NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-19-01KHT0X6VW3HS9N9DQGX0A56T5
Run Details
Model:
Qwen 2.5 72B
Test:
Bad Writing Habits
Scenario:
Mystery: examining a crime scene
Duration:
33.6s
Cost:
$0.000820
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
81.80%
AI-ism adverb frequency
(details)
80.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
9.02%
AI-ism word frequency
(details)
66.67%
Cliché density
(details)
100.00%
Emotion telling (show vs. tell)
(details)
42.02%
Filter word density
(details)
100.00%
Gibberish response detection
(details)
100.00%
Markdown formatting overuse
(details)
100.00%
Missing dialogue indicators (quotation marks)
(details)
0.00%
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)
97.01%
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)
52.80%
Sentence opener variety
(details)
41.15%
Adverb-first sentence starts
(details)
91.60%
Pronoun-first sentence starts
(details)
0.00%
Subject-first sentence starts
(details)
0.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
0.00%
Useless dialogue additions
(details)
0.00%
Dialogue tag variety (said vs. fancy)
(details)
72.0693%
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 neon flicker of the
underground market cast eerie shadows on the damp, tiled walls.
Detective Harlow Quinn stepped off
the rickety platform, her boots
echoing
in the abandoned Tube station.
The Veil Market, hidden beneath
Camden, was a world away from the bustling streets above.
The air was thick with
the scent of damp earth and magic. Quinn's eyes
scanned
the crowd, picking out faces she recognized from previous visits.
Some dodged her gaze, others
met it with a challenge.
Her closely cropped salt-and-pepper hair
stood in sharp contrast to the colorful and
chaotic
scene around her.
She adjusted the worn leather
watch
on her left wrist, a habit honed from years of military precision. "Detective Quinn,"
a voice called out, and
she turned to see DS Brian Knight approaching. Knight was a younger officer, eager and a little too trusting of the world around him.
His eyes were wide, but
his stance was firm. "Thank you for coming." "Where's the victim?"
Quinn asked, her voice cutting
through the murmur of the crowd. "Right this way,"
Knight said, leading her deeper
into the market.
They passed stalls selling enchanted
trinkets, dubious potions, and ancient texts.
The market shifted locations every
full moon, always to an abandoned station, and the vendors
seemed to
know the drill.
They moved with a fluid
grace that belied the supernatural elements at play.
Knight led Quinn to a
corner where a small crowd had gathered.
A young woman with curly
red hair and round glasses stood at the center, tucking a strand of hair behind her left ear.
She looked up as Quinn
approached, her green eyes narrowing. "Eva Kowalski,"
Quinn nodded, recognizing the research
assistant from the British Museum. "What are you doing here?" Eva's freckled complexion flushed. "I was just... investigating. This market is full of valuable artifacts, and one of them has gone missing. I think it might be connected to the murder." Quinn raised an
eyebrow
. "And what makes you think that?" Eva gestured to the body sprawled on the ground. "The victim, a local street dealer named
Marcus
, had a Veil Compass on him. It was last seen in the hands of a shady figure who disappeared as soon as the alarm was raised. I believe the Compass was stolen, and the thief killed
Marcus
to cover their tracks." Knight frowned. "That's a lot of assumptions, Eva. We haven't found the Compass yet." Quinn knelt beside the body, her sharp jawline set in concentration.
Marcus
's eyes were wide open, frozen in a final moment of fear.
She noticed a small, almost
imperceptible scratch on his wrist, just above his
pulse
point.
It was barely visible, but
to Quinn, it stood out like a
beacon
. "What's this?"
she asked, pointing to the
scratch. Eva leaned in, her eyes widening. "That looks like a sigil. It could be a magical ward or a curse." Quinn stood up, her mind
racing
. "I need to see the rest of the area. Knight, interview the witnesses. Eva, help him. I want to know everything about this Compass."
She moved away from the
crowd, her eyes
scanning
the stalls and the faces of the vendors. The market was a labyrinth, and each turn
seemed to
lead to something new.
