Run: 2026-02-17-01KHNFNA41XWK76R4S01JMEQ26

Run Details

Model:
Arcee AI: Trinity Large (Preview)
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
21.0s
Cost:
$0.000000
Provider:
Arcee AI

Evaluation summary

Score Evaluator
Details Link
73.08% Adverbs in dialogue tags (details)
86.52% AI-ism adverb frequency (details)
80.00% AI-ism character names (details)
100.00% AI-ism location names (details)
32.61% 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)
4.01% Name drop frequency (details)
30.95% 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)
100.00% Passive voice overuse (details)
100.00% Past progressive (was/were + -ing) overuse (details)
0.00% Em-dash & semicolon overuse (details)
94.00% Purple prose (modifier overload) (details)
100.00% Repeated phrase echo (details)
100.00% Sentence length variance (details)
100.00% Sentence opener variety (details)
0.00% Adverb-first sentence starts (details)
91.43% Pronoun-first sentence starts (details)
31.43% Subject-first sentence starts (details)
0.00% Subordinate conjunction sentence starts (details)
100.00% Technical jargon density (details)
100.00% Useless dialogue additions (details)
0.00% Dialogue tag variety (said vs. fancy) (details)
74.1346% Overall

Model input

System
You are an expert novelist with a gift for vivid, immersive prose. You write in tight third-person limited point of view with a strong narrative voice. Your prose is clean, precise, and engaging — you favor strong verbs, concrete details, and natural-sounding dialogue. You will be given a story bible (codex) containing canonical details about characters, locations, items, and lore. Use these details to ground your writing in the established world. Stay consistent with the codex. Write only the prose of the scene. Do not include titles, chapter headings, markdown formatting, or any commentary before or after the scene.
User/Human
<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> 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.

Model response

AI
The abandoned Tube station smelled of damp concrete and something else—something metallic and sharp that made Harlow's nose twitch. She clicked on her flashlight, the beam cutting through the gloom. Graffiti covered the walls in layers, decades of urban hieroglyphics telling stories she didn't have time to decipher. "Detective Quinn," called a voice from the darkness. "Down here." Harlow followed the sound, her footsteps echoing on the platform. She found DS Patel crouched beside what looked like a body, though it was hard to tell in the poor light. "Found her about twenty minutes ago," Patel said, straightening up. "No ID, no witnesses. Looks like a mugging gone wrong, maybe?" Harlow crouched beside the body. The woman was young, mid-twenties, with curly red hair spread out on the grimy tiles. Her eyes were open, staring at nothing. There was a dark stain spreading across her chest. "No wallet, no phone," Harlow noted, running her eyes over the scene. "But look at this." She pointed to the woman's left hand. A leather satchel lay half-open beside it, books spilling out. Not just any books—ancient-looking tomes with strange symbols on their covers. "That's not something muggers usually leave behind," Harlow said. Patel frowned. "Maybe they got spooked? Or maybe it's not about robbery at all." Harlow stood, scanning the platform. Something about this scene felt wrong. The position of the body, the way the blood had pooled, the books scattered just so. It was almost... staged. "Check the exits," she ordered. "See if anyone saw or heard anything. And get forensics down here. I want every inch of this place examined." As Patel moved off to carry out her instructions, Harlow's phone buzzed. A text from an unknown number: "The compass points north, but the truth lies east. - E" She frowned, typing back: "Who is this?" The reply came instantly: "Someone who knows what really happened here." Harlow's heart rate picked up. She pocketed her phone and turned back to the body, her mind racing. The compass. She'd heard rumors of such a thing—a device that could detect supernatural energy. And east... that would take her to Camden. She needed to get to the Veil Market. Now.
created_at"2026-02-17T09:42:39.793596+00:00" 2/17/2026, 9:42:39 AM
model"arcee-ai/trinity-large-preview:free"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency198
moderation_latency(null)
generation_time20851
tokens_prompt923
tokens_completion578
native_tokens_prompt810
native_tokens_completion476
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
router(null)
provider_responses
0
id"chatcmpl-8358e9ec9851197a"
status200
is_byokfalse
latency21
endpoint_id"b9d81865-ce9a-432a-9cd5-0d9be55e7cb5"
provider_name"Arcee AI"
model_permaslug"arcee-ai/trinity-large-preview"
api_type"completions"
id"gen-1771321337-sl60FDuENuMiYwRkTddD"
upstream_id"chatcmpl-8358e9ec9851197a"
total_cost0
cache_discount(null)
upstream_inference_cost0
provider_name"Arcee AI"

