Run: 2026-02-20-01KHY7ZKGX79ZET5JEE53PEZ2P

Run Details

Model:
Ministral 3 3B
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
2.8s
Cost:
$0.000189
Provider:
Mistral

Evaluation summary

Score Evaluator
Details Link
100.00% 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)
21.74% 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)
19.85% 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)
53.03% Sentence opener variety (details)
70.92% 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)
100.00% Technical jargon density (details)
0.00% Useless dialogue additions (details)
59.09% Dialogue tag variety (said vs. fancy) (details)
77.2045% 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. “You’re sure this is where it happened?” DS Morris’s voice cut through the silence, sharp as a blade. He stood near the entrance, his breath misting in the cold. His jacket was still damp, the sleeves rolled up to his elbows, fingers twitching toward the holster at his side. Quinn didn’t answer. She knelt beside the body, her gloved fingers brushing the back of a skull. The teeth were missing, but the jawbone still held the imprint of a mouth that hadn’t been meant to be. The skin around it was too pale, too *wrong*—like something had been drawn across it before the killer struck. “Morris,” she murmured, “you ever see a face like that before?” Morris exhaled through his nose, rubbing his temples. “No. But I’ve seen worse.” A low hum vibrated through the station, deep beneath the concrete. Quinn’s watch—her worn leather strap—ticked faster. The needle on her wrist didn’t move, but the air did. The shadows stretched unnaturally, pooling around the body like ink in water. “You hear that?” Quinn asked. Morris’s eyes flicked toward the ceiling. “What?” “That’s not the station’s ventilation.” A voice, thin and cracked, slithered from the darkness. *“You shouldn’t be here.”* Eva Kowalski stepped into the light, her curly red hair tangled around her freckled face. She carried a satchel, the leather worn smooth by years of use. Her glasses reflected the dim glow of the station’s emergency lights, but her green eyes were sharp, assessing. “Detective Quinn,” she said, voice steady. “I was just leaving.” Quinn didn’t look away. “You’re in the wrong place, Eva.” Morris shifted, his grip tightening on his gun. “What the hell is going on?” Eva’s fingers twitched toward the satchel. “I was researching something. Nothing to do with you.” “Then why are you here?” Quinn demanded. Eva’s gaze flicked to the body. “Because the Veil Market moved here.” The words hung between them, heavy. Quinn’s jaw tightened. “You’re talking about the Market.” “Yes.” Eva’s voice dropped. “They’re selling things that shouldn’t exist. And the last thing they sold was a man.” Morris’s breath hitched. “You’re saying this wasn’t a homicide.” Quinn’s fingers dug into the corpse’s shoulder. “No. It’s worse.” A rustle came from the shadows. The hum grew louder, vibrating through Quinn’s bones. The brass compass in her pocket—*the Veil Compass*—pulled against her palm, the needle spinning erratically. “What’s that?” Morris asked, voice low. Quinn didn’t answer. She just stared at the compass, at the sigils etched into its face, at the way the light bent around it like a mirage. Then the station trembled. The walls groaned, the ceiling above them splitting open. Something dark and shifting spilled into the station, a swarm of shadows that moved without sound, without form. The air turned thick, suffocating. Eva’s voice was a whisper. “They’re here.” Morris grabbed Quinn’s arm, his grip iron. “We need to go.” Quinn didn’t move. The shadows coiled around the body, wrapping around it like a second skin. The teeth were back in place now, sharp and jagged, but the jawbone was wrong—too thin, too *wrong*. And then the compass lit up. Not with light. With *pain*.
created_at"2026-02-20T19:21:16.585Z" 2/20/2026, 7:21:16 PM
model"mistralai/ministral-3b-2512"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency206
moderation_latency(null)
generation_time2372
tokens_prompt1149
tokens_completion982
native_tokens_prompt1062
native_tokens_completion823
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"
usage0.0001885
router(null)
provider_responses
0
endpoint_id"b9f6828f-aef9-498a-91f5-6816fbf72420"
id"7ca3083ce1e4462e94faca28ce7665de"
is_byokfalse
latency206
model_permaslug"mistralai/ministral-3b-2512"
provider_name"Mistral"
status200
api_type"completions"
id"gen-1771615276-0Or5EvirhdFxHWH2cPMR"
upstream_id"7ca3083ce1e4462e94faca28ce7665de"
total_cost0.0001885
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)
dialogueSentences22
tagDensity0.273
leniency0.545
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount575
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)
21.74% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount575
