Run: 2026-02-20-01KHXPEXM70B47K3XH81NPYTC5

Run Details

Model:
Mistral Large 3
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
15.8s
Cost:
$0.001682
Provider:
Mistral

Evaluation summary

Score Evaluator
Details Link
100.00% Adverbs in dialogue tags (details)
90.65% AI-ism adverb frequency (details)
100.00% AI-ism character names (details)
100.00% AI-ism location names (details)
62.62% 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)
8.93% 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)
85.21% Passive voice overuse (details)
100.00% Past progressive (was/were + -ing) overuse (details)
32.97% Em-dash & semicolon overuse (details)
100.00% Purple prose (modifier overload) (details)
100.00% Repeated phrase echo (details)
100.00% Sentence length variance (details)
83.33% 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)
0.00% Subordinate conjunction sentence starts (details)
100.00% Technical jargon density (details)
100.00% Useless dialogue additions (details)
100.00% Dialogue tag variety (said vs. fancy) (details)
82.1240% 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 smelled of damp concrete and rust. Quinn stepped over the police tape, her boots clicking against the cracked tiles. The beam of her torch cut through the gloom, illuminating the graffiti-scarred walls and the skeletal remains of turnstiles long since stripped for scrap. "Bit off the beaten path, even for you, Quinn." DS Carter stood near the edge of the platform, arms crossed, his breath fogging in the cold air. He nodded toward the body sprawled across the tracks. "Male, mid-thirties. No ID, no wallet. Looks like he took a header onto the live rail." Quinn crouched, shining her light over the corpse. The man’s face was frozen in a rictus of surprise, his fingers curled into the gravel like he’d tried to claw his way back up. His clothes were expensive—tailored wool coat, leather gloves—but his shoes were scuffed, the soles worn thin. "Time of death?" she asked. "ME’s guess? Between midnight and two. No signs of struggle, no defensive wounds. Tox screen’s clean." Carter shrugged. "Open-and-shut. Jumped or fell. Probably another sad bastard who couldn’t take it anymore." Quinn’s torch flickered over the third rail. The metal gleamed, untouched by blood or scorch marks. She stood, brushing dust from her knees. "Where’s the burn?" Carter frowned. "What?" "If he hit the live rail, there’d be burns. On his clothes, his skin. Electrical damage." She stepped closer, nudging the man’s sleeve with the toe of her boot. The fabric didn’t so much as singe. "This doesn’t add up." Carter exhaled through his nose. "Maybe he didn’t make contact. Maybe he just—" "Then how’d he die?" Quinn’s gaze drifted to the tunnel mouth, where the darkness swallowed the tracks whole. "And why here? This station’s been closed for twenty years. No cameras, no witnesses. Convenient, isn’t it?" Carter rubbed the back of his neck. "You’re reaching. Guy’s probably just some city worker who had a bad day. Happens." Quinn ignored him, stepping down onto the tracks. The gravel crunched underfoot as she moved toward the body. Something glinted near the man’s outstretched hand—a small brass compass, its face etched with strange symbols. She picked it up, turning it over in her palm. The needle spun lazily, then stilled, pointing toward the tunnel. Carter’s radio crackled. "DS Carter, you copy? We’ve got another one. Same MO, different location." Quinn’s fingers tightened around the compass. "Where?" "Camden. Another abandoned station." She pocketed the compass. "That’s two in one night. Both in places no one should be." Carter’s jaw worked. "Coincidence." "Bullshit." Quinn climbed back onto the platform. "This isn’t a suicide. It’s a pattern. And I want to know who’s behind it." Carter stepped in front of her, blocking her path. "You’re obsessed. Morris’s case messed you up, and now you’re seeing ghosts where there’s just sad bastards with bad luck." Quinn’s eyes locked onto his. "Then explain the compass." Carter opened his mouth, then shut it. He didn’t have an answer. Quinn pushed past him, heading for the exit. "I’m going to Camden. You can either help me or get out of my way." The tunnel swallowed her footsteps as she disappeared into the dark.
created_at"2026-02-20T14:15:04.082Z" 2/20/2026, 2:15:04 PM
model"mistralai/mistral-large-2512" 1/1/2512, 12:00:00 AM
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency461
moderation_latency(null)
generation_time15737
tokens_prompt1149
tokens_completion866
native_tokens_prompt1062
native_tokens_completion767
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"
usage0.0016815
router(null)
provider_responses
0
endpoint_id"fa718841-07ea-4b7e-b8a3-6069545c7e6a"