Evaluation details

Result Evaluator Details Meta Data
73.08% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags6
adverbTagCount1
adverbTags
0"The reply came instantly: [instantly]"
dialogueSentences13
tagDensity0.462
leniency0.923
rawRatio0.167
effectiveRatio0.154
86.52% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount371
totalAiIsmAdverbs1
found
0
adverb"really"
count1
highlights
0"really"
80.00% AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions(empty)
found
0"Patel"
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
32.61% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount371
totalAiIsms5
found
0
word"gloom"
count1
1
word"footsteps"
count1
2
word"echoing"
count1
3
word"scanning"
count1
4
word"racing"
count1
highlights
0"gloom"
1"footsteps"
2"echoing"
3"scanning"
4"racing"
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
hedgeCount0
narrationSentences35
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences40
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen21
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords366
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions6
unquotedAttributions0
matches(empty)
4.01% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions16
wordCount274
uniqueNames6
maxNameDensity2.92
worstName"Harlow"
maxWindowNameDensity3.5
worstWindowName"Harlow"
discoveredNames
Tube1
Harlow8
Patel4
Camden1
Veil1
Market1
persons
0"Harlow"
1"Patel"
places
0"Camden"
1"Veil"
globalScore0.04
windowScore0.5
30.95% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences21
glossingSentenceCount1
matches
0"looked like a body, though it was hard to"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount366
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences40
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs16
mean22.88
std12.26
cv0.536
sampleLengths
048
110
231
321
436
516
628
79
814
931
1025
1129
127
1311
1441
159
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences35
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs54
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount3
semicolonCount0
flaggedSentences3
totalSentences40
ratio0.075
matches
0"The abandoned Tube station smelled of damp concrete and something else—something metallic and sharp that made Harlow's nose twitch."
1"Not just any books—ancient-looking tomes with strange symbols on their covers."
2"She'd heard rumors of such a thing—a device that could detect supernatural energy."
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount280
adjectiveStacks1
stackExamples
0"lay half-open beside it,"
adverbCount8
adverbRatio0.02857142857142857
lyAdverbCount3
lyAdverbRatio0.010714285714285714
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences40
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences40
mean9.15
std5.37
cv0.587
sampleLengths
019
111
218
38
42
510
621
710
811
95
1015
117
129
1312
144
157
1610
1711
189
192
2012
215
226
2316
243
251
265
2720
2812
2917
307
3111
325
3313
342
3513
362
376
388
391
100.00% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats0
diversityRatio0.6
totalSentences40
uniqueOpeners24
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences28
matches(empty)
ratio0
91.43% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount9
totalSentences28
matches
0"She clicked on her flashlight,"
1"She found DS Patel crouched"
2"Her eyes were open, staring"
3"She pointed to the woman's"
4"It was almost..."
5"She frowned, typing back:"
6"She pocketed her phone and"
7"She'd heard rumors of such"
8"She needed to get to"
ratio0.321
31.43% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount24
totalSentences28
matches
0"The abandoned Tube station smelled"
1"She clicked on her flashlight,"
2"Graffiti covered the walls in"
3"Harlow followed the sound, her"
4"She found DS Patel crouched"
5"Patel said, straightening up"
6"Harlow crouched beside the body."
7"The woman was young, mid-twenties,"
8"Her eyes were open, staring"
9"Harlow noted, running her eyes"
10"She pointed to the woman's"
11"A leather satchel lay half-open"
12"Harlow stood, scanning the platform."
13"Something about this scene felt"
14"The position of the body,"
15"It was almost..."
16"A text from an unknown"
17"She frowned, typing back:"
18"The reply came instantly:"
19"Harlow's heart rate picked up."
ratio0.857
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences28
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences12
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount0
matches(empty)
0.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags4
fancyCount2
fancyTags
0"Harlow noted (note)"
1"she ordered (order)"
dialogueSentences13
tagDensity0.308
leniency0.615
rawRatio0.5
effectiveRatio0.308
74.1346%