Run: 2026-02-20-01KHYA5FAF7WN7GWSD57GCCA7E

Run Details

Model:
Ministral 3 8B
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
4.6s
Cost:
$0.000290
Provider:
Mistral

Evaluation summary

Score Evaluator
Details Link
94.74% Adverbs in dialogue tags (details)
91.96% AI-ism adverb frequency (details)
100.00% AI-ism character names (details)
100.00% AI-ism location names (details)
59.81% 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)
74.10% 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)
91.50% 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)
53.13% Sentence opener variety (details)
0.00% Adverb-first sentence starts (details)
83.83% Pronoun-first sentence starts (details)
0.00% Subject-first sentence starts (details)
0.00% Subordinate conjunction sentence starts (details)
83.33% Technical jargon density (details)
0.00% Useless dialogue additions (details)
100.00% Dialogue tag variety (said vs. fancy) (details)
77.7465% 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 drummed against the corrugated metal roof of the abandoned Tube station like a slow, relentless drumbeat. Detective Harlow Quinn adjusted the cuffs of her coat, her sharp jaw set beneath the brim of her hat, the leather watch on her left wrist ticking away the seconds. The air smelled of damp earth and something older—something metallic, like old blood left to rust. She stepped over the rusted warning signs, her boots crunching on broken glass and the occasional bone fragment. The station’s nameplate, *Camden Overground*, hung askew, its letters peeling. The flickering light of her torch cut through the gloom, illuminating the scattered debris: a single shoe, its sole torn, a tattered scarf snagged on a broken pipe. “You’re late,” DS Carter said from the shadows, his voice tight. He stood near the far wall, arms crossed, his breath visible in the cold. “Thought you’d never get here.” Harlow didn’t look at him. Her gaze locked onto the body. The woman lay sprawled against the wall, her back pressed into the damp stone. Her curly red hair fanned out around her like a halo of copper, but her face was wrong—too still, too pale. Her lips were blue-tinged, her skin stretched too tight over her cheekbones. A jagged gash ran from her temple to her jaw, but it wasn’t fresh. The blood had dried dark, crusting at the edges. Harlow crouched, her gloved fingers brushing the woman’s wrist. No pulse. No breath. She turned her head, following the trail of blood leading away from the body. It pooled in the corner, thick and dark, but not enough for a fatal wound. Not unless something else had finished her. “Eva Kowalski,” Carter said, his voice flat. “Occult researcher. Worked at the British Museum.” Harlow didn’t answer. She stood, her torchlight sweeping over the scene. The walls were lined with strange symbols, scratched into the stone—some recent, others faded with time. A Veil Compass lay half-buried in the dirt near the body, its brass casing tarnished with verdigris. The needle pointed straight at the ceiling, as if it had been tossed there in frustration. “You think this is a hit?” Carter asked, his voice careful. “Or just another bad deal gone wrong?” Harlow picked up the compass, turning it over in her fingers. The sigils on the face were intricate, almost hypnotic. “It’s not a hit.” “Then what?” She didn’t look at him. “She didn’t die here.” Carter exhaled sharply. “You’re saying she was brought in?” “No.” Harlow’s voice was low, precise. “She was *taken*.” The torchlight caught something else—a single bone token, half-buried in the dirt near the compass. It was small, no bigger than her thumbnail, etched with the same sigils as the compass. The kind of thing you’d need to get into the Veil Market. Carter crouched beside her, his breath hitching. “You think she was dealing with the wrong people?” Harlow didn’t answer. She stepped back, her gaze sweeping over the scene again. The symbols on the wall weren’t just random. They formed a pattern, a map of sorts. And at the center of it all, just above the body, was a single word, scratched into the stone: *Rift.* “This isn’t just a crime scene,” she said finally. “It’s a warning.” Carter stared at her, his face pale in the torchlight. “What do you mean?” Harlow didn’t explain. She didn’t need to. She already knew what she had to do next. She turned and walked toward the exit, her boots crunching over the broken glass. Carter followed, his voice tight behind her. “Where are we going?” “To the Veil Market,” she said. “And we’re bringing the whole damn station with us.”
created_at"2026-02-20T19:59:26.043Z" 2/20/2026, 7:59:26 PM
model"mistralai/ministral-8b-2512"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency252
moderation_latency(null)
generation_time4183
tokens_prompt1149
tokens_completion982
native_tokens_prompt1062
native_tokens_completion871
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached256
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"
usage0.00028995
router(null)
provider_responses
0
endpoint_id"c85d26e1-1e0c-449b-9775-2afce7ae510b"
id"6ecc5a2637ca4818bdb0224550701b1a"
is_byokfalse
latency252
model_permaslug"mistralai/ministral-8b-2512"
provider_name"Mistral"
status200
api_type"completions"
id"gen-1771617566-SYogEm1Fbf9WYu8zxCOM"
upstream_id"6ecc5a2637ca4818bdb0224550701b1a"
total_cost0.00028995
cache_discount(null)
upstream_inference_cost0
provider_name"Mistral"

