NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHMMGAHRBKKGR8T278N18J9P
Run Details
Model:
Hermes 3 70B
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
22.5s
Cost:
$0.000522
Provider:
DeepInfra
Model input
System
You are an expert novelist with a gift for vivid, immersive prose. You write in tight third-person limited point of view with a strong narrative voice. Your prose is clean, precise, and engaging — you favor strong verbs, concrete details, and natural-sounding dialogue. You will be given a story bible (codex) containing canonical details about characters, locations, items, and lore. Use these details to ground your writing in the established world. Stay consistent with the codex. Write only the prose of the scene. Do not include titles, chapter headings, markdown formatting, or any commentary before or after the scene.
User/Human
<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="4417" name="Tomás Herrera" aliases="Tommy, Tomás, Herrera" pronouns="he/him" species="Human" storyRole="Support"> <eyeColor>warm brown</eyeColor> <hair>short curly dark brown</hair> <height>5'10"</height> <age>29</age> <skinTone>olive skin</skinTone> <scar>scar running along his left forearm from a knife attack</scar> <medallion>Saint Christopher medallion around his neck</medallion> <birthplace>Seville, Spain</birthplace> <description>A former paramedic who provides off-the-books medical care for the clique.</description> <backstory>Born in Seville, Spain. He moved to London to work for the NHS but lost his license after administering unauthorized treatments to supernatural patients.</backstory> </character> <location id="854" name="The Raven's Nest" aliases="the Nest, Raven, Silas' bar" realm="Earth"> <signColor>distinctive green neon sign above the entrance</signColor> <secretRoom>hidden back room accessible through a bookshelf, used for clandestine meetings</secretRoom> <description>A dimly lit bar in Soho, London. The walls are covered with old maps and black-and-white photographs.</description> </location> <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> </codex> Write a fully fleshed out scene of at least 1000 words in the thriller genre. A detective is pursuing a suspect through rain-soaked city streets at night. The chase takes them from the street level down into an underground market. The detective must decide whether to follow the suspect into unfamiliar and potentially dangerous territory. 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.
Model response
Messages
Meta
AI
Rain lashed the pavement, the gutters flowing like rivers as Detective Harlow Quinn stepped from her car, the green neon sign of The Raven's Nest flickering overhead. She adjusted her worn leather
watch
, her sharp jaw set with determination. "Tomás Herrera, you slippery bastard," she muttered under her breath. For weeks, she'd been tracking the rogue paramedic – since discovering his involvement with theVeil Market. Tonight, she would confront him and
unravel
the secrets of his
clandestine
operations. Entering the bar, the musky scent of old wood and stale ale wrapped around her. Quinn scanned the dimly lit room, her eyes landing on a man fitting Herrera's description – olive skin, short curly hair – seated at the counter, a Saint Christopher medallion
glinting
at his neck. She approached, her bearing military precision. "Tomás Herrera,"she said, flashing her badge. "I need to talk to you about the Veil Market." The man's warm brown
eyes widened
, but before he could respond or react, gunfire shattered the silence. Patrons screamed, diving for cover. Quinn dropped behind the counter, pulling her gun from its holster. Herrera crouched beside her. "What the hell is this?" she shouted above the chaos. "Someone doesn't want me talking to you," he replied, yanking a knife from his boot and clutching it
tightly
. Another burst of gunfire, and Quinn knew they had to move. "Come on!" She grabbed Herrera, dragging him through the hidden back room. They emerged into a narrow alley, the rain assaulting them sideways. "This way!" Herrera called, sprinting for the end of the alley. Quinn hesitated only for a second before following. If the alternative was getting shot, she had little choice. They ran through the labyrinth of Soho's back streets, the roar of the rain drowning any sound of pursuit. Quinn
watch
ed Herrera closely, his scar running along his left forearm a
stark
white against his otherwise tanned skin. His movements were swift, precise, like he knew exactly where he
was going
. Suddenly, the Spaniard stopped at the mouth of a tube station. "Down here," he said, pulling a bone token from his pocket. "It's safe." Quinn faltered, the stairs leading deep into the abandoned station. To follow him into the Undercity, the underground market... She hesitated, her hand instinctively checking her
watch
. Eighteen years of decorated service, and they'd lost her partner, DS Morris, to something supernatural. She couldn't afford to lose herself, or Tomás. But she had to see this though, and that meant following him, wherever he went. Taking a deep breath, she made her decision. "You better not be leading me into some trap." Herrera met her gaze, his expression serious. "Detective, I'm trying to stay alive here. TheVeil Market is our best chance." Quinn nodded curtly,
watch
ing as he slipped the bone token into a slot and pushed open the doorway. They descended into the bowels of the earth, the sounds of the rain fading behind them. Machines hummed, the air stagnant and thick with the scent of ozone. "This way," Herrera said, leading them through the winding tunnels. Quinn kept her gun at the ready, her senses alert. She had no idea what awaited them in the Veil Market, but she knew it was best to be prepared for anything. As they rounded the last bend, the market came into view. Stalls and tables filled a cavernous space, lit by flickering gas lamps. The air hummed with hushed voices, with deals
being made
in the shadows. Objects glinted in the low light, enchantments flickering at the edges of Quinn's vision. "Herrera," she said, her voice low, "what is all this?" He turned to face her, a grim smile tugging at his lips. "TheVeil Market, Detective. A place where the supernatural and the mundane collide. I think you'll find some answers here, if you look close enough." And with that, he disappeared into the crowd, leaving Quinn alone in the throng of people. She scanned the room, her hand still clutching her gun, the
weight
of what lay ahead heavy on her mind. To uncover the truth, she would have to
delve
deep into the heart of theVeil Market. But she was a detective, and that was what she did best. Time to get to work.