id"d4a9675b85d1483ca304b0a36a6de57a"
is_byokfalse
latency461
model_permaslug"mistralai/mistral-large-2512" 1/1/2512, 12:00:00 AM
provider_name"Mistral"
status200
api_type"completions"
id"gen-1771596904-GXbx44l3WjvW3I5uOsFX"
upstream_id"d4a9675b85d1483ca304b0a36a6de57a"
total_cost0.0016815
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
adverbTagCount1
adverbTags
0"Quinn climbed back [back]"
dialogueSentences23
tagDensity0.261
leniency0.522
rawRatio0.167
effectiveRatio0.087
90.65% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount535
totalAiIsmAdverbs1
found
0
adverb"lazily"
count1
highlights
0"lazily"
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)
62.62% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount535
totalAiIsms4
found
0
word"gloom"
count1
1
word"flickered"
count1
2
word"etched"
count1
3
word"footsteps"
count1
highlights
0"gloom"
1"flickered"
2"etched"
3"footsteps"
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
narrationSentences35
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount1
narrationSentences35
filterMatches(empty)
hedgeMatches
0"tried to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences52
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen29
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords528
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions3
unquotedAttributions0
matches(empty)
8.93% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions19
wordCount319
uniqueNames3
maxNameDensity2.82
worstName"Carter"
maxWindowNameDensity4
worstWindowName"Carter"
discoveredNames
Tube1
Carter9
Quinn9
persons
0"Carter"
1"Quinn"
places(empty)
globalScore0.089
windowScore0.333
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences26
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount528
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences52
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs23
mean22.96
std16.12
cv0.702
sampleLengths
047
152
249
35
431
526
63
740
813
935
1021
1154
1215
137
144
1516
164
1722
1829
199
2012
2123
2211
85.21% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences35
matches
0"was frozen"
1"were scuffed"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs62
matches(empty)
32.97% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount3
semicolonCount0
flaggedSentences2
totalSentences52
ratio0.038
matches
0"His clothes were expensive—tailored wool coat, leather gloves—but his shoes were scuffed, the soles worn thin."
1"Something glinted near the man’s outstretched hand—a small brass compass, its face etched with strange symbols."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount323
adjectiveStacks0
stackExamples(empty)
adverbCount8
adverbRatio0.02476780185758514
lyAdverbCount1
lyAdverbRatio0.0030959752321981426
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences52
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences52
mean10.15
std6.7
cv0.66
sampleLengths
010
113
224
327
49
516
68
725
816
95
1018
1113
127
139
147
153
162
171
1829
197
204
215
228
2318
2417
257
2614
278
2810
2916
3010
3110
323
3312
346
351
364
374
3812
393
401
417
4215
439
4420
455
464
477
485
498
83.33% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats0
diversityRatio0.5
totalSentences52
uniqueOpeners26
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences32
matches(empty)
ratio0
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount7
totalSentences32
matches
0"He nodded toward the body"
1"His clothes were expensive—tailored wool"
2"She stood, brushing dust from"
3"She stepped closer, nudging the"
4"She picked it up, turning"
5"She pocketed the compass."
6"He didn’t have an answer."
ratio0.219
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount32
totalSentences32
matches
0"The abandoned Tube station smelled"
1"Quinn stepped over the police"
2"The beam of her torch"
3"DS Carter stood near the"
4"He nodded toward the body"
5"Quinn crouched, shining her light"
6"The man’s face was frozen"
7"His clothes were expensive—tailored wool"
8"Quinn’s torch flickered over the"
9"The metal gleamed, untouched by"
10"She stood, brushing dust from"
11"She stepped closer, nudging the"
12"The fabric didn’t so much"
13"Carter exhaled through his nose."
14"Quinn’s gaze drifted to the"
15"Carter rubbed the back of"
16"Quinn ignored him, stepping down"
17"The gravel crunched underfoot as"
18"Something glinted near the man’s"
19"She picked it up, turning"
ratio1
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences32
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences10
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags1
fancyCount0
fancyTags(empty)
dialogueSentences23
tagDensity0.043
leniency0.087
rawRatio0
effectiveRatio0
82.1240%