NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHSZ0RY1J9171JRBBPVP79KN
Run Details
Model:
Cohere Command R+ (Aug. 2024)
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
30.7s
Cost:
$0.017382
Provider:
Cohere
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)
4.49%
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)
50.57%
Name drop frequency
(details)
57.41%
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)
86.80%
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)
77.35%
Sentence opener variety
(details)
49.75%
Adverb-first sentence starts
(details)
100.00%
Pronoun-first sentence starts
(details)
64.48%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
89.29%
Technical jargon density
(details)
100.00%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
86.0040%
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
Detective Harlow Quinn stepped into
the abandoned Tube station, the air thick with the smell of damp concrete and something earthy and foul. An eerie
silence
engulfed her, broken only by the
echo
of her boot heels on the platform.
The unlit fluorescent bulbs cast
long shadows, adding to the claustrophobic atmosphere. She approached the crime scene, a makeshift barrier of police tape cordoning off the area.
The body lay sprawled on
the ground, a pool of blood soaking into the old tracks. 'This one's a doozy, isn't it?' DS Elliot Foster, a portly man with a ruddy complexion, stood over the body.
His round face glistened with
sweat, his jowls wobbling as he spoke. 'The vic's been ripped to shreds.' Quinn's sharp eyes darted around, taking in every detail.
The torn clothes, the savage
wounds, the markings on the ground. Something was not right. She knelt by the corpse, her military precision apparent in the slow, deliberate movement. 'Looks like an animal attack, doesn't it?
Maybe a pack of wild
dogs.' Foster continued, wiping his forehead with a handkerchief. 'But no animals down here, not with that smell.' He waved his hand, indicating the strange odour permeating the station. Quinn's brown
eyes narrowed
.
The pattern of wounds was
irregular, almost... intentional. But why?
She turned over the victim's
hand, revealing clean, neatly trimmed nails. No defensive wounds. The victim hadn't fought back. 'The ME will know more, but I'm thinking we got us a sacrifice, Detective.' Foster's voice boomed, his bulk casting an
imposing
shadow. 'You know, with all them freak shows and weirdos in Camden, probably some sick cult business.'
Quinn's gaze fell on the
victim's face.
A young woman, her features
frozen in a mask of terror.
Brown curls matted with blood
and grime framed her pale face. But it wasn't fear in her eyes, Quinn noted; it was something else. Resignation, perhaps. Or was it acceptance? 'Hey, you see this?' Foster called out, directing his maglite at the far wall. 'Looks like them freaks were summoning something. Weird, eh?'
Quinn rose, her eyes scanning
the wall. Ritualistic symbols
were painted
in what
looked like blood
. 'Could just be a distraction, DS Foster. Throw us off the scent.' She moved closer to the wall, scrutinising the
intricate
design.
Someone had put effort into
this.
The symbols were unlike anything
she'd seen, even in her work with the Occult Crimes Unit. 'What're the uniforms saying?' 'Not much, boss. A bunch of youngsters came down for a rave and found the body.
They're shaken up, giving conflicting
statements. The kids are getting rounded up, and the doc's on their way to pronounce.' Foster snorted. 'Can you believe it? Rave in a stinking hole like this. Kids these days.' 'I want to talk to this lot once they've calmed down.' Quinn took out her worn leather notebook, jotting down observations. 'And get forensics down here, something doesn't sit right.' 'You don't think it's as simple as I said, do ya? Some nutcase cultists?' Foster leaned in, his breath rank with tobacco. Quinn tilted her head, eyes
scanning
the platform. The kids' footprints were everywhere, and some had trampled over the ritual markings. 'Too many
variables
. This location, the markings... It's a message. But for whom?' 'You getting all tinfoil hat on me, boss?' Foster chuckled. 'Or is that detective instincts?' Quinn ignored him, her attention fixed on the girl's belongings scattered nearby. A hair tie, a tube of lip balm, and a small brass compass. She picked up the compass, her thumb brushing over the verdigris casing.