totalAiIsms9
found
0
word"pulsed"
count1
1
word"silence"
count1
2
word"vibrated"
count1
3
word"flicked"
count2
4
word"the last thing"
count1
5
word"etched"
count1
6
word"trembled"
count1
7
word"whisper"
count1
highlights
0"pulsed"
1"silence"
2"vibrated"
3"flicked"
4"the last thing"
5"etched"
6"trembled"
7"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
narrationSentences51
matches(empty)
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)
analyzedSentences66
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen24
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans5
markdownWords10
totalWords571
ratio0.018
matches
0"wrong"
1"“You shouldn’t be here.”"
2"the Veil Compass"
3"wrong"
4"pain"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions6
unquotedAttributions0
matches(empty)
19.85% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions28
wordCount461
uniqueNames7
maxNameDensity2.6
worstName"Quinn"
maxWindowNameDensity4
worstWindowName"Quinn"
discoveredNames
Tube1
Harlow1
Quinn12
Morris7
Kowalski1
Eva5
Veil1
persons
0"Harlow"
1"Quinn"
2"Morris"
3"Kowalski"
4"Eva"
places(empty)
globalScore0.198
windowScore0.333
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences34
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount571
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences66
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs32
mean17.84
std15.02
cv0.842
sampleLengths
046
149
256
311
413
540
65
77
85
913
1045
1110
1210
1314
1415
157
1612
1714
1819
199
2010
2129
226
2327
244
2532
267
2711
2834
296
303
312
91.50% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences51
matches
0"been meant"
1"been drawn"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount1
totalVerbs81
matches
0"were missing"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount7
semicolonCount0
flaggedSentences5
totalSentences66
ratio0.076
matches
0"The air smelled of damp earth and something older—something that clung to the walls like a second skin."
1"The skin around it was too pale, too *wrong*—like something had been drawn across it before the killer struck."
2"Quinn’s watch—her worn leather strap—ticked faster."
3"The brass compass in her pocket—*the Veil Compass*—pulled against her palm, the needle spinning erratically."
4"The teeth were back in place now, sharp and jagged, but the jawbone was wrong—too thin, too *wrong*."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount465
adjectiveStacks0
stackExamples(empty)
adverbCount17
adverbRatio0.03655913978494624
lyAdverbCount3
lyAdverbRatio0.0064516129032258064
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences66
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences66
mean8.65
std5.49
cv0.635
sampleLengths
013
115
218
318
411
520
63
714
820
919
1011
118
125
1311
146
1511
1612
175
186
191
205
219
224
2315
2412
2518
266
274
284
296
308
316
326
339
347
356
366
376
383
395
404
4115
423
436
447
453
466
478
4815
496
53.03% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats5
diversityRatio0.36363636363636365
totalSentences66
uniqueOpeners24
70.92% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences47
matches
0"Then the station trembled."
ratio0.021
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount7
totalSentences47
matches
0"He stood near the entrance,"
1"His jacket was still damp,"
2"She knelt beside the body,"
3"She carried a satchel, the"
4"Her glasses reflected the dim"
5"she said, voice steady"
6"She just stared at the"
ratio0.149
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount44
totalSentences47
matches
0"The flickering neon of the"
1"Detective Harlow Quinn stepped over"
2"The air smelled of damp"
3"DS Morris’s voice cut through"
4"He stood near the entrance,"
5"His jacket was still damp,"
6"Quinn didn’t answer."
7"She knelt beside the body,"
8"The teeth were missing, but"
9"The skin around it was"
10"Morris exhaled through his nose,"
11"A low hum vibrated through"
12"Quinn’s watch—her worn leather strap—ticked"
13"The needle on her wrist"
14"The shadows stretched unnaturally, pooling"
15"Morris’s eyes flicked toward the"
16"A voice, thin and cracked,"
17"Eva Kowalski stepped into the"
18"She carried a satchel, the"
19"Her glasses reflected the dim"
ratio0.936
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences47
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences19
technicalSentenceCount1
matches
0"The air smelled of damp earth and something older—something that clung to the walls like a second skin."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount2
matches
0"she said, voice steady"
1"Morris asked, voice low"
59.09% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags5
fancyCount2
fancyTags
0"she murmured (murmur)"
1"Quinn demanded (demand)"
dialogueSentences22
tagDensity0.227
leniency0.455
rawRatio0.4
effectiveRatio0.182
77.2045%