Run: 2026-02-20-01KHY7K0KWET6V0WG3F44XD1H2

Run Details

Model:
Ministral 3 14B
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
5.9s
Cost:
$0.000353
Provider:
Mistral

Evaluation summary

Score Evaluator
Details Link
100.00% Adverbs in dialogue tags (details)
90.25% AI-ism adverb frequency (details)
100.00% AI-ism character names (details)
100.00% AI-ism location names (details)
41.52% 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)
46.91% 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)
82.38% Passive voice overuse (details)
100.00% Past progressive (was/were + -ing) overuse (details)
0.00% Em-dash & semicolon overuse (details)
97.25% Purple prose (modifier overload) (details)
100.00% Repeated phrase echo (details)
100.00% Sentence length variance (details)
66.07% Sentence opener variety (details)
0.00% Adverb-first sentence starts (details)
100.00% Pronoun-first sentence starts (details)
22.50% Subject-first sentence starts (details)
0.00% Subordinate conjunction sentence starts (details)
95.24% Technical jargon density (details)
0.00% Useless dialogue additions (details)
100.00% Dialogue tag variety (said vs. fancy) (details)
78.0706% 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 abandoned Tube station reeked of damp concrete and something older, something that clung to the air like a second skin. Detective Harlow Quinn stepped over the yellow tape, her boots crunching on shattered glass. The flickering overhead lights cast long, skeletal shadows across the graffiti-scarred walls. This wasn’t just another crime scene—it was a puzzle with pieces missing. DS Whitaker stood near the body, his flashlight beam trembling slightly as he adjusted his glasses. “Looks like another overdose,” he said, voice tight. “Third this month. Same MO—needle marks, empty vial on the floor.” Quinn didn’t touch the body. She didn’t need to. The victim was sprawled near the old ticket booth, arms splayed like they’d been trying to crawl away. But the bruising on his wrists wasn’t from struggling. It was from restraints. And the restraints weren’t there anymore. She crouched, examining the concrete. No drag marks. No blood spatter beyond what the coroner would expect. Just… clean. Too clean. “You see this?” Quinn tapped the ground where the victim’s fingers had dug into the dirt. The marks were too precise, like someone had pressed them there. “And the bruises—too neat. No struggle. No panic.” Whitaker exhaled through his nose. “Could be a clean kill. Maybe he was already dead when they dumped him.” Quinn stood, her sharp jaw tightening. “No. He was alive when they left him here.” She pointed to the far wall, where the graffiti had been scratched out in jagged lines—symbols she didn’t recognise, but the way they pulsed under the flickering light made her skin prickle. “And this wasn’t just a drop point.” Whitaker followed her gaze. “You think it’s connected to the others?” “No.” Quinn’s voice was low, certain. “I think this one’s different.” A uniformed officer approached, holding a small brass compass. The needle spun wildly before settling on a spot just beyond the station’s collapsed exit. Quinn’s pulse jumped. She’d seen that before—in the files she’d buried after Morris died. “Where’d you find that?” she asked. The officer swallowed. “By the body. Looked like it fell out of his pocket.” Quinn took it. The casing was warm, almost alive. The sigils etched into the brass weren’t just decorative—they burned faintly, like embers under skin. She’d read about these in Eva’s notes. *Veil Compass*. A relic from the underground markets where things that shouldn’t exist changed hands. Whitaker’s radio crackled. “Detective? We got a witness. Says she saw someone carrying a bag down here last night. Dark coat, hood up.” Quinn’s fingers tightened around the compass. “Get her in. Now.” The station’s air thickened, pressing in like a held breath. She could almost taste the lie in the scene—the way the shadows stretched too long, the way the symbols on the wall seemed to whisper. Whitaker hesitated. “Quinn, we don’t know what we’re dealing with here.” She didn’t answer. She was already moving toward the exit, the compass heavy in her palm. The witness would talk. And whatever was buried beneath Camden would have to show itself.
created_at"2026-02-20T19:14:24.01Z" 2/20/2026, 7:14:24 PM
model"mistralai/ministral-14b-2512"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency302
moderation_latency(null)
generation_time5667
tokens_prompt1149
tokens_completion849
native_tokens_prompt1062
native_tokens_completion705
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"
usage0.0003534
router(null)
provider_responses
0
endpoint_id"0b53717b-9af5-4de3-80af-ebedd2adf981"
id"922d3cbb2d43491dae7af72a6ad18bdc"
is_byokfalse
latency302
model_permaslug"mistralai/ministral-14b-2512"
provider_name"Mistral"
status200
api_type"completions"
id"gen-1771614864-Qvj5S9EytUV2RlKTgCmj"
upstream_id"922d3cbb2d43491dae7af72a6ad18bdc"
total_cost0.0003534
cache_discount(null)
upstream_inference_cost0
provider_name"Mistral"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags4
adverbTagCount0
adverbTags(empty)
dialogueSentences15
tagDensity0.267
