NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHTXN35JD3HKNY5NYKRHAGD6
Run Details
Model:
Gemini 2.5 Flash
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
11.5s
Cost:
$0.004892
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
92.49%
AI-ism adverb frequency
(details)
80.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
39.94%
AI-ism word frequency
(details)
66.67%
Cliché density
(details)
100.00%
Emotion telling (show vs. tell)
(details)
99.57%
Filter word density
(details)
100.00%
Gibberish response detection
(details)
100.00%
Markdown formatting overuse
(details)
100.00%
Missing dialogue indicators (quotation marks)
(details)
66.67%
Name drop frequency
(details)
100.00%
Narrator intent-glossing
(details)
0.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
100.00%
Paragraph length variance
(details)
91.09%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
92.29%
Em-dash & semicolon overuse
(details)
94.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
50.44%
Sentence opener variety
(details)
0.00%
Adverb-first sentence starts
(details)
79.09%
Pronoun-first sentence starts
(details)
22.50%
Subject-first sentence starts
(details)
56.82%
Subordinate conjunction sentence starts
(details)
65.22%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
0.00%
Dialogue tag variety (said vs. fancy)
(details)
73.2259%
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
Messages
Meta
AI
The air hung thick with
the metallic reek of blood, a coppery tang that clawed at the back of Harlow's throat.
She stepped over the yellow
police tape, the crisp crinkle of plastic a jarring sound in the cavernous
silence
of the abandoned Tube station.
Water dripped somewhere in the
gloom
, a
rhythmic
plink-plunk that
echoed
off the curved tunnel walls.
A faded map, still clinging
to a grimy pillar, showed lines long decommissioned, a phantom network of forgotten routes.
The Veil Market, some bobby
had called it.
She’d heard whispers of a
place like this, a myth amongst the rank and file, a haven for the weird and unsavoury.
Now it was a crime
scene.
Harlow’s gaze swept across the
platform.
The usual trappings of a
forensic investigation were already in place: glowing chemical lights illuminating arcs of blood, evidence markers dotting the concrete like morbid confetti, the hushed murmur of officers going about their grim work. But something was off. The light. It was dim, an
oppressive
, shadowy half-light that even the powerful lamps struggled to penetrate.
Dust motes danced in the
beams, but not the floating, lazy kind. These particles
seemed to
writhe, to swirl with an unseen current, creating an unsettling visual static.
A figure detached itself from
a cluster of uniforms, a stocky man with a neatly trimmed beard and an air of perpetual annoyance. Detective Inspector Harding.
He gestured towards a huddle
of crime scene investigators near a defunct turnstile. “Quinn. Took your sweet time getting here.”
Harlow clocked his watch, a
cheap digital affair. “Traffic. And I didn’t realise the job came with a chauffeur service.”
She ran a hand over
her closely cropped salt-and-pepper hair.
Her brown eyes narrowed, taking
in the scene.
A body lay slumped against
the grimy ticket booth, a man, or what remained of one.
The bloodied outline on the
concrete was disturbingly artistic. “Lovely, isn’t it?” Harding grimaced. “Another one for the weird file. Third in as many weeks. You got any bright ideas, or are we just collecting cadavers for the supernaturals now?” Harlow ignored the jab.
She moved closer, her gaze
fixed on the body. A faint metallic aroma, separate from the blood,
hung in the air
. A sharp tang, like ozone, or a storm about to break.
It prickled her nose, raised
the hairs on her arms. “Victim identification?”
she asked, her voice low
. Harding consulted a small notepad. “Gary
Henderson
. Forty-two. Unemployed. Small-time drug dealer, apparently. Had a rap sheet longer than my arm. Looks like a turf war gone wrong.” “Turf war?” Harlow knelt,
carefully
avoiding a splatter of congealed blood. The body
was contorted
, limbs at unnatural angles. The man’s eyes were wide, staring at the discoloured ceiling. But it wasn’t the expression of surprise that caught her attention. It was the colour. A faint, ethereal glow
seemed to
emanate from his irises, a pale green light that
pulsed
faintly. “What else would it be?” Harding scoffed. “Look at him. Slumped like a sack of spuds. Stab wounds, blunt force trauma. Textbook. Probably crossed the wrong bloke, ended up here.” Harlow reached for her penlight, shining it on the victim’s chest. A series of deep lacerations marred his torso, but they weren't typical knife wounds. The edges were uneven, ragged, as if something had torn through flesh rather than sliced. And beneath the dried blood, a peculiar pattern emerged, faint but distinct. A series of interlocking circles and lines, almost like a brand. “This isn’t a knife,”
she stated, more to herself
than to Harding. “Looks like a knife to me,” Harding mumbled, peering over her shoulder. “Or a
very
angry ice pick. Point is, it’s a murder. We found a shiv nearby, covered in his blood. Open and shut.” “A shiv?”