She stopped at a stall
selling magical artifacts and spoke to the vendor, a wizened old woman with a knowing smile. "Ma'am, do you know anything about a Veil Compass?" Quinn asked. The woman's eyes twinkled. "Ah, the Shadow Compass. Rare piece, that. It points to the nearest supernatural rift or portal. Very valuable to those who know its value." Quinn nodded, her mind piecing together the puzzle. "And who might be interested in such a thing?" The woman leaned in, her voice dropping to a conspiratorial
whisper
. "Those who seek the hidden paths. The ones who walk the shadows and trade in secrets. The Shades, they call themselves." Quinn thanked the woman and continued her search.
She found a small, dark
corner where the market's magical energy
seemed to
congregate. There, hidden under a pile of old books, she spotted a small brass compass with a patina of verdigris. The face
was etched
with protective sigils, and the needle pointed unwaveringly toward a nearby wall. "Knight, Eva,"
she called out, her voice
steady. "Come here."
They joined her, and Quinn
held up the Compass. "This is what we're looking for. It points to a rift. Someone is using this market to access something else." Eva's
eyes widened
. "A rift? What kind of rift?" Quinn's gaze was steely. "The kind that leads to places we don't understand. And I suspect our killer used it to disappear." Knight nodded, his face serious. "We need to secure this area. If there's a rift, we can't let anyone else use it." Eva tugged on her satchel, pulling out a leather-bound notebook. "I can help with that. I've studied these things. We need to seal it before it draws more attention." Quinn's mind
raced
, the pieces falling into place. "We need to move
quickly
. Eva, help Knight secure the area. I'll check the wall and see if I can find the rift."
She approached the wall, her
eyes
scanning
the ancient stone for any sign of the rift.
Her fingers traced the sigils
on the Compass, and she felt a faint, tingling energy.
Suddenly, a hidden door revealed
itself, carved into the stone with
intricate
, glowing symbols. "Knight, Eva, get over here,"
she called out, her voice
urgent.
They joined her, and Quinn
pointed to the door. "This is it. We need to find out what's on the other side." Eva's hands
trembled
as she approached the door. "We need to be careful. These things can be unpredictable." Quinn nodded, her
resolve
firm. "We'll go in together. Knight, cover us. Eva, stay close." With a deep breath, Quinn pushed the door open, and they stepped into the unknown. The air beyond was thick with a different kind of magic, and the light
seemed to
bend around them.
They moved cautiously, their senses
on high alert. As they ventured deeper, Quinn's instincts kicked in. Something was off, and she couldn't put her finger on it. The walls
pulsed
with a faint,
rhythmic
glow, and the floor
seemed to
shift beneath their feet.
She stopped, her hand on
her weapon. "Wait," she whispered. "Something's not right." Eva and Knight froze, their eyes wide with fear. Quinn's gaze darted around, searching for the source of the disturbance. And then she saw it—a faint shadow moving in the corner of her eye. "Behind you," she shouted, pushing Eva and Knight out of the way as a dark figure lunged from the shadows. Quinn drew her weapon, her heart
pounding
. The figure
was cloaked
in a dark hood, and its movements were swift and precise. It lunged again, and Quinn fired, but the figure dodged with an agility that defied logic. "We need to get out of here,"
Quinn yelled, her voice firm
. "Now!" They retreated, the figure hot on their heels. Quinn kept her weapon trained, her mind
racing
. They couldn't let this thing escape, not now. They reached the door, and Quinn slammed it shut, leaning against it with all her strength. "Secure it," she ordered. "We need to find out who this is and why they want the Compass." Eva and Knight worked together, reinforcing the door with whatever they could find. Quinn's mind
raced
, piecing together the clues. The scratch on
Marcus
's wrist, the missing Compass, the hidden rift, and now this shadowy figure. It all pointed to a deeper, more
sinister
plot. When the door was secure, Quinn took a deep breath and turned to her colleagues. "We need to find out who's behind this. And we need to do it soon." Eva nodded, her eyes
determined
. "I can start by looking into the Shades and their connections in the market. They might know more about this rift and the Compass." Knight straightened, his
resolve
firm. "I'll interview the witnesses again. Someone here must know something." Quinn nodded, her mind already shifting to the next steps. "Good. Let's find out what's
really
going on here. This is just the beginning."
