Run: 2026-07-25-01KYCVY5FBP5QE1NQQJC63XZ40

Run Details

Model:
Gemini 3.5 Flash Lite (Reasoning)
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
3.5s
Cost:
$0.001759
Provider:
Google AI Studio

Evaluation summary

Score Evaluator
Details Link
100.00% Adverbs in dialogue tags (details)
88.40% AI-ism adverb frequency (details)
100.00% AI-ism character names (details)
100.00% AI-ism location names (details)
7.19% AI-ism word frequency (details)
100.00% Cliché density (details)
100.00% Emotion telling (show vs. tell) (details)
91.84% Filter word density (details)
100.00% Gibberish response detection (details)
100.00% Markdown formatting overuse (details)
100.00% Missing dialogue indicators (quotation marks) (details)
12.07% 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)
100.00% Passive voice overuse (details)
100.00% Past progressive (was/were + -ing) overuse (details)
100.00% Em-dash & semicolon overuse (details)
100.00% Purple prose (modifier overload) (details)
100.00% Repeated phrase echo (details)
100.00% Sentence length variance (details)
97.22% Sentence opener variety (details)
0.00% Adverb-first sentence starts (details)
100.00% Pronoun-first sentence starts (details)
36.92% Subject-first sentence starts (details)
0.00% Subordinate conjunction sentence starts (details)
91.84% Technical jargon density (details)
100.00% Useless dialogue additions (details)
73.08% Dialogue tag variety (said vs. fancy) (details)
83.2852% 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
Rain slicked the tiles of the abandoned Camden Tube station long before the stairs ended. Detective Harlow Quinn thumbed the worn leather watch on her left wrist, checking the time against the damp chill rising from the subterranean platform. Salt-and-pepper hair clung to her temples as she stepped past the police tape strung across the rusty iron turnstiles. Down here, the air tasted of copper and stagnant ballast water. Footsteps echoed off the curved brick ceiling ahead. The uniform crouching beside the bench lifted a silver flashlight. "Body was dropped right here, boss. Looks like a mugging gone south. Pockets turned inside out." Quinn approached the platform edge. Her sharp jaw tightened. She scanned the tracks where three rusting locomotives sat half-swallowed by darkness. "No blood on the gravel. None on the platform edge." "He bled internally," the officer offered, standing up and dusting soot from his knees. "Coroner will find a ruptured spleen or a cracked skull. Drunk tumbled down the stairs and crawled onto the bench." Quinn ignored the speculation. Her brown eyes tracked a peculiar crescent-shaped burn marring the wooden slats of the bench. It matched nothing in her eighteen years of homicide files. She reached out, hovering gloved fingers above the scorched wood. The air felt heavy, charged like the seconds before a summer storm. "Drunks don't leave geometric carbon traces," Quinn said. The officer crossed his arms, shaking his head. "Kids with lighters, then. Vandalism down in the tunnels. Happens every weekend." Quinn crouched lower. Beneath the bench lay a small brass compass with a patina of verdigris, its face etched with intricate protective sigils. The needle spun wildly, vibrating against the glass dome despite the stillness of the underground air. She lifted the instrument, turning it over in her palm. No serial numbers. No manufacturer stamps. "Kids don't carry Shade craftsmanship," Quinn muttered. "You lost me, Harlow. It's just brass junk dropped by a vagrant." "Look at the dust on the platform floor," Quinn pointed the flashlight beam in a wide arc around the bench. "Footprints lead in from the tracks, not the stairs. Nobody walked down here from the street." The officer squinted into the gloom of the tunnel. "Service tunnels connect to the Northern Line. Tramps use them to sleep out of the rain." "Tramps don't wear heavy boots with square heels," Quinn stood, stepping into the dust trail. The impressions cut deep into the soot, perfectly uniform, stopping abruptly beside the scorched bench as if the wearer simply dissolved into the damp air. "And they certainly don't vanish into solid brick walls."
created_at"2026-07-25T14:47:44.887Z" 7/25/2026, 2:47:44 PM
model"google/gemini-3.5-flash-lite-20260721"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency287
moderation_latency(null)
generation_time3340
tokens_prompt1112
tokens_completion680
native_tokens_prompt1073
native_tokens_completion575
native_tokens_completion_images0
native_tokens_reasoning0
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"STOP"
service_tier"default"
usage0.0017594
router(null)
provider_responses
0
endpoint_id"6bd8f433-79e1-416c-b407-1772eb796c9a"
id"kcxkavTVAZ-5sOIP6ejsgAo"
is_byokfalse
latency287
model_permaslug"google/gemini-3.5-flash-lite-20260721"