created_at
"2026-02-17T01:48:05.855892+00:00"
2/17/2026, 1:48:05 AM
model
"nousresearch/hermes-3-llama-3.1-70b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
189
moderation_latency
(null)
generation_time
22389
tokens_prompt
936
tokens_completion
1082
native_tokens_prompt
815
native_tokens_completion
924
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
0.0005217
router
(null)
provider_responses
0
id
"cmpl-2c5de11941e34bdf89554ba28e225fae"
status
200
is_byok
false
latency
83
endpoint_id
"2151651b-f4e9-4db7-b20d-8b91fb524bf8"
provider_name
"DeepInfra"
model_permaslug
"nousresearch/hermes-3-llama-3.1-70b"
api_type
"completions"
id
"gen-1771292863-j2KIvFZPUbbHOeUV8K0J"
upstream_id
"cmpl-2c5de11941e34bdf89554ba28e225fae"
total_cost
0.0005217
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
85.7143%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
7
adverbTagCount
1
adverbTags
0
"he replied, yanking a knife from his boot and clutching it tightly [tightly]"
71.6312%
AI-ism adverb frequency
Target: <1% AI-ism adverbs (57 tracked)
wordCount
705
totalAiIsmAdverbs
2
found
0
adverb
"suddenly"
count
1
1
adverb
"tightly"
count
1
highlights
0
"suddenly"
1
"tightly"
100.0000%
AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
100.0000%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
14.8936%
AI-ism word frequency
Target: <1% AI-ism words (140 tracked)
wordCount
705
totalAiIsms
6
found
0
word
"glinting"
count
1
1
word
"clandestine"
count
1
2
word
"stark"
count
1
3
word
"weight"
count
1
4
word
"delve"
count
1
5
word
"unravel"
count
1
highlights
0
"glinting"
1
"clandestine"
2
"stark"
3
"weight"
4
"delve"
5
"unravel"
100.0000%
Cliche density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"eyes widened/narrowed"
count
1
highlights
0
"eyes widened"
100.0000%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
51
matches
(empty)
100.0000%
Filter word density
Target: ≤12% sentences with filter/hedge words
filterCount
2
hedgeCount
0
narrationSentences
51
filterMatches
0
"watch"
hedgeMatches
(empty)
100.0000%
Overuse of "that" (subordinate clause padding)
Target: ≤10% sentences with "that" clauses
thatCount
0
totalSentences
56
matches
(empty)
75.8830%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
20
mean
35.4
std
14.71
cv
0.416
sampleLengths
0
39
1
39
2
49
3
22
4
37
5
10
6
19
7
34
8
29
9
51
10
24
11
50
12
32
13
20
14
46
15
42
16
50
17
10
18
36
19
69
100.0000%
Passive voice overuse
Target: ≤5% passive sentences
passiveCount
1
totalSentences
51
matches
0
"being made"
100.0000%
Past progressive (was/were + -ing) overuse
Target: ≤10% past progressive verbs
pastProgressiveCount
1
totalVerbs
114
matches
0
"was going"
94.0000%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
616
adjectiveStacks
1
stackExamples
0
"stark white against his"
adverbCount
12
adverbRatio
0.01948051948051948
lyAdverbCount
9
lyAdverbRatio
0.01461038961038961
100.0000%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
56
echoCount
0
echoWords
(empty)
100.0000%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
56
mean
12.64
std
5.64
cv
0.446
sampleLengths
0
27
1
12
2
10
3
16
4
13
5
15
6
34
7
6
8
6
9
10
10
17
11
5
12
11
13
4
14
10
15
19
16
11
17
12
18
11
19
11
20
8
21
10
22
19
23
19
24
13
25
11
26
11
27
2
28
10
29
9
30
8
31
15
32
8
33
15
34
8
35
9
36
7
37
13
38
18
39
16
40
12
41
10
42
10
43
22
44
11
45
12
46
13
47
14
48
10
49
12
100.0000%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
0
diversityRatio
0.6428571428571429
totalSentences
56
uniqueOpeners
36
0.0000%
Dialogue tag variety (said vs. fancy)
Target: ≤30% fancy dialogue tags
totalTags
7
fancyCount
5
fancyTags
0
"she muttered under her breath (mutter)"
1
"shouted (shout)"
2
"he replied, yanking a knife from his boot and clutching it tightly (reply, yank clutch)"
3
"he said, pulling a bone token from his pocket (say, pull)"
4
"Herrera said, leading them through the winding tunnels (say, lead)"
84.8307%