created_at
"2026-02-19T04:00:40.348Z"
2/19/2026, 4:00:40 AM
model
"qwen/qwen-2.5-72b-instruct"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
474
moderation_latency
(null)
generation_time
33315
tokens_prompt
1171
tokens_completion
2051
native_tokens_prompt
1037
native_tokens_completion
1783
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
0.00081981
router
(null)
provider_responses
0
endpoint_id
"8b6b26e9-621a-4b31-b55a-c9aaa7482ede"
id
"cmpl-8a25d1064cf240dd8ffaaa99c91fc408"
is_byok
false
latency
92
model_permaslug
"qwen/qwen-2.5-72b-instruct"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771473640-VwmYv48GObXBD1FJ5ANI"
upstream_id
"cmpl-8a25d1064cf240dd8ffaaa99c91fc408"
total_cost
0.00081981
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
12
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
40
tagDensity
0.3
leniency
0.6
rawRatio
0
effectiveRatio
0
81.80%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1374
totalAiIsmAdverbs
5
found
0
adverb
"very"
count
1
1
adverb
"quickly"
count
1
2
adverb
"suddenly"
count
1
3
adverb
"cautiously"
count
1
4
adverb
"really"
count
1
highlights
0
"very"
1
"quickly"
2
"suddenly"
3
"cautiously"
4
"really"
80.00%
AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions
(empty)
found
0
"Marcus"
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
9.02%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1374
totalAiIsms
25
found
0
word
"flicker"
count
1
1
word
"echoing"
count
1
2
word
"scanned"
count
1
3
word
"chaotic"
count
1
4
word
"eyebrow"
count
1
5
word
"pulse"
count
1
6
word
"beacon"
count
1
7
word
"racing"
count
2
8
word
"scanning"
count
2
9
word
"whisper"
count
1
10
word
"etched"
count
1
11
word
"raced"
count
2
12
word
"traced"
count
1
13
word
"intricate"
count
1
14
word
"trembled"
count
1
15
word
"resolve"
count
2
16
word
"pulsed"
count
1
17
word
"rhythmic"
count
1
18
word
"pounding"
count
1
19
word
"sinister"
count
1
20
word
"determined"
count
1
highlights
0
"flicker"
1
"echoing"
2
"scanned"
3
"chaotic"
4
"eyebrow"
5
"pulse"
6
"beacon"
7
"racing"
8
"scanning"
9
"whisper"
10
"etched"
11
"raced"
12
"traced"
13
"intricate"
14
"trembled"
15
"resolve"
16
"pulsed"
17
"rhythmic"
18
"pounding"
19
"sinister"
20
"determined"
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
"air was thick with"
count
1
highlights
0
"eyes widened"
1
"The air was thick with"
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
1
narrationSentences
85
matches
0
"e with fear"
42.02%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
1
hedgeCount
5
narrationSentences
85
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
49
ratio
0
matches
(empty)
100.00%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
0
markdownWords
0
totalWords
1370
ratio
0
matches
(empty)
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
9
unquotedAttributions
0
matches
(empty)
0.00%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
62
wordCount
916
uniqueNames
13
maxNameDensity
3.17
worstName
"Quinn"
maxWindowNameDensity
4.5
worstWindowName
"Quinn"
discoveredNames
Harlow
1
Quinn
29
Tube
1
Veil
1
Market
1
Camden
1
Brian
1
Knight
10
British
1
Museum
1
Eva
10
Compass
3
Marcus
2
persons
0
"Harlow"
1
"Quinn"
2
"Market"
3
"Brian"
4
"Knight"
5
"Eva"
6
"Marcus"
places
0
"British"
globalScore
0
windowScore
0.167
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
71
glossingSentenceCount
0
matches
(empty)
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1370
matches
(empty)
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
47
mean
29.15
std
15.4
cv
0.528
sampleLengths
0
58
1
58
2
44
3
14
4
55
5
45
6
17
7
31
8
10
9
58
10
14
11
51
12
8
13
20
14
30
15
52
16
11
17
28
18
17
19
32
20
57
21
10
22
29
23
9
24
22
25
22
26
