NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHMRCSTCHXTGCPVQZNBM3NSY
Run Details
Model:
GPT-4.1 Mini
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
19.9s
Cost:
$0.002612
Provider:
OpenAI
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="4412" name="Aurora Carter" aliases="Rory, Laila, Aurora, Carter, Malphora" pronouns="she/her" species="Human" storyRole="Protagonist"> <eyeColor>bright blue</eyeColor> <hair>straight shoulder-length black</hair> <height>5'6"</height> <age>25</age> <scar>small crescent-shaped scar on her left wrist from a childhood accident</scar> <description>Aurora, referred to by her friends as Rory, is cool-headed, intelligent, and known for quick out-of-the-box thinking.</description> <backstory>Born in Cardiff to an Irish barrister father (Brendan Carter) and Welsh teacher mother (Jennifer Carter née Ellis), Rory reluctantly pursued Pre-Law at Cardiff University. She fled to London at the behest of her childhood friend Eva after leaving an abusive ex named Evan. By day, Rory works part-time as a delivery person for Yu-Fei Cheung's Golden Empress restaurant. She lives in a flat above Silas' bar.</backstory> </character> <character id="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</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> </codex> Write a fully fleshed out scene of at least 1000 words in the literary fiction genre. Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret. 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
The green neon glow buzzed
softly
above the entrance to The Raven’s Nest, casting a sickly light on the cracked pavement of Old Compton Street. Inside, the bar carried the familiar scent of aged wood and spilled whiskey—a graveyard of forgotten nights. Aurora Carter pushed open the heavy door, the faint
echo
of her shoes clipping against the hardwood floor as she stepped inside, shoulder-length black hair tucked behind one ear. She paused, eyes adjusting to the dim light, taking in the scene. The walls
were lined
with old maps—some curling at the edges—and black-and-white photographs capturing moments long past, ghosts captured behind glass and silver. Her gaze
flicked
past the cluttered tables to the bar, where a man stood polishing a glass with the slow, sure patience of rehearsed routine. Silas Blackwood. The man had changed since the last time they’d seen each other—years ago now, before the blackened edges of London chilled her own bones, before the bruises Evan left hung unseen beneath her clothes. The auburn of his hair had silvered like dust settling over a forgotten tome. A slight limp pulled at his left leg as he moved. His hazel eyes caught hers across the room, steady and
unreadable
,
a flicker of recognition
tracing their surface like a shadow under still water. Rory’s heart tightened. She half-expected him to say something sharp, cold in the way old friends sometimes are when stretched thin by time and silence. Instead, his lips pulled into a slow, composed smile—a quiet invitation she didn’t feel ready to accept but walked toward anyway. “Rory,” he said, voice low and measured. “Long time.” She swallowed, feeling the
weight
of that phrase settle around her shoulders like a cloak. “Silas.” His eyes searched hers for a moment longer, as if confirming the girl she’d
been was
the woman now standing before him—a stranger forged from the same copper and smoke. “Come, sit.” His hand gestured toward an empty booth near the back, away from the few scattered patrons nursing their drinks and tired conversations. Rory slid into the seat opposite him, the old leather creaking under her. She wrestled with the familiar surge of nerves, the unease of standing on a precipice of unsaid words. “How long has it been?” she asked finally, voice careful, as if the answer might fracture the moment. “Nearly six years,” Silas replied. He ran a hand through the streaked auburn curls, then folded them on the table. “You look well.” She lifted her wrist subtly, the small crescent-shaped scar catching the
flicker
ing light. “Life’s been... complicated.” Silas nodded, the line of his mouth tightening just
slightly
. “I heard about Evan.” Her throat constricted. The past was a shadow she’d left behind her, but it still clung. “It’s over.” He studied her, his gaze tender but unyielding. “For what it’s worth, I’m glad you’re out.” Rory’s eyes dipped to the scar. “I didn’t expect to see you here.” “I don’t get out much.” His faint smile
was edged
with self-mockery. “The Nest has been my corner of the world for years now. A front, some say, for what remains of my old life.” His eyes gleamed mischievously, though shadows lurked beneath. “Spies never
really
retire. We just change battlegrounds.” She nodded, sensing the layers beneath. Silas had always been a man of secrets and scars—visible and otherwise. And yet, here he was, a quiet bulwark against the chaos she’d been running from. “I’ve been working deliveries,” she said, her voice gaining strength as she spoke. “Part-time at a restaurant down near Chinatown. Helps me keep my head above water.” “And London?” he asked, never taking his eyes off her. “London’s been both—a refuge and a
weight
.” She smiled tenuously, the tension easing just a fraction. “Eva’s been a lifeline.” Silas tapped the silver signet ring on his right hand against the table. “It’s strange, isn’t it? How people drift apart and then collide again like suns—burning with the past but unwilling to fizzle out.” Rory met his gaze, and for a heartbeat she saw in him not the spymaster of old tales, but a man shaped by time and regret. “Why did you leave, Si? After... everything?” He sighed, the motion slow and deliberate, as if releasing a breath held for a decade. “After Prague, I thought I could disappear. I was wrong. There are pieces of me scattered across the continent—pieces I can’t reclaim but must carry. The Nest... it’s my way of holding on. And maybe, in a twisted way, my penance.” She folded her hands over the scar, feeling its smooth curve under her skin. “I’ve been carrying my own pieces, some broken and sharp. Evan made sure of that.” Silas reached out, a rough hand hovering an inch from hers but never quite touching. “You’re stronger than you know, Rory.” A
flicker
of the girl she once
was surged
to the surface—the girl who had dreamed of law and justice before life became survival. The blue of her eyes caught his hazel, both of them measuring what had
been lost
and what, miraculously, remained. “Do you ever regret it?” she asked. “The life you left?” He pondered, his gaze distant. “Regret is a luxury for those who think they had a choice. I made mine. Sometimes I wish I’d made it differently. But the past... the past shapes the edge we walk on. Without it, there’s nothing.” “Maybe that’s why I’m here,” Rory whispered. “To find a new edge. To stop running.” Silas inclined his head, respect and something gentler folding into his expression. “The Nest will always have a corner for you, Rory. You’re safer here.” A silence stretched between them—not uncomfortable, but charged, a fragile truce carved out of years lost. “Do you still think about Cardiff?” she asked, voice barely above the hum of the bar. “Every day,” he said. “But London… London is home now. The memories, the mistakes—they live within these walls. And sometimes, they talk.” Rory smiled, a real one that cracked through the armor she’d worn for so long. “I’m glad we met again, Si.” His eyes softened. “Me too, Rory. Me too.” The neon outside
flickered
, casting
fragmented
light through the rain-streaked windows as past and present folded into the quiet hum of The Raven’s Nest. Two friends, scarred but unbroken, sat side by side in the shelter of shared silence, the
weight
of time no longer a chain but a bridge.
