Run: 2026-02-20-01KHY8GH3XC2AN497MSVHYJP85

Run Details

Model:
Ministral 3 3B
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
3.1s
Cost:
$0.000193
Provider:
Mistral

Evaluation summary

Score Evaluator
Details Link
100.00% Adverbs in dialogue tags (details)
91.94% AI-ism adverb frequency (details)
100.00% AI-ism character names (details)
100.00% AI-ism location names (details)
27.42% 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)
22.30% 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)
93.16% 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)
42.54% Sentence opener variety (details)
0.00% Adverb-first sentence starts (details)
100.00% Pronoun-first sentence starts (details)
0.00% Subject-first sentence starts (details)
89.29% Subordinate conjunction sentence starts (details)
74.83% Technical jargon density (details)
0.00% Useless dialogue additions (details)
0.00% Dialogue tag variety (said vs. fancy) (details)
74.7157% 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 of the abandoned Tube station pulsed like a dying heartbeat. Detective Harlow Quinn stepped over the rusted metal grates, her boots crunching on broken glass. The air smelled of damp earth and something older—something that clung to the walls like a second skin. A body lay sprawled in the shadows, its face pressed into the concrete. The victim’s throat had been slit, but not in the way Quinn expected. The cuts were precise, almost surgical, yet the blood pooled in a way that defied gravity. It didn’t drip. It *froze* mid-air, suspended in a thin, shimmering layer before settling back into the ground. “Quinn,” a voice cut through the silence. She turned just in time to see DS Morris—her partner, gone three years—standing in the dim glow of a flickering emergency light. His jaw was set, his uniform still crisp despite the chaos. “You’re late.” Quinn didn’t answer. She knelt, brushing her fingers over the frozen blood. It didn’t stick. It didn’t even *touch*. The skin beneath the cuts was unmarred, as if the blade had passed through something solid. “You’re not supposed to be here,” Morris said, his voice low. “The Market’s not for the police.” Quinn’s gaze flicked to the shadows where the body’s chest should have been. The lungs were gone. Not torn out, not cut away—*erased*. As if something had sucked them clean. “What the hell is this place?” Quinn demanded. Morris exhaled sharply, rubbing the back of his neck. “The Veil Market. They call it that because it’s not a place. It’s a *hole* in reality. And whatever’s down there… it doesn’t play by the rules.” A distant *clink* echoed from the far end of the station. Quinn’s instincts sharpened. She stood, her watch ticking against her wrist. The needle on the Veil Compass in her pocket—she’d found it in the victim’s pocket—was already twitching, though the light here was too dim to see it clearly. “You’re not supposed to be carrying that,” Morris said, his voice tight. Quinn didn’t look at him. “I found it in the body bag.” The clink came again, louder this time. A second figure stepped into the light—a woman with curly red hair and round glasses, her fingers twitching as she tucked a strand behind her ear. She wore a long coat, the sleeves rolled up to reveal hands stained with something dark. “Eva Kowalski,” Morris said, voice grim. “She’s been looking for this place for years.” Eva didn’t meet their eyes. “I found the token. The one that lets you in.” Quinn’s pulse spiked. Bone tokens. The Market’s entry requirement. “You’re not supposed to be here either.” Eva’s gaze flickered to the body. “Neither are you.” The ground beneath Quinn’s feet trembled. The air thickened, pressing in like a suffocating weight. The Veil Compass in her pocket *screamed*—a high, keening sound that made her teeth ache. Morris grabbed her arm. “We need to move.” Quinn didn’t hesitate. She lunged forward, her boots slamming into the concrete as she grabbed Eva’s wrist. The woman’s skin was cold, her breath shallow. “Let go,” Eva hissed, but Quinn didn’t stop. She dragged her toward the exit, the flickering lights casting long, shifting shadows. “What the hell is happening?” Morris demanded, his voice raw. Quinn didn’t answer. She could feel it—the pull, the *hunger*. The Market wasn’t just a place. It was a *thirst*. And whatever had taken the victim’s lungs was still down there, waiting. The station doors groaned open, the world outside a blur of grays and blues. Quinn didn’t look back. She didn’t have to. The truth was in the way the blood didn’t drip. It didn’t *belong*.
created_at"2026-02-20T19:30:31.175Z" 2/20/2026, 7:30:31 PM
model"mistralai/ministral-3b-2512"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency210
moderation_latency(null)
generation_time2641
tokens_prompt1149
tokens_completion993
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"
usage0.0001933
router(null)
provider_responses
0
endpoint_id"b9f6828f-aef9-498a-91f5-6816fbf72420"
id"5d4e3f8200384d53bce32cede44bb3d3"
is_byokfalse
latency210
model_permaslug"mistralai/ministral-3b-2512"
provider_name"Mistral"
status200
api_type"completions"
id"gen-1771615831-TYLEJnAmM2FA0f9HiwBM"
upstream_id"5d4e3f8200384d53bce32cede44bb3d3"
total_cost0.0001933
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
totalTags6
adverbTagCount0
adverbTags(empty)
dialogueSentences16
tagDensity0.375
leniency0.75
rawRatio0
effectiveRatio0
91.94% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount620