It was etched with strange
protective sigils, the needle pointing to the north. North? Quinn turned in a circle, taking in her surroundings. 'Foster, where's north from here?' She spoke without taking her eyes off the compass. 'Should be that way.' Foster pointed, his finger aiming directly towards the platform's edge and the tunnel beyond. Quinn's heart
quickened
. The compass needle should spin aimlessly underground, but this one pointed with certainty. She took a step forward, then another, towards the mouth of the tunnel. The hairs on the back of her neck rose as she neared the darkness, and the compass needle
trembled
. 'What you playing at, Detective?' Foster's voice
echoed
behind her. 'The compass, it...' Quinn's words were cut off by a loud, piercing scream from the tunnel. The sound ricocheted off the concrete walls, a primal terror that rooted them to the spot. 'That didn't sound human, did it?' Foster's voice was barely a
whisper
. Quinn stood her ground, her hand reaching for her service weapon. She took a deep breath, the air heavy and
oppressive
. 'You go back topside.
I'll check it
out.' 'Like hell,' Foster growled. 'I ain't leaving you down—' 'DS Foster, that's an order! Keep the scene secure and wait for forensics.
I'll meet you up
top.' Quinn didn't wait for a reply, striding into the tunnel, her boot steps
echoing
. As she ventured deeper into the Tube's bowels, the air grew colder, and the sound of dripping water amplified.
Her hand tightened on her
gun, fingers sweat-slick on the handle. The dim beam of her torch danced over crumbling walls, revealing the Tube's abandonment. Graffitied walls and litter gave way to ancient brickwork, the further she went. The scream
echoed
again, closer this time, a ragged, desperate sound.
Her footfalls slowed, each step
measured
, wary. The tunnel opened into a larger chamber, her torch beam revealing a scene straight from a nightmare. Figures, human-like in shape but twisted and distorted, gathered in a circle.
Their bodies contorted, limbs bending
in ways that defied anatomy. At their centre, a dark, gaping portal
pulsed
with malevolent energy. And from it, a creature, unlike anything Quinn had encountered, emerged.
It hovered, suspended, its many
eyes
glinting
in the darkness. Quinn's hand froze mid-draw, her mouth dry. This was the source of the stench, the reason why the compass needle spun. One of the figures turned, its face a grotesque mask. A sound emanated from its mouth,
not quite laughter but a terrible parody of it
. She
was discovered
. The other figures joined in, their horrid
cacophony
echoing
, filling the chamber. Quinn's finger twitched on the trigger as she raised her pistol, ready to fire.
created_at
"2026-02-19T03:27:39.976Z"
2/19/2026, 3:27:39 AM
model
"cohere/command-r-plus-08-2024"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
141
moderation_latency
113
generation_time
30508
tokens_prompt
1149
tokens_completion
1629
native_tokens_prompt
1049
native_tokens_completion
1476
native_tokens_completion_images
(null)
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
0.0173825
router
(null)
provider_responses
0
endpoint_id
"cd63714a-d459-4806-bdf2-0dfea4f6614c"
id
"2edc2dc8-a686-467f-9a56-a5549869efbc"
is_byok
false
latency
141
model_permaslug
"cohere/command-r-plus-08-2024"
provider_name
"Cohere"
status
200
api_type
"completions"
id
"gen-1771471659-vTA8hdkPyPB02k593FvZ"
upstream_id
"2edc2dc8-a686-467f-9a56-a5549869efbc"
total_cost
0.0173825
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Cohere"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
3
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
0
tagDensity
1
leniency
1
rawRatio
0
effectiveRatio
0
100.00%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1047
totalAiIsmAdverbs
0
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)
4.49%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1047
totalAiIsms
20
found
0
word
"silence"
count
1
1
word
"echo"
count
1
2
word
"imposing"
count
1
3
word
"scanning"
count
2
4
word
"intricate"
count
1
5
word
"variables"
count
1
6
word
"etched"
count
1
7
word
"quickened"
count
1
8
word
"trembled"
count
1
9
word
"echoed"
count
2
10
word
"whisper"
count
1
11
word
"oppressive"
count
1
12
word
"echoing"
count
2
13
word
"measured"
count
1
14
word
"pulsed"
count
1
15
word
"glinting"
count
1
16
word
"cacophony"
count
1
highlights
0
"silence"
1
"echo"
2
"imposing"
3
"scanning"
4
"intricate"
5
"variables"
6
"etched"
7
"quickened"
8
"trembled"
9
"echoed"
10
"whisper"
11
"oppressive"
12
"echoing"
13
"measured"
14
"pulsed"
15
"glinting"
16
"cacophony"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"eyes widened/narrowed"
count
