Run: 2026-07-25-01KYCSDMHSZG301K1CJRWM4FG6

Run Details

Model:
Gemini 3.5 Flash Lite (Reasoning, Minimal)
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
4.5s
Cost:
$0.002094
Provider:
Google AI Studio

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)
23.95% 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)
8.25% 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)
95.92% Sentence opener variety (details)
0.00% Adverb-first sentence starts (details)
100.00% Pronoun-first sentence starts (details)
45.71% Subject-first sentence starts (details)
0.00% Subordinate conjunction sentence starts (details)
100.00% Technical jargon density (details)
41.67% Useless dialogue additions (details)
38.89% Dialogue tag variety (said vs. fancy) (details)
81.8130% 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
Damp brick walls weep stagnant water onto the abandoned platform beneath Camden. Detective Harlow Quinn steps over rusted iron rails, boots crunching on glass shards. The Metropolitan Police tape stretches taut across the entrance of the defunct underground station. A flashlight beam cuts through the gloom, dancing across chalk symbols freshly scrawled on the curved station wall. "Dead center of the platform. No forced entry through the street grates." Harlow keeps her eyes fixed on the pavement, ignoring the sergeant. She taps the worn leather watch on her left wrist. Eighteen years on the force taught her concrete floors whisper truths the living ignore. "Tramps use this line for shelter," the sergeant offers, pointing his heavy-duty lantern toward a heap of rotting canvas in the corner. "Overdose. Simple as that. We find junkies down here every Tuesday." Harlow kneels beside the chalk markings. The circle measures exactly six feet across, geometric perfection drawn with powdered bone. Junkies do not carry ritualistic reagents. She traces a gloved finger along the inner edge of the sigil. Residue flakes off, smelling faintly of ozone and old copper. "Junkies leave needles and vomit," Harlow says, standing up to tower over the junior officer. "Not intricate wards designed to trap ambient energy." The sergeant crosses his arms, shifting his weight onto his heels. "The coroner clears the body in an hour. Pathologist smells like cheap gin, sure, but he knows a standard cardiac arrest when he sees one." Harlow bends closer to the victim slumped against the tiled wall. The dead man wears a tweed jacket, pockets turned inside out. No wallet. No keys. Yet a small brass compass with a verdigris patina sits untouched in the palm of his open hand. She lifts the instrument. The needle spins wildly, ignoring true north, vibrating against the glass cover etched with protective sigils. "Standard cardiac arrests do not leave victims holding esoteric artifacts," Harlow mutters. "Suicide pact bullshit. Kids playing occult games in the dark." Harlow ignores the dismissal. She examines the victim's fingernails. Caked in subterranean silt, but the cuticles bleed fresh crimson. Heart attacks stop circulation instantly. Fresh blood defies post-mortem biology. She tracks a smear of dark fluid leading away from the body toward the yawning mouth of the dark tunnel. "Look at the dust on the rails," Harlow points her mag-light down the tracks. "Disturbed only in one direction. Someone dragged him here from the deep tunnels." "The platform doors rusted shut twenty years ago." "Someone unlocked them." Harlow traces the edge of the iron gate. Fresh file marks gleam silver against black oxidation. The heavy padlock rests on the wooden tie beneath the platform, unclicked, its mechanism jammed with lead shot. "Professional work," Harlow notes, rising smoothly from her crouch. "Lock doesn't pick. It gets disabled." "Or rusted through." "Feel the metal." The sergeant hesitates, then reaches out a gloved thumb to brush the padlock. He pulls his hand back fast. "Warm," the sergeant whispers, eyes widening in the dim beam. "Friction from a thermal drill," Harlow says, sliding her gaze down the empty subterranean corridor where the compass needle pins itself rigidly toward the black void.
created_at"2026-07-25T14:03:46.184Z" 7/25/2026, 2:03:46 PM
model"google/gemini-3.5-flash-lite-20260721"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency405
moderation_latency(null)
generation_time4185
tokens_prompt1112
tokens_completion847
native_tokens_prompt1073
native_tokens_completion709
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"
usage0.0020944
router(null)
provider_responses
0
endpoint_id"6bd8f433-79e1-416c-b407-1772eb796c9a"