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)
27.42% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount620
totalAiIsms9
found
0
word"pulsed"
count1
1
word"silence"
count1
2
word"flicked"
count1
3
word"echoed"
count1
4
word"pulse"
count1
5
word"flickered"
count1
6
word"trembled"
count1
7
word"weight"
count1
8
word"could feel"
count1
highlights
0"pulsed"
1"silence"
2"flicked"
3"echoed"
4"pulse"
5"flickered"
6"trembled"
7"weight"
8"could feel"
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
narrationSentences58
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences58
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences67
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen30
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans9
markdownWords9
totalWords612
ratio0.015
matches
0"froze"
1"touch"
2"erased"
3"hole"
4"clink"
5"screamed"
6"hunger"
7"thirst"
8"belong"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions7
unquotedAttributions0
matches(empty)
22.30% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions32
wordCount509
uniqueNames8
maxNameDensity2.55
worstName"Quinn"
maxWindowNameDensity3
worstWindowName"Quinn"
discoveredNames
Tube1
Harlow1
Quinn13
Morris7
Veil2
Compass2
Eva4
Market2
persons
0"Harlow"
1"Quinn"
2"Morris"
3"Eva"
4"Market"
places(empty)
globalScore0.223
windowScore0.667
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences35
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount612
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences67
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs23
mean26.61
std15.17
cv0.57
sampleLengths
046
160
242
335
417
530
68
736
850
912
1012
1149
1214
1315
1416
159
1630
178
1825
1921
2010
2132
2235
93.16% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences58
matches
0"was unmarred"
1"were gone"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs93
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount9
semicolonCount0
flaggedSentences7
totalSentences67
ratio0.104
matches
0"The air smelled of damp earth and something older—something that clung to the walls like a second skin."
1"She turned just in time to see DS Morris—her partner, gone three years—standing in the dim glow of a flickering emergency light."
2"Not torn out, not cut away—*erased*."
3"The needle on the Veil Compass in her pocket—she’d found it in the victim’s pocket—was already twitching, though the light here was too dim to see it clearly."
4"A second figure stepped into the light—a woman with curly red hair and round glasses, her fingers twitching as she tucked a strand behind her ear."
5"The Veil Compass in her pocket *screamed*—a high, keening sound that made her teeth ache."
6"She could feel it—the pull, the *hunger*."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount517
adjectiveStacks0
stackExamples(empty)
adverbCount11
adverbRatio0.02127659574468085
lyAdverbCount3
lyAdverbRatio0.005802707930367505
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences67
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences67
mean9.13
std5.96
cv0.652
sampleLengths
013
115
218
313
413
516
63
715
87
922
1011
112
123
139
143
154
1616
1711
186
1913
204
216
227
238
249
2527
2611
273
288
2928
3012
315
327
337
3426
3516
366
378
385
3910
403
412
424
437
446
453
466
479
4815
494
42.54% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats5
diversityRatio0.2835820895522388
totalSentences67
uniqueOpeners19
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences56
matches(empty)
ratio0
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount15
totalSentences56
matches
0"It didn’t drip."
1"It *froze* mid-air, suspended in"
2"She turned just in time"
3"His jaw was set, his"
4"She knelt, brushing her fingers"
5"It didn’t stick."
6"It didn’t even *touch*."
7"She stood, her watch ticking"
8"She wore a long coat,"
9"She lunged forward, her boots"
10"She dragged her toward the"
11"She could feel it—the pull,"
12"It was a *thirst*."
13"She didn’t have to."
14"It didn’t *belong*."
ratio0.268
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount53
totalSentences56
matches
0"The flickering neon of the"
1"Detective Harlow Quinn stepped over"
2"The air smelled of damp"
3"A body lay sprawled in"
4"The victim’s throat had been"
5"The cuts were precise, almost"
6"It didn’t drip."
7"It *froze* mid-air, suspended in"
8"a voice cut through the"
9"She turned just in time"
10"His jaw was set, his"
11"Quinn didn’t answer."
12"She knelt, brushing her fingers"
13"It didn’t stick."
14"It didn’t even *touch*."
15"The skin beneath the cuts"
16"Morris said, his voice low"
17"Quinn’s gaze flicked to the"
18"The lungs were gone."
19"Morris exhaled sharply, rubbing the"
ratio0.946
89.29% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences56
matches
0"As if something had sucked"
ratio0.018
74.83% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences21
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 in her pocket *screamed*—a high, keening sound that made her teeth ache."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount4
matches
0"Morris said, his voice low"
1"Morris said, his voice tight"
2"Morris said, voice grim"
3"Morris demanded, his voice raw"
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags6
fancyCount3
fancyTags
0"Quinn demanded (demand)"
1"Eva hissed (hiss)"
2"Morris demanded (demand)"
dialogueSentences16
tagDensity0.375
leniency0.75
rawRatio0.5
effectiveRatio0.375
74.7157%