leniency0.533
rawRatio0
effectiveRatio0
90.25% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount513
totalAiIsmAdverbs1
found
0
adverb"slightly"
count1
highlights
0"slightly"
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)
41.52% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount513
totalAiIsms6
found
0
word"shattered"
count1
1
word"pulsed"
count1
2
word"pulse"
count1
3
word"almost alive"
count1
4
word"etched"
count1
5
word"whisper"
count1
highlights
0"shattered"
1"pulsed"
2"pulse"
3"almost alive"
4"etched"
5"whisper"
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)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount1
narrationSentences46
filterMatches(empty)
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences56
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen42
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans1
markdownWords2
totalWords505
ratio0.004
matches
0"Veil Compass"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions5
unquotedAttributions0
matches(empty)
46.91% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions18
wordCount388
uniqueNames7
maxNameDensity2.06
worstName"Quinn"
maxWindowNameDensity3
worstWindowName"Quinn"
discoveredNames
Tube1
Harlow1
Quinn8
Whitaker5
Morris1
Eva1
Camden1
persons
0"Harlow"
1"Quinn"
2"Whitaker"
3"Morris"
4"Eva"
5"Camden"
places(empty)
globalScore0.469
windowScore0.667
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences25
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount505
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences56
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs19
mean26.58
std15.95
cv0.6
sampleLengths
059
135
246
321
435
519
654
711
811
938
106
1114
1246
1323
1410
1535
1611
1716
1815
82.38% Passive voice overuse
Target: ≤2% passive sentences
passiveCount3
totalSentences46
matches
0"was sprawled"
1"been scratched"
2"was buried"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs82
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount5
semicolonCount0
flaggedSentences5
totalSentences56
ratio0.089
matches
0"This wasn’t just another crime scene—it was a puzzle with pieces missing."
1"“No. He was alive when they left him here.” She pointed to the far wall, where the graffiti had been scratched out in jagged lines—symbols she didn’t recognise, but the way they pulsed under the flickering light made her skin prickle."
2"She’d seen that before—in the files she’d buried after Morris died."
3"The sigils etched into the brass weren’t just decorative—they burned faintly, like embers under skin."
4"She could almost taste the lie in the scene—the way the shadows stretched too long, the way the symbols on the wall seemed to whisper."
97.25% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount394
adjectiveStacks0
stackExamples(empty)
adverbCount17
adverbRatio0.04314720812182741
lyAdverbCount3
lyAdverbRatio0.007614213197969543
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences56
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences56
mean9.02
std6.9
cv0.765
sampleLengths
021
114
212
312
416
58
611
75
84
918
109
114
126
135
143
159
161
171
182
1916
2011
218
225
2314
246
2541
267
274
287
296
305
319
3215
333
3411
356
363
3711
383
396
4015
417
422
4313
443
4520
466
474
4810
4925
66.07% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.42857142857142855
totalSentences56
uniqueOpeners24
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences40
matches(empty)
ratio0
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount10
totalSentences40
matches
0"he said, voice tight"
1"She didn’t need to."
2"It was from restraints."
3"She crouched, examining the concrete."
4"She pointed to the far"
5"She’d seen that before—in the"
6"She’d read about these in"
7"She could almost taste the"
8"She didn’t answer."
9"She was already moving toward"
ratio0.25
22.50% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount35
totalSentences40
matches
0"The abandoned Tube station reeked"
1"Detective Harlow Quinn stepped over"
2"The flickering overhead lights cast"
3"This wasn’t just another crime"
4"DS Whitaker stood near the"
5"he said, voice tight"
6"Quinn didn’t touch the body."
7"She didn’t need to."
8"The victim was sprawled near"
9"It was from restraints."
10"She crouched, examining the concrete."
11"Quinn tapped the ground where"
12"The marks were too precise,"
13"Whitaker exhaled through his nose."
14"Quinn stood, her sharp jaw"
15"She pointed to the far"
16"Whitaker followed her gaze."
17"Quinn’s voice was low, certain"
18"A uniformed officer approached, holding"
19"The needle spun wildly before"
ratio0.875
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences40
matches(empty)
ratio0
95.24% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences15
technicalSentenceCount1
matches
0"The abandoned Tube station reeked of damp concrete and something older, something that clung to the air like a second skin."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags4
uselessAdditionCount1
matches
0"he said, voice tight"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount0
fancyTags(empty)
dialogueSentences15
tagDensity0.133
leniency0.267
rawRatio0
effectiveRatio0
78.0706%