29
27
31
28
45
29
11
30
22
31
18
32
15
33
42
34
43
35
6
36
34
37
27
38
31
39
13
40
40
41
18
42
45
43
30
44
29
45
15
46
24
97.01%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
2
totalSentences
85
matches
0
"was etched"
1
"was cloaked"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
0
totalVerbs
163
matches
(empty)
100.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
1
semicolonCount
0
flaggedSentences
1
totalSentences
113
ratio
0.009
matches
0
"And then she saw it—a faint shadow moving in the corner of her eye."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
920
adjectiveStacks
0
stackExamples
(empty)
adverbCount
17
adverbRatio
0.01847826086956522
lyAdverbCount
7
lyAdverbRatio
0.007608695652173913
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
12.12
std
6.56
cv
0.541
sampleLengths
0
15
1
16
2
15
3
12
4
13
5
10
6
17
7
18
8
15
9
16
10
9
11
4
12
14
13
11
14
11
15
20
16
13
17
12
18
23
19
10
20
12
21
5
22
4
23
27
24
4
25
6
26
9
27
49
28
2
29
12
30
11
31
12
32
15
33
13
34
8
35
6
36
14
37
6
38
24
39
17
40
14
41
21
42
11
43
4
44
24
45
8
46
9
47
11
48
21
49
8
52.80%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
2
diversityRatio
0.3274336283185841
totalSentences
113
uniqueOpeners
37
41.15%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
81
matches
0
"Suddenly, a hidden door revealed"
ratio
0.012
91.60%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
26
totalSentences
81
matches
0
"Her closely cropped salt-and-pepper hair"
1
"She adjusted the worn leather"
2
"His eyes were wide, but"
3
"They passed stalls selling enchanted"
4
"They moved with a fluid"
5
"She looked up as Quinn"
6
"She noticed a small, almost"
7
"It was barely visible, but"
8
"she asked, pointing to the"
9
"She moved away from the"
10
"She stopped at a stall"
11
"She found a small, dark"
12
"she called out, her voice"
13
"They joined her, and Quinn"
14
"She approached the wall, her"
15
"Her fingers traced the sigils"
16
"she called out, her voice"
17
"They joined her, and Quinn"
18
"They moved cautiously, their senses"
19
"She stopped, her hand on"
ratio
0.321
0.00%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
76
totalSentences
81
matches
0
"The neon flicker of the"
1
"Detective Harlow Quinn stepped off"
2
"The Veil Market, hidden beneath"
3
"The air was thick with"
4
"Quinn's eyes scanned the crowd,"
5
"Some dodged her gaze, others"
6
"Her closely cropped salt-and-pepper hair"
7
"She adjusted the worn leather"
8
"a voice called out, and"
9
"Knight was a younger officer,"
10
"His eyes were wide, but"
11
"Quinn asked, her voice cutting"
12
"Knight said, leading her deeper"
13
"They passed stalls selling enchanted"
14
"The market shifted locations every"
15
"They moved with a fluid"
16
"Knight led Quinn to a"
17
"A young woman with curly"
18
"She looked up as Quinn"
19
"Quinn nodded, recognizing the research"
ratio
0.938
0.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
0
totalSentences
81
matches
(empty)
ratio
0
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
43
technicalSentenceCount
0
matches
(empty)
0.00%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
12
uselessAdditionCount
4
matches
0
"Quinn asked, her voice cutting through the murmur of the crowd"
1
"she called out, her voice steady"
2
"she called out, her voice urgent"
3
"Quinn yelled, her voice firm"
0.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
11
fancyCount
7
fancyTags
0
"a voice called out (call out)"
1
"she called out (call out)"
2
"she called out (call out)"
3
"she whispered (whisper)"
4
"she shouted (shout)"
5
"Quinn yelled (yell)"
6
"she ordered (order)"
dialogueSentences
40
tagDensity
0.275
leniency
0.55
rawRatio
0.636
effectiveRatio
0.35
72.0693%