Harlow stood, her keen eyes scanning the immediate area
. “Where?” Harding pointed to an evidence marker next to a discarded crisp packet. A crude, make-shift blade lay there,
glinting
dully under the forensic lights. It
was wrapped
in cloth, the tip stained dark. Harlow walked over, a frown creasing her brow.
She studied the shiv for
a long moment, then looked back at the wounds on
Henderson
's chest. The patterns, the ragged edges – they didn’t match. Not even close. The shiv was too narrow, too precise to inflict such wide, tearing injuries. “This shiv,”
she began, turning to face
Harding, her voice gaining an edge. “It would make neat, thin cuts. These…these are tears. Like he was mauled.” Harding shrugged. “Maybe he was. Some street brawl. They got creative.” “Creative, or something else entirely.” Harlow’s gaze drifted to the walls of the platform, noting the graffiti. Not the typical spray-painted tags, but
intricate
symbols,
etched
into the grime, some almost glowing faintly under the forensic lights. They were everywhere, interlocking patterns, swirling lines, symbols that felt ancient, foreign.
Her partner had seen things
like this before, in the last days.
She could feel the hairs
on her neck prickle.
She knelt again, closer to
the victim, ignoring Harding’s exasperated sigh. The smell of ozone was stronger here, almost stinging her nostrils.
She noticed, for the first
time, a peculiar residue on the concrete beneath the body – a fine, shimmering dust, almost invisible to the naked eye. It looked like crushed moonlight. Harlow meticulously examined the man’s hands. His fingers
were splayed
, but not in the rigor mortis grip of someone fighting for their life. They looked… relaxed. Too relaxed. And on his left palm, a faint, circular indentation. Like he had been holding something. “He was holding something,” she murmured,
tracing
the outline with a gloved finger. “Something round. And then it was taken.” Harding snorted. “A mobile phone, probably. Thieves nicked it. Comes with the territory down here.” “A mobile phone wouldn’t leave this kind of imprint,” Harlow countered, shaking her head. “This is specific. A worn impression. Like a compass.” She cast her eyes around the platform again, moving with a military precision that always irked Harding. Her gaze landed on a faint trail, barely perceptible, leading from the body towards the curved tunnel entrance.
Not blood, but the same shimmering dust she'd seen beneath the victim
. A
whisper
of a trail, almost like someone had dragged something heavy, something that shed moonlight. “Did anyone check down here?” she asked, pointing towards the tunnel. Harding scoffed. “What for? The perp probably ran off into the night. Unless you think he took the Tube. Pretty sure they don’t run anymore.” “I think he went this way,”
Harlow insisted, her voice quiet but firm
. “And whatever he held, whatever left that mark on
Henderson
’s hand, it went with him.” She paused, her jaw sharp, a
flicker
of understanding in her brown eyes. “And it wasn't a phone. It was heavier. Something metallic. Something… attuned.” The dust trail grew clearer as she followed it, the faint shimmer more pronounced against the grime of the tunnel floor. It led away from the platform, deeper into the
echoing
darkness. The ozone smell grew stronger, filling the air, a scent that now brought with it a memory of an old case, of things she hadn't understood. The trail abruptly stopped near a crumbling brick wall, where the tunnel had clearly
been blocked
off. But here, the shimmering dust was concentrated, thick and almost glowing.
