NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHMRCMWQ0E6HHMC0RK59Z2CF
Run Details
Model:
GPT-4.1 Mini
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
20.7s
Cost:
$0.002490
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 sign outside
flickered
erratically, casting a sickly glow onto the rain-slicked pavement. Inside The Raven’s Nest, the murmur of low conversations mingled with the clink of glasses and the faint scratch of jazz notes from the jukebox.
The air was thick with
warm woodsmoke and the bitter tang of spilled beer. Aurora stepped in, shoulders hunched against the London drizzle, her black hair damp and clinging to her face. She scanned the dim room, the scent of smoke and old paper grounding her as always. The familiar
weight
of the bar’s atmosphere folded over her like an old coat. Behind the worn oak counter, Silas Blackwood stood polishing a glass with
methodical
calm. His grey-streaked auburn hair caught the muted light, the silver signet ring on his right hand
gleaming
faintly with each stroke. The limp in his left leg remained subtle, but it was there—an
echo
of a past life buried beneath his poised exterior. He looked up from his glass and for a heartbeat, his gaze locked with hers. “Aurora,” he said, voice edged with surprise but steady, the faint traces of time softening the name like a well-worn book. She hesitated, the nickname threading through years of silent memories. “Si,” she replied
cautiously
, sliding onto a barstool, the leather creaking beneath her. Her bright blue eyes searched his face, cataloguing the changes—the lines
etched
deeper than she remembered, the garnered patience in his gaze, the absence of the lighter recklessness they once shared. “You’ve hardly changed,” he said, a small smirk tugging at his lips, though a
flicker
of something less charmed
flickered
in his hazel eyes. “Except maybe older. And quieter.” Aurora glanced at her hands, the small crescent-shaped scar on her left wrist catching the light, a private memento of a childhood that now felt like a distant country. “You noticed the quiet before I sat down.” Silas’s laugh was low, and the sound rippled around them like a fragile peace offering. “You always had a way with words. Still sharp as a tack.” She smiled briefly, but the warmth didn’t quite reach her eyes. “You haven’t changed much either,” she said. “Still
wearing that ring
. Still limping along.” He regarded her with a half-nod, as if acknowledging the truth she pushed between them. “Old habits die hard. And I suppose a limp is a reminder to pace myself.” The bartender’s eyes
flicked
briefly to a shadowed corner where a bookshelf leaned heavily against the wall, concealing the bar’s secret room. Rory remembered the many nights spent here, gathering rumors, plotting escapes with Silas’s quiet counsel. Now the room felt like it belonged to someone else, a relic of their separate histories. “Why now?” Silas asked finally, voice lowered as the noise of the bar gravitated away from their small space. “After all this time. You just walk back into the Nest like nothing’s changed?” Aurora’s gaze
wavered
, the
weight
of
unspoken
years pressing against her ribs. “I was close,” she said, each word deliberate, “to breaking. I stayed away because I didn’t want you to see what I’d become. Because I wasn’t sure I’d recognize myself.” Silas’s face softened, shadows drawing deeper into the hollows around his mouth and eyes. “You know, I never believed you lost yourself. Not
really
.” “Maybe not,” Rory replied. “But I felt like I was drowning in everything I ran from. Evan—the way he haunted my nights, the way his shadow followed me wherever I went. I left my studies, my family. I even helped deliver food to keep my head above water.” The mention of Evan hardening her will, Silas reached out and rested a hand briefly on hers. The touch
was reassuring
, not intrusive, a reminder of the friendship that had once promised endless possibilities. “I wish you’d reached out sooner,” he said quietly. “I could’ve helped.” She bit her lip, the familiar sting of regret. “I was scared. Scared you’d see the broken parts and turn away.” Silas’s smile was faint, but genuine. “I’ve seen broken parts before, Rory. It’s not the cracks that define us, but how we hold ourselves together.” The bartender slid a glass towards Silas—a neat pour of something amber, aged and steady. Silas nodded his thanks and returned his attention to her. “So, what brings you back into the city? Into the Nest?” Aurora pulled her sleeve down to hide the scar again, a reflex that didn’t need explanation. “Eva’s been pulling me back. She said home isn’t just a place—it’s where you find yourself. I’m still figuring out what that means, I guess.” Silas regarded her with a keen, insightful gaze, as if weighing the invisible scales of her truth. “Home is complicated.” “Tell me about it.” She laughed, the sound brittle but real. “I’m staying here. Above your bar. Maybe for a while. Part-time delivery, full-time trying-not-to-fall-apart.” He offered her a rare, wry smile. “You do things on your own terms. That hasn’t changed.” “And you,” she whispered, “what is it that holds you here? The bar? The memories? The shadows of MI6?” Silas’s eyes darkened
slightly
, a
flicker
of something
unreadable
crossing his face. “A bit of all that. But mostly the people. The ones who stumble in looking for something to hold onto. I’m here because someone has to watch the door.” For a long moment, silence wrapped between them, neither willing to break the fragile connection they’d re-established. Outside, the rain continued its relentless cadence, a rhythm that mirrored the passing of years—constant, unforgiving, yet oddly cleansing. Rory reached for the glass of water that Silas had pushed toward her. The liquid was cool and steady, a quiet anchor
amidst
the interior storm. “Maybe this time,” she said, her voice low, “we won’t have to run so far to find each other.” Silas lifted his glass in a gentle salute. “To finding ourselves, then. And to not losing the friends who remember the pieces.” They drank together, two lives converging again in the faint amber light of The Raven’s Nest—scarred but unbroken, waiting to chart the uncertain map of what lay ahead.