Evaluation details

Result Evaluator Details Meta Data
94.74% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags5
adverbTagCount1
adverbTags
0"she said finally [finally]"
dialogueSentences19
tagDensity0.263
leniency0.526
rawRatio0.2
effectiveRatio0.105
91.96% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount622
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)
59.81% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount622
totalAiIsms5
found
0
word"gloom"
count1
1
word"tinged"
count1
2
word"pulse"
count1
3
word"intricate"
count1
4
word"etched"
count1
highlights
0"gloom"
1"tinged"
2"pulse"
3"intricate"
4"etched"
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
emotionTells1
narrationSentences51
matches
0"e in frustration"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences51
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences64
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen30
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans3
markdownWords4
totalWords615
ratio0.007
matches
0"Camden Overground"
1"taken"
2"Rift."
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions8
unquotedAttributions0
matches(empty)
74.10% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions21
wordCount527
uniqueNames7
maxNameDensity1.52
worstName"Harlow"
maxWindowNameDensity2.5
worstWindowName"Carter"
discoveredNames
Tube1
Harlow8
Quinn1
Carter7
Veil2
Compass1
Market1
persons
0"Harlow"
1"Quinn"
2"Carter"
places
0"Veil"
globalScore0.741
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences36
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount615
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences64
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs24
mean25.63
std20.84
cv0.813
sampleLengths
064
156
230
311
470
549
614
760
818
924
102
119
129
139
1443
1516
1648
171
1812
1914
2016
2121
224
2315
91.50% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences51
matches
0"were lined"
1"been tossed"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs87
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount4
semicolonCount0
flaggedSentences4
totalSentences64
ratio0.063
matches
0"The air smelled of damp earth and something older—something metallic, like old blood left to rust."
1"Her curly red hair fanned out around her like a halo of copper, but her face was wrong—too still, too pale."
2"The walls were lined with strange symbols, scratched into the stone—some recent, others faded with time."
3"The torchlight caught something else—a single bone token, half-buried in the dirt near the compass."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount534
adjectiveStacks0
stackExamples(empty)
adverbCount13
adverbRatio0.024344569288389514
lyAdverbCount3
lyAdverbRatio0.0056179775280898875
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences64
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences64
mean9.61
std6.04
cv0.629
sampleLengths
018
130
216
318
410
528
611
714
85
95
106
1114
1221
1312
1414
159
169
172
182
1914
2015
217
227
237
243
258
2616
2717
2816
2911
307
3111
329
334
342
355
364
373
386
396
403
4115
4216
4312
447
459
463
4710
488
498
53.13% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats6
diversityRatio0.375
totalSentences64
uniqueOpeners24
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences47
matches(empty)
ratio0
83.83% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount16
totalSentences47
matches
0"She stepped over the rusted"
1"He stood near the far"
2"Her gaze locked onto the"
3"Her curly red hair fanned"
4"Her lips were blue-tinged, her"
5"She turned her head, following"
6"It pooled in the corner,"
7"She stood, her torchlight sweeping"
8"She didn’t look at him."
9"It was small, no bigger"
10"She stepped back, her gaze"
11"They formed a pattern, a"
12"she said finally"
13"She didn’t need to."
14"She already knew what she"
15"She turned and walked toward"
ratio0.34
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount45
totalSentences47
matches
0"The rain drummed against the"
1"Detective Harlow Quinn adjusted the"
2"The air smelled of damp"
3"She stepped over the rusted"
4"The station’s nameplate, *Camden Overground*,"
5"The flickering light of her"
6"DS Carter said from the"
7"He stood near the far"
8"Harlow didn’t look at him."
9"Her gaze locked onto the"
10"The woman lay sprawled against"
11"Her curly red hair fanned"
12"Her lips were blue-tinged, her"
13"A jagged gash ran from"
14"The blood had dried dark,"
15"Harlow crouched, her gloved fingers"
16"She turned her head, following"
17"It pooled in the corner,"
18"Carter said, his voice flat"
19"Harlow didn’t answer."
ratio0.957
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences47
matches(empty)
ratio0
83.33% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences24
technicalSentenceCount2
matches
0"She stepped over the rusted warning signs, her boots crunching on broken glass and the occasional bone fragment."
1"She turned her head, following the trail of blood leading away from the body."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags5
uselessAdditionCount3
matches
0"DS Carter said, his voice tight"
1"Carter said, his voice flat"
2"Carter asked, his voice careful"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags5
fancyCount0
fancyTags(empty)
dialogueSentences19
tagDensity0.263
leniency0.526
rawRatio0
effectiveRatio0
77.7465%