1
highlights
0
"eyes narrowed"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
76
matches
(empty)
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
76
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
103
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
23
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1045
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
9
unquotedAttributions
0
matches
(empty)
50.57%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
23
wordCount
704
uniqueNames
8
maxNameDensity
1.99
worstName
"Quinn"
maxWindowNameDensity
3
worstWindowName
"Quinn"
discoveredNames
Harlow
1
Quinn
14
Tube
3
Occult
1
Crimes
1
Unit
1
Rave
1
Keep
1
persons
0
"Harlow"
1
"Quinn"
2
"Tube"
places
0
"Rave"
globalScore
0.506
windowScore
0.667
57.41%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
54
glossingSentenceCount
2
matches
0
"looked like blood"
1
"not quite laughter but a terrible parody of it"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
1
per1kWords
0.957
wordCount
1045
matches
0
"not quite laughter but a terrible parody of it"
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
103
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
33
mean
31.67
std
16.14
cv
0.51
sampleLengths
0
52
1
31
2
38
3
38
4
41
5
33
6
39
7
48
8
23
9
64
10
52
11
30
12
22
13
34
14
15
15
60
16
14
17
18
18
48
19
10
20
32
21
12
22
29
23
9
24
32
25
57
26
35
27
54
28
21
29
25
30
3
31
12
32
14
86.80%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
4
totalSentences
76
matches
0
"were painted"
1
"shaken"
2
"was etched"
3
"was discovered"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
110
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
0
semicolonCount
1
flaggedSentences
1
totalSentences
103
ratio
0.01
matches
0
"But it wasn't fear in her eyes, Quinn noted; it was something else."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
83
adjectiveStacks
0
stackExamples
(empty)
adverbCount
1
adverbRatio
0.012048192771084338
lyAdverbCount
1
lyAdverbRatio
0.012048192771084338
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
103
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
103
mean
10.15
std
5.29
cv
0.522
sampleLengths
0
23
1
17
2
12
3
15
4
16
5
20
6
12
7
6
8
9
9
11
10
4
11
14
12
7
13
14
14
20
15
4
16
7
17
1
18
2
19
11
20
3
21
5
22
23
23
16
24
7
25
11
26
11
27
13
28
2
29
4
30
14
31
7
32
2
33
7
34
9
35
7
36
15
37
6
38
16
39
4
40
3
41
13
42
6
43
16
44
4
45
7
46
3
47
21
48
9
49
11
77.35%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
2
diversityRatio
0.47572815533980584
totalSentences
103
uniqueOpeners
49
49.75%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
67
matches
0
"Maybe a pack of wild"
ratio
0.015
100.00%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
17
totalSentences
67
matches
0
"She approached the crime scene,"
1
"His round face glistened with"
2
"She knelt by the corpse,"
3
"She turned over the victim's"
4
"They're shaken up, giving conflicting"
5
"It's a message."
6
"She picked up the compass,"
7
"It was etched with strange"
8
"She took a step forward,"
9
"She took a deep breath,"
10
"I'll check it"
11
"I'll meet you up"
12
"Her hand tightened on her"
13
"Her footfalls slowed, each step"
14
"Their bodies contorted, limbs bending"
15
"It hovered, suspended, its many"
16
"She was discovered."
ratio
0.254
64.48%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
53
totalSentences
67
matches
0
"Detective Harlow Quinn stepped into"
1
"An eerie silence engulfed her,"
2
"The unlit fluorescent bulbs cast"
3
"She approached the crime scene,"
4
"The body lay sprawled on"
5
"His round face glistened with"
6
"Quinn's sharp eyes darted around,"
7
"The torn clothes, the savage"
8
"Something was not right."
9
"She knelt by the corpse,"
10
"Quinn's brown eyes narrowed."
11
"The pattern of wounds was"
12
"She turned over the victim's"
13
"The victim hadn't fought back."
14
"Quinn's gaze fell on the"
15
"A young woman, her features"
16
"Brown curls matted with blood"
17
"Quinn rose, her eyes scanning"
18
"Someone had put effort into"
19
"The symbols were unlike anything"
ratio
0.791
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
67
matches
(empty)
ratio
0
89.29%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
40
technicalSentenceCount
3
matches
0
"She picked up the compass, her thumb brushing over the verdigris casing."
1
"The sound ricocheted off the concrete walls, a primal terror that rooted them to the spot."
2
"Their bodies contorted, limbs bending in ways that defied anatomy."
100.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
3
uselessAdditionCount
0
matches
(empty)
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
0
86.0040%