NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHMMEYTS6RKJ6Z17AG4B0E2A
Run Details
Model:
Hermes 3 405B
Test:
Bad Writing Habits
Scenario:
Thriller: chase through city streets
Duration:
1m 9s
Cost:
$0.001702
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
Detective Harlow Quinn charged through the rain-soaked Soho streets, her boots pounding the pavement in a staccato rhythm. Glass towers,
gleaming
even in the darkness,
loomed
over her, indifferent to the late-night drama unfolding beneath them. Her brown eyes flashed with determination, narrowing at the fleeing silhouette ahead. Another blast of lightning turned the evening sky an electric shade of blue, suspending her target in midair for a split second. Thunder followed, and he vanished once more into the darkness. As she
navigated
the tangled alleyways, Harlow cursed silently, wishing for a glimpse of the stars, any celestial body to guide her way. But London skies were rarely so obliging. She could see nothing beyond the harsh orange of sodium vapour lights, ancient
sentinels
that kept
watch
over the unwary and unwanted. The man she pursued, Tomás Herrera, glanced back over his shoulder, making brief eye contact with Harlow. His eyes, warm brown and framed by curly dark hair, contradicted the cool calculation that crossed his face before he darted into an alleyway. His olive skin shone with sweat and rain, and the Saint Christopher medallion around his neck bounced with every step. His scar, pale against his forearm, was a cruel reminder of his past, a knife attack survived but not forgotten. Harlow knew of him, a former paramedic who had lost his license administering unauthorized treatments. She didn't understand then, but now she knew: he'd been helping those society refused to acknowledge, the ones who walked the line between myth and reality. She'd learned too much and lost too much in the process. Her partner's death still hung heavy around her neck, a
weight
she couldn't shake off. The sound of the Tube rumbled beneath her feet, the underground network a pulsing lifeline beneath the city. Tomás led her down a set of crumbling concrete steps, descending into a forgotten station. This place was abandoned, left to decay and darkness. Yet, as they plunged deeper, new sounds
began to
echo
around them: haggling voices, the clinking of goods, the hiss of secret conversations. They had entered the Veil Market. Hidden within the forgotten bowels of the city, the Market sold the impossible, the forbidden, the unknown. It thrived on the fringe of society, existing in the shadows and whispers. As Harlow stepped into the Market, she felt the
weight
of the bone token in her pocket. It had been a small victory, procuring it from the last bust. Now, it was her entry ticket into this underworld. The market bustled with activity, a secret world teeming with life. Shadowy figures moved among the stalls, their faces obscured by hoods, their voices hushed and urgent.
The air was thick with
the scent of mystery, a potent mix of spices and secrets. Goods of all kinds lay on display, enchanted artifacts, banned alchemical substances, information that could bring down empires or build them up. In the midst of this, Tomás had vanished. Harlow paused, her breathing heavy, her mind racing. She had come this far, but the decision to
delve
deeper into the Market wasn't one she could make
lightly
. This was unknown territory, a place where her badge held no power. She
was walking
into the belly of the beast, and she knew it. She glanced at her worn leather
watch
, a habitual check before plunging into the unknown. The decision weighed on her, the pros and cons seesawing in her mind. She thought of DS Morris, her lost partner, of the supernatural circumstances that led to his death. Answers waited for her down here, submerged in the shadows, veiled in secrecy. Harlow made her decision. She had come too far to back down now. She would follow Tomás, even if it meant stepping into the unknown. She had to know the truth, whatever the cost.lıkları The rain continued to fall, but she was no longer there to feel it. Instead, she moved deeper into the Market, her senses alert, her resolve
unwavering
. The scar on her sharp jaw pulsed, a reminder of past battles, a promise of those to come. She was Detective Harlow Quinn, and she would find the truth, no matter where it lay buried.
