoulders."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount4
matches
0"she said, voice low, sharp"
1"Eva Kowalski said, voice steady"
2"she said, her fingers hovering over the page"
3"she asked, voice cutting through the silence"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags4
fancyCount0
fancyTags(empty)
dialogueSentences17
tagDensity0.235
leniency0.471
rawRatio0
effectiveRatio0
74.3856%