Not a continuous trail anymore, but a concentrated patch, as if something had dissolved there
, or reappeared. Harlow’s mind
raced
. The unusual wounds, the brand, the glowing dust, the missing object. The Veil Market. Her partner. It all clicked into place, a sudden, horrifying clarity. This wasn't a turf war. This was something else. Something supernatural. She turned back towards Harding, a cold certainty settling in her gut. “This isn’t a shiv murder,”
she stated, her voice devoid of inflection
. “And that isn’t just dust.” Her gaze swept across the ghostly light and strange etchings. “This isn’t a normal crime scene at all.”
created_at
"2026-02-19T12:23:03.096Z"
2/19/2026, 12:23:03 PM
model
"google/gemini-2.5-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
433
moderation_latency
(null)
generation_time
11460
tokens_prompt
1149
tokens_completion
2125
native_tokens_prompt
1073
native_tokens_completion
1828
native_tokens_completion_images
0
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"STOP"
usage
0.0048919
router
(null)
provider_responses
0
endpoint_id
"16c01e26-9b91-4d22-b487-ed35634b017d"
is_byok
false
latency
433
model_permaslug
"google/gemini-2.5-flash"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771503783-A8B0h9SHhArHCTT05Lsm"
upstream_id
(null)
total_cost
0.0048919
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
17
adverbTagCount
1
adverbTags
0
"Harlow knelt carefully [carefully]"
dialogueSentences
31
tagDensity
0.548
leniency
1
rawRatio
0.059
effectiveRatio
0.059
92.49%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1332
totalAiIsmAdverbs
2
found
0
adverb
"carefully"
count
1
1
adverb
"very"
count
1
highlights
0
"carefully"
1
"very"
80.00%
AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions
(empty)
found
0
"Henderson"
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
39.94%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1332
totalAiIsms
16
found
0
word
"silence"
count
1
1
word
"gloom"
count
1
2
word
"rhythmic"
count
1
3
word
"echoed"
count
1
4
word
"oppressive"
count
1
5
word
"pulsed"
count
1
6
word
"scanning"
count
1
7
word
"glinting"
count
1
8
word
"intricate"
count
1
9
word
"etched"
count
1
10
word
"could feel"
count
1
11
word
"tracing"
count
1
12
word
"whisper"
count
1
13
word
"flicker"
count
1
14
word
"echoing"
count
1
15
word
"raced"
count
1
highlights
0
"silence"
1
"gloom"
2
"rhythmic"
3
"echoed"
4
"oppressive"
5
"pulsed"
6
"scanning"
7
"glinting"
8
"intricate"
9
"etched"
10
"could feel"
11
"tracing"
12
"whisper"
13
"flicker"
14
"echoing"
15
"raced"
66.67%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
2
maxInWindow
2
found
0
label
"eyes widened/narrowed"
count
1
1
label
"hung in the air"
count
1
highlights
0
"eyes narrowed"
1
"hung in the air"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
99
matches
(empty)
99.57%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
2
narrationSentences
99
filterMatches
0
"watch"
hedgeMatches
0
"seemed to"
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
113
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
36
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1326
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
8
unquotedAttributions
0
matches
(empty)
66.67%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
34
wordCount
1037
uniqueNames
7
maxNameDensity
1.35
worstName
"Harding"
maxWindowNameDensity
3
worstWindowName
"Harding"
discoveredNames
Harlow
13
Tube
1
Veil
2
Market
2
Inspector
1
Harding
14
Henderson
1
persons
0
"Harlow"
1
"Inspector"
2
"Harding"
3
"Henderson"
places
(empty)
globalScore
0.825
windowScore
0.667
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
75
glossingSentenceCount
0
matches
(empty)
0.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
3
per1kWords
2.262
wordCount
1326
matches
0
"Not the typical spray-painted tags, but intricate symbols, etched into the grime, some almost glowin"
1
"Not blood, but the same shimmering dust she'd seen beneath the victim"
2
"Not a continuous trail anymore, but a concentrated patch, as if something had dissolved there"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
113
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
34
mean
39
std
24.54
cv
0.629
sampleLengths
0
116
1
91
2
39
3
7
4
63
5
31
6
46
7
7
8
28
9
61
10
30
11
63
12
12
13
35
14
12
15
33
16
50
17
26
18
11
19
70
20
53
21
43
22
20
23
15
24
23
25
63
26
11
27
25
28
53
29
58
30
45
31
39
32
12
33
35
91.09%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
4
totalSentences
99
matches
0
"was contorted"
1
"was wrapped"
2
"were splayed"
3
"been blocked"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
163
matches
(empty)
92.29%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
2
semicolonCount
0
flaggedSentences
2
totalSentences
113
ratio
0.018
matches
0
"The patterns, the ragged edges – they didn’t match."