id"QsJkatSSGYLGjMcP1-XhsQ0"
is_byokfalse
latency405
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-1784988226-mh4GK0Q3J6ELPwkIGfhe"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1784988226-Ab6NMTdVCreiyHCF3R00"
upstream_id"QsJkatSSGYLGjMcP1-XhsQ0"
total_cost0.0020944
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
totalTags6
adverbTagCount0
adverbTags(empty)
dialogueSentences18
tagDensity0.333
leniency0.667
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount526
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)
23.95% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount526
totalAiIsms8
found
0
word"gloom"
count1
1
word"dancing"
count1
2
word"whisper"
count1
3
word"intricate"
count1
4
word"weight"
count1
5
word"standard"
count2
6
word"etched"
count1
highlights
0"gloom"
1"dancing"
2"whisper"
3"intricate"
4"weight"
5"standard"
6"etched"
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
narrationSentences38
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences38
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences49
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen26
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords526
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions2
unquotedAttributions0
matches(empty)
8.25% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions15
wordCount388
uniqueNames5
maxNameDensity2.84
worstName"Harlow"
maxWindowNameDensity3.5
worstWindowName"Harlow"
discoveredNames
Camden1
Harlow11
Quinn1
Metropolitan1
Police1
persons
0"Harlow"
1"Quinn"
places(empty)
globalScore0.082
windowScore0.5
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences30
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount526
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences49
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs22
mean23.91
std16.29
cv0.681
sampleLengths
039
118
212
335
433
547
623
736
864
912
1010
1149
1227
138
143
1534
1615
173
183
1919
2010
2126
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences38
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs67
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences49
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount391
adjectiveStacks0
stackExamples(empty)
adverbCount9
adverbRatio0.023017902813299233
lyAdverbCount7
lyAdverbRatio0.017902813299232736
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences49
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences49
mean10.73
std5.64
cv0.526
sampleLengths
012
113
214
318
412
511
610
714
822
911
106
1113
126
1312
1410
1515
168
1711
1825
1911
2011
212
222
2318
244
2516
2612
2710
284
295
3010
315
325
3320
3414
3513
368
373
388
398
4018
419
426
433
443
4513
466
4710
4826
95.92% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats2
diversityRatio0.6122448979591837
totalSentences49
uniqueOpeners30
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences35
matches(empty)
ratio0
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount6
totalSentences35
matches
0"She taps the worn leather"
1"She traces a gloved finger"
2"She lifts the instrument."
3"She examines the victim's fingernails."
4"She tracks a smear of"
5"He pulls his hand back"
ratio0.171
45.71% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount29
totalSentences35
matches
0"Detective Harlow Quinn steps over"
1"The Metropolitan Police tape stretches"
2"A flashlight beam cuts through"
3"Harlow keeps her eyes fixed"
4"She taps the worn leather"
5"the sergeant offers, pointing his"
6"Harlow kneels beside the chalk"
7"The circle measures exactly six"
8"Junkies do not carry ritualistic"
9"She traces a gloved finger"
10"Residue flakes off, smelling faintly"
11"Harlow says, standing up to"
12"The sergeant crosses his arms,"
13"Harlow bends closer to the"
14"The dead man wears a"
15"She lifts the instrument."
16"The needle spins wildly, ignoring"
17"Harlow ignores the dismissal."
18"She examines the victim's fingernails."
19"Heart attacks stop circulation instantly."
ratio0.829
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences35
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences19
technicalSentenceCount0
matches(empty)
41.67% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount1
matches
0"the sergeant whispers, eyes widening in the dim beam"
38.89% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags4
fancyCount2
fancyTags
0"Harlow notes (harlow note)"
1"the sergeant whispers (whisper)"
dialogueSentences18
tagDensity0.222
leniency0.444
rawRatio0.5
effectiveRatio0.222
81.8130%