created_at
"2026-02-17T02:56:02.334644+00:00"
2/17/2026, 2:56:02 AM
model
"openai/gpt-4.1-mini-2025-04-14"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
494
moderation_latency
(null)
generation_time
19819
tokens_prompt
867
tokens_completion
1730
native_tokens_prompt
809
native_tokens_completion
1430
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
"completed"
usage
0.0026116
router
(null)
provider_responses
0
id
"resp_05f66a24fc348525016993d8adfddc8194af19add823a8b7d5"
status
200
is_byok
false
latency
127
endpoint_id
"872eccb7-9c85-45fc-974a-ff7c8e2407e6"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-4.1-mini-2025-04-14"
api_type
"completions"
id
"gen-1771296941-QYtSh29p51iu9BTGAlPP"
upstream_id
"resp_05f66a24fc348525016993d8adfddc8194af19add823a8b7d5"
total_cost
0.0026116
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
9
adverbTagCount
0
adverbTags
(empty)
72.6277%
AI-ism adverb frequency
Target: <1% AI-ism adverbs (57 tracked)
wordCount
1096
totalAiIsmAdverbs
3
found
0
adverb
"slightly"
count
1
1
adverb
"softly"
count
1
2
adverb
"really"
count
1
highlights
0
"slightly"
1
"softly"
2
"really"
100.0000%
AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0
"Blackwood"
found
(empty)
100.0000%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
8.7591%
AI-ism word frequency
Target: <1% AI-ism words (140 tracked)
wordCount
1096
totalAiIsms
10
found
0
word
"flickered"
count
1
1
word
"flicker"
count
2
2
word
"flicked"
count
1
3
word
"unreadable"
count
1
4
word
"fragmented"
count
1
5
word
"weight"
count
3
6
word
"echo"
count
1
highlights
0
"flickered"
1
"flicker"
2
"flicked"
3
"unreadable"
4
"fragmented"
5
"weight"
6
"echo"
100.0000%
Cliche density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"flicker of emotion"
count
1
highlights
0
"a flicker of recognition"
100.0000%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
55
matches
(empty)
100.0000%
Filter word density
Target: ≤12% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
55
filterMatches
(empty)
hedgeMatches
(empty)
100.0000%
Overuse of "that" (subordinate clause padding)
Target: ≤10% sentences with "that" clauses
thatCount
0
totalSentences
78
matches
(empty)
100.0000%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
40
mean
26.9
std
18.27
cv
0.679
sampleLengths
0
71
1
60
2
2
3
83
4
3
5
43
6
9
7
16
8
30
9
24
10
31
11
18
12
23
13
16
14
14
15
18
16
16
17
13
18
51
19
33
20
27
21
10
22
20
23
35
24
26
25
7
26
57
27
29
28
21
29
44
30
11
31
42
32
15
33
25
34
16
35
16
36
22
37
21
38
8
39
50
72.7273%
Passive voice overuse
Target: ≤5% passive sentences
passiveCount
5
totalSentences
55
matches
0
"were lined"
1
"been was"
2
"was edged"
3
"was surged"
4
"been lost"
100.0000%
Past progressive (was/were + -ing) overuse
Target: ≤10% past progressive verbs
pastProgressiveCount
0
totalVerbs
132
matches
(empty)
94.0000%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
784
adjectiveStacks
1
stackExamples
0
"small crescent-shaped scar"
adverbCount
24
adverbRatio
0.030612244897959183
lyAdverbCount
9
lyAdverbRatio
0.011479591836734694
100.0000%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
78
echoCount
0
echoWords
(empty)
100.0000%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
78
mean
13.79
std
8.98
cv
0.651
sampleLengths
0
25
1
17
2
29
3
12
4
23
5
25
6
2
7
34
8
14
9
11
10
24
11
3
12
22
13
21
14
7
15
2
16
15
17
1
18
30
19
24
20
13
21
18
22
18
23
5
24
15
25
3
26
13
27
3
28
10
29
4
30
3
31
13
32
2
33
8
34
8
35
6
36
7
37
12
38
31
39
8
40
6
41
12
42
15
43
13
44
14
45
10
46
16
47
4
48
13
49
22
72.2222%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
2
diversityRatio
0.44871794871794873
totalSentences
78
uniqueOpeners
35
91.6667%
Dialogue tag variety (said vs. fancy)
Target: ≤30% fancy dialogue tags
totalTags
9
fancyCount
3
fancyTags
0
"he said, voice low and measured (say, voice)"
1
"she said, her voice gaining strength as she spoke (say, gain speak)"
2
"Rory whispered (whisper)"
88.9414%