1
"She noticed, for the first time, a peculiar residue on the concrete beneath the body – a fine, shimmering dust, almost invisible to the naked eye."
94.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1041
adjectiveStacks
1
stackExamples
0
"typical spray-painted tags,"
adverbCount
39
adverbRatio
0.037463976945244955
lyAdverbCount
12
lyAdverbRatio
0.011527377521613832
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
113
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
113
mean
11.73
std
6.79
cv
0.579
sampleLengths
0
21
1
24
2
16
3
19
4
8
5
22
6
6
7
6
8
36
9
4
10
2
11
15
12
12
13
16
14
23
15
3
16
13
17
7
18
8
19
22
20
8
21
16
22
9
23
5
24
26
25
4
26
9
27
12
28
11
29
10
30
7
31
5
32
23
33
11
34
8
35
10
36
11
37
4
38
17
39
7
40
23
41
11
42
14
43
15
44
12
45
11
46
12
47
12
48
23
49
11
50.44%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
8
diversityRatio
0.34513274336283184
totalSentences
113
uniqueOpeners
39
0.00%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
0
totalSentences
88
matches
(empty)
ratio
0
79.09%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
31
totalSentences
88
matches
0
"She stepped over the yellow"
1
"She’d heard whispers of a"
2
"It was dim, an oppressive,"
3
"He gestured towards a huddle"
4
"She ran a hand over"
5
"Her brown eyes narrowed, taking"
6
"She moved closer, her gaze"
7
"It prickled her nose, raised"
8
"she asked, her voice low"
9
"It was the colour."
10
"she stated, more to herself"
11
"It was wrapped in cloth,"
12
"She studied the shiv for"
13
"she began, turning to face"
14
"They were everywhere, interlocking patterns,"
15
"Her partner had seen things"
16
"She could feel the hairs"
17
"She knelt again, closer to"
18
"She noticed, for the first"
19
"It looked like crushed moonlight."
ratio
0.352
22.50%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
77
totalSentences
88
matches
0
"The air hung thick with"
1
"She stepped over the yellow"
2
"Water dripped somewhere in the"
3
"A faded map, still clinging"
4
"The Veil Market, some bobby"
5
"She’d heard whispers of a"
6
"Harlow’s gaze swept across the"
7
"The usual trappings of a"
8
"It was dim, an oppressive,"
9
"Dust motes danced in the"
10
"These particles seemed to writhe,"
11
"A figure detached itself from"
12
"Detective Inspector Harding."
13
"He gestured towards a huddle"
14
"Harlow clocked his watch, a"
15
"She ran a hand over"
16
"Her brown eyes narrowed, taking"
17
"A body lay slumped against"
18
"The bloodied outline on the"
19
"Harlow ignored the jab."
ratio
0.875
56.82%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
1
totalSentences
88
matches
0
"Now it was a crime"
ratio
0.011
65.22%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
46
technicalSentenceCount
5
matches
0
"The air hung thick with the metallic reek of blood, a coppery tang that clawed at the back of Harlow's throat."
1
"Water dripped somewhere in the gloom, a rhythmic plink-plunk that echoed off the curved tunnel walls."
2
"But it wasn’t the expression of surprise that caught her attention."
3
"They were everywhere, interlocking patterns, swirling lines, symbols that felt ancient, foreign."
4
"Not a continuous trail anymore, but a concentrated patch, as if something had dissolved there, or reappeared."
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
17
uselessAdditionCount
6
matches
0
"she asked, her voice low"
1
"she stated, more to herself than to Harding"
2
"Harlow stood, her keen eyes scanning the immediate area"
3
"she began, turning to face Harding, her voice gaining an edge"
4
"Harlow insisted, her voice quiet but firm"
5
"she stated, her voice devoid of inflection"
0.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
7
fancyCount
5
fancyTags
0
"she stated (state)"
1
"Harding mumbled (mumble)"
2
"she murmured (murmur)"
3
"Harlow insisted (insist)"
4
"she stated (state)"
dialogueSentences
31
tagDensity
0.226
leniency
0.452
rawRatio
0.714
effectiveRatio
0.323
73.2259%