provider_name"Google AI Studio"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer(null)
request_id"req-1784990864-EqAkgSoJO5YFYfbH2IIu"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1784990864-fXINDccfTgwGye1gXRNX"
upstream_id"kcxkavTVAZ-5sOIP6ejsgAo"
total_cost0.0017594
cache_discount(null)
upstream_inference_cost0
provider_name"Google AI Studio"
response_cache_source_id(null)
data_region"global"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags5
adverbTagCount0
adverbTags(empty)
dialogueSentences13
tagDensity0.385
leniency0.769
rawRatio0
effectiveRatio0
88.40% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount431
totalAiIsmAdverbs1
found
0
adverb"perfectly"
count1
highlights
0"perfectly"
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)
7.19% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount431
totalAiIsms8
found
0
word"chill"
count1
1
word"footsteps"
count1
2
word"echoed"
count1
3
word"scanned"
count1
4
word"charged"
count1
5
word"etched"
count1
6
word"intricate"
count1
7
word"gloom"
count1
highlights
0"chill"
1"footsteps"
2"echoed"
3"scanned"
4"charged"
5"etched"
6"intricate"
7"gloom"
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
narrationSentences28
matches(empty)
91.84% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences28
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences36
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen25
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords431
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions2
unquotedAttributions0
matches(empty)
12.07% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions11
wordCount290
uniqueNames4
maxNameDensity2.76
worstName"Quinn"
maxWindowNameDensity3.5
worstWindowName"Quinn"
discoveredNames
Camden1
Tube1
Harlow1
Quinn8
persons
0"Harlow"
1"Quinn"
places(empty)
globalScore0.121
windowScore0.5
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences20
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount431
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences36
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs14
mean30.79
std18.81
cv0.611
sampleLengths
069
18
226
331
434
551
68
720
855
97
1012
1136
1225
1349
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences28
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs49
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences36
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount294
adjectiveStacks0
stackExamples(empty)
adverbCount4
adverbRatio0.013605442176870748
lyAdverbCount4
lyAdverbRatio0.013605442176870748
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences36
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences36
mean11.97
std5.73
cv0.478
sampleLengths
015
124
219
311
48
510
616
75
84
912
1010
1114
1220
134
1415
1510
1610
1712
188
198
2012
213
2220
2316
2410
253
263
277
2812
2920
3016
319
3216
3315
3425
359
97.22% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.6388888888888888
totalSentences36
uniqueOpeners23
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences26
matches(empty)
ratio0
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount6
totalSentences26
matches
0"Her sharp jaw tightened."
1"She scanned the tracks where"
2"Her brown eyes tracked a"
3"It matched nothing in her"
4"She reached out, hovering gloved"
5"She lifted the instrument, turning"
ratio0.231
36.92% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount22
totalSentences26
matches
0"Rain slicked the tiles of"
1"Detective Harlow Quinn thumbed the"
2"Salt-and-pepper hair clung to her"
3"Footsteps echoed off the curved"
4"The uniform crouching beside the"
5"Quinn approached the platform edge."
6"Her sharp jaw tightened."
7"She scanned the tracks where"
8"the officer offered, standing up"
9"Quinn ignored the speculation."
10"Her brown eyes tracked a"
11"It matched nothing in her"
12"She reached out, hovering gloved"
13"The air felt heavy, charged"
14"The officer crossed his arms,"
15"Quinn crouched lower."
16"The needle spun wildly, vibrating"
17"She lifted the instrument, turning"
18"Quinn pointed the flashlight beam"
19"The officer squinted into the"
ratio0.846
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences26
matches(empty)
ratio0
91.84% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences14
technicalSentenceCount1
matches
0"The impressions cut deep into the soot, perfectly uniform, stopping abruptly beside the scorched bench as if the wearer simply dissolved into the damp air."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags5
uselessAdditionCount0
matches(empty)
73.08% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount1
fancyTags
0"Quinn muttered (mutter)"
dialogueSentences13
tagDensity0.154
leniency0.308
rawRatio0.5
effectiveRatio0.154
83.2852%