created_at
"2026-02-17T02:55:57.897779+00:00"
2/17/2026, 2:55:57 AM
model
"openai/gpt-4.1-mini-2025-04-14"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
583
moderation_latency
(null)
generation_time
20611
tokens_prompt
867
tokens_completion
1638
native_tokens_prompt
809
native_tokens_completion
1354
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
0.00249
router
(null)
provider_responses
0
id
"resp_07f352f15c3b4636016993d8a8f4dc8195816cf4598a165e3a"
status
200
is_byok
false
latency
172
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-1771296936-yqZcvNQCIrTasLv2Gvri"
upstream_id
"resp_07f352f15c3b4636016993d8a8f4dc8195816cf4598a165e3a"
total_cost
0.00249
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
72.7273%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
11
adverbTagCount
2
adverbTags
0
"she replied cautiously, sliding onto a barstool, the leather creaking beneath her [cautiously]"
1
"he said quietly [quietly]"
71.0704%
AI-ism adverb frequency
Target: <1% AI-ism adverbs (57 tracked)
wordCount
1037
totalAiIsmAdverbs
3
found
0
adverb
"cautiously"
count
1
1
adverb
"slightly"
count
1
2
adverb
"really"
count
1
highlights
0
"cautiously"
1
"slightly"
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)
0.0000%
AI-ism word frequency
Target: <1% AI-ism words (140 tracked)
wordCount
1037
totalAiIsms
15
found
0
word
"flickered"
count
2
1
word
"flicker"
count
2
2
word
"flicked"
count
1
3
word
"gleaming"
count
1
4
word
"wavered"
count
1
5
word
"methodical"
count
1
6
word
"unspoken"
count
1
7
word
"unreadable"
count
1
8
word
"weight"
count
2
9
word
"amidst"
count
1
10
word
"echo"
count
1
11
word
"etched"
count
1
highlights
0
"flickered"
1
"flicker"
2
"flicked"
3
"gleaming"
4
"wavered"
5
"methodical"
6
"unspoken"
7
"unreadable"
8
"weight"
9
"amidst"
10
"echo"
11
"etched"
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
48
matches
(empty)
100.0000%
Filter word density
Target: ≤12% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
48
filterMatches
(empty)
hedgeMatches
(empty)
100.0000%
Overuse of "that" (subordinate clause padding)
Target: ≤10% sentences with "that" clauses
thatCount
1
totalSentences
66
matches
0
"wearing that ring"
100.0000%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
29
mean
35.14
std
18.04
cv
0.513
sampleLengths
0
102
1
72
2
21
3
54
4
29
5
37
6
27
7
25
8
30
9
53
10
33
11
42
12
24
13
48
14
34
15
12
16
21
17
25
18
36
19
41
20
20
21
25
22
17
23
19
24
41
25
36
26
45
27
22
28
28
100.0000%
Passive voice overuse
Target: ≤5% passive sentences
passiveCount
0
totalSentences
48
matches
(empty)
100.0000%
Past progressive (was/were + -ing) overuse
Target: ≤10% past progressive verbs
pastProgressiveCount
1
totalVerbs
110
matches
0
"was reassuring"
94.0000%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
694
adjectiveStacks
1
stackExamples
0
"small crescent-shaped scar"
adverbCount
23
adverbRatio
0.03314121037463977
lyAdverbCount
12
lyAdverbRatio
0.01729106628242075
100.0000%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
66
echoCount
0
echoWords
(empty)
100.0000%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
66
mean
15.44
std
7.37
cv
0.477
sampleLengths
0
15
1
25
2
14
3
18
4
16
5
14
6
14
7
21
8
22
9
15
10
21
11
10
12
13
13
31
14
24
15
5
16
29
17
8
18
15
19
12
20
11
21
7
22
7
23
15
24
15
25
22
26
15
27
16
28
19
29
14
30
12
31
30
32
14
33
10
34
4
35
44
36
17
37
17
38
9
39
3
40
9
41
12
42
6
43
19
44
15
45
10
46
11
47
16
48
25
49
17
75.2525%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
2
diversityRatio
0.4696969696969697
totalSentences
66
uniqueOpeners
31
38.6364%
Dialogue tag variety (said vs. fancy)
Target: ≤30% fancy dialogue tags
totalTags
11
fancyCount
6
fancyTags
0
"he said, voice edged with surprise but steady, the faint traces of time softening the name like a well-worn book (say, edge soften like)"
1
"she replied cautiously, sliding onto a barstool, the leather creaking beneath her (reply cautiously, slide creak)"
2
"he said, a small smirk tugging at his lips, though a flicker of something less charmed flickered in his hazel eyes (say, tug charm flicker)"
3
"he said quietly (say quietly)"
4
"laughed (laugh)"
5
"she whispered (whisper)"
85.3933%