created_at
"2026-02-17T01:48:07.704054+00:00"
2/17/2026, 1:48:07 AM
model
"nousresearch/hermes-3-llama-3.1-405b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
11725
moderation_latency
(null)
generation_time
68640
tokens_prompt
949
tokens_completion
1056
native_tokens_prompt
818
native_tokens_completion
884
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
0.001702
router
(null)
provider_responses
0
id
"cmpl-d3b31dc24df3496495a24aa15d5e5bb1"
status
200
is_byok
false
latency
75
endpoint_id
"3280e8f8-0960-400c-8284-2e03a0bcb446"
provider_name
"DeepInfra"
model_permaslug
"nousresearch/hermes-3-llama-3.1-405b"
api_type
"completions"
id
"gen-1771292818-f1hIxd2AXYt8xCqdtja1"
upstream_id
"cmpl-d3b31dc24df3496495a24aa15d5e5bb1"
total_cost
0.001702
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
0
adverbTagCount
0
adverbTags
(empty)
85.7347%
AI-ism adverb frequency
Target: <1% AI-ism adverbs (57 tracked)
wordCount
701
totalAiIsmAdverbs
1
found
0
adverb
"lightly"
count
1
highlights
0
"lightly"
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)
0.0000%
AI-ism word frequency
Target: <1% AI-ism words (140 tracked)
wordCount
701
totalAiIsms
9
found
0
word
"sentinels"
count
1
1
word
"gleaming"
count
1
2
word
"loomed"
count
1
3
word
"unwavering"
count
1
4
word
"weight"
count
2
5
word
"delve"
count
1
6
word
"echo"
count
1
7
word
"navigated"
count
1
highlights
0
"sentinels"
1
"gleaming"
2
"loomed"
3
"unwavering"
4
"weight"
5
"delve"
6
"echo"
7
"navigated"
100.0000%
Cliche density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"air was thick with"
count
1
highlights
0
"The air was thick with"
100.0000%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
46
matches
(empty)
100.0000%
Filter word density
Target: ≤12% sentences with filter/hedge words
filterCount
1
hedgeCount
1
narrationSentences
46
filterMatches
0
"watch"
hedgeMatches
0
"began to"
100.0000%
Overuse of "that" (subordinate clause padding)
Target: ≤10% sentences with "that" clauses
thatCount
0
totalSentences
46
matches
(empty)
83.7905%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
12
mean
58.25
std
25.82
cv
0.443
sampleLengths
0
80
1
52
2
81
3
67
4
65
5
6
6
68
7
65
8
8
9
53
10
58
11
96
100.0000%
Passive voice overuse
Target: ≤5% passive sentences
passiveCount
0
totalSentences
46
matches
(empty)
100.0000%
Past progressive (was/were + -ing) overuse
Target: ≤10% past progressive verbs
pastProgressiveCount
1
totalVerbs
112
matches
0
"was walking"
100.0000%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
701
adjectiveStacks
0
stackExamples
(empty)
adverbCount
18
adverbRatio
0.025677603423680456
lyAdverbCount
5
lyAdverbRatio
0.007132667617689016
100.0000%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
46
echoCount
0
echoWords
(empty)
77.6166%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
46
mean
15.2
std
5.23
cv
0.344
sampleLengths
0
18
1
18
2
12
3
22
4
10
5
23
6
7
7
22
8
17
9
24
10
20
11
20
12
15
13
26
14
11
15
15
16
18
17
15
18
9
19
23
20
6
21
17
22
13
23
17
24
12
25
9
26
11
27
16
28
16
29
22
30
8
31
8
32
20
33
12
34
13
35
15
36
13
37
17
38
13
39
4
40
9
41
12
42
23
43
13
44
18
45
17
70.2899%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
6
diversityRatio
0.5
totalSentences
46
uniqueOpeners
23
100.0000%
Dialogue tag variety (said vs. fancy)
Target: ≤30% fancy dialogue tags
totalTags
0
fancyCount
0
fancyTags
(empty)
89.2607%