NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHMQJXH9FVSWS4DVA5H4B34K
Run Details
Model:
GPT-4.1
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
28.2s
Cost:
$0.018362
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
Rain glossed the pavements along Greek Street, turning puddles into shallow pools of neon that rippled with every passing black cab. Aurora Carter stood beneath the jutting awning of The Raven’s Nest, tugging her coat tighter around her, hood masking the worst of the drizzle. The green neon above the door cast a sickly glow across her face,
glinting
off the tiny scar on her wrist where her sleeve rode up. She hesitated, measuring her reflection in the glass—just a moment—before ducking inside. The warmth and fug of old whisky met her first, followed by the slow murmur of voices, laughter smudged at the corners. The Nest had that tired, lived-in hush, maps curling behind smudged glass frames and photographs melted into sepia. Silas stood polishing a glass behind the bar, his broad shoulders
set, that limping
sway unmistakable as he set the tumbler aside and greeted her with a raised brow. Aurora flashed him a smile—small, habitual, grateful for its simplicity—and slid onto a stool near the wall. “How’s the leg, Si?” she asked. “Predictably mutinous.” His mouth twitched beneath his greying beard. “You’re late tonight. Everything all right at Golden Empress?” “Yu-Fei’s new driver clipped a cyclist. Put dinner back forty minutes.” She shrugged off her coat, setting it
deliberately
across her lap. London seeped into her bones in winter, and she couldn’t shake the sense of being damp, unfinished, as though she hadn’t quite arrived. Silas set a mug of tea before her—a ritual, not even needing to ask. “This one’s on me.” She returned the favor with a nod, fingers circling the
porcelain
for warmth, but before she could draw a breath or a story, the door shuddered open and someone stepped through—a man, taller than her by a head, his trench coat soaking, hair gone nearly silver. For a moment, Aurora’s body tensed; he had the cautious, scanned-unfamiliarity of someone seeking shelter not
solace
. Then hazel eyes swept the bar, cutting a wake, and she knew him. Oscar. She hadn’t seen him—what, six years? Seven? It had been Bristol, a festival bleeding into breakup, laughter tangled with the sour taste of last words. Oscar had changed. Gone was the lean, eager figure of their university days. His face was sharper, smile lines scored deeper, and weary creases owned the corners of those once-too-expressive eyes. Even his clothes looked more expensive and less approachable—instead of badges and bright jumpers, navy and charcoal,
watch
face
glinting
severe under the dim light. He paused, halfway to the bar. His gaze
flickered
—uncertain—and then recognition kindled, cautious and threaded with something else. Regret, maybe, or old rivalry. Aurora forced herself not to shrink, not to check her posture. Instead, she lifted her tea, offering the fragile pretense of habit. “Oscar?” she said, voice tentative but steady. He looked straight at her,
unreadable
for an instant—then the hard lines ebbed and a ghost of the old grin surfaced. “I didn’t think you were still in London.” “Didn’t plan to be,” she said. “But plans are funny that way.” He glanced at Silas, the old bar routine already half-familiar, before pulling out the stool beside her. The squeal of the leg across tile was louder than conversation. For a while, neither spoke; the
weight
of coincidence filled the air between them, warmer than the radiator, sharper than his cologne. “It’s been a while,” Oscar said, almost an accusation. Aurora kept her eyes on him, tracing the places that had gotten harder, rougher, the way his mouth pressed into a careful line before he spoke. “Seven years, give or take.” “Long time.” He toyed with the coaster. “You look… different.” Then, as if apologizing for honesty, “Good different.” She couldn’t help the smirk. “Hair’s shorter. World got bigger. You know how it goes.” He lifted his chin, not quite smiling. “I do. Fair to say we’re both a little… worn in.” That drew a laugh, short and genuine. “Grown up, you mean?” “Something
like that.” He
let the silence stretch. “Do you still… draw? I remember you used to cover your notes in little birds and maps.” Her fingers twitched reflexively at the memory. “Not
really
. No time for paper. I make lists instead—the boring kind. Grocery, hours, delivery routes, things not to forget.” She took another sip. “And you? I heard you went into consulting. Or was it politics?” Oscar grimaced. “Consulting. All numbers and strategy meetings. They pay you to talk until no one remembers what question they asked.” “I don’t
know, that sounds
like a superpower.” Her words were light, but regret hid in the cadence. They’d talked so much, once—debates at three a.m., sprawled on cheap carpet, the city swelling outside. She wondered if he heard it too, that ache for things unsaid. He leaned closer, elbows pressed to the bar. “I missed you, you know. For a while.” The admission dangled, heavy as a confession, and she felt its
echo
in her chest. “Yeah.” Aurora set her mug down, turning it
slowly
. “I missed you too. At least, I missed… the possibility.” He frowned. “Possibility?” “Of things turning out different. Of not losing touch.” She stared at her wrist, at the white scar, remembering softer days—the ones before escape became habit, before she measured her life in train fares and rainy windows. “We were good once, weren’t we?” Oscar allowed himself a small, real smile. “We were. Back then, you made it seem like you could redraw the world if you wanted.” She shook her head, gaze fixed stubbornly to the bar. “You only remember the sketches. Not the ones I tore up.” “No.” His voice had roughened, eyes catching the memory. “I remember the warnings. I just thought you’d outgrow them.” Aurora stiffened. “That’s the thing about warnings, Oscar. They’re not shoes you grow into.” He sat back, his composure faltering. “You always had a line for everything.” He tried for levity but couldn’t hide the ruefulness. “God, Rory—you still hate being called Aurora?” That old nickname tugged at her, a silver thread from an old jumper. “No. Not anymore. Laila, Aurora—take your pick. The world forgets your name if you let it.” He looked away, into the shadows. Silas
was stacking
bottles at the far end, hands
methodical
, but Aurora caught him
watch
ing—checking, as he often did, for signals she was all right. She shot him a tiny nod. Oscar
watch
ed the exchange, brow
furrowed
. “He looks after you?” “As much as anyone can,” she said. “London’s a different beast than Cardiff. Or Bristol.” He dragged a hand down his face. “Funny. Last time I came here, I thought I had it all figured out. Job, flat, girlfriend. Now it’s just… noise.” “People don’t like to talk about entropy in their twenties,” Aurora said. “But eventually the house gets messy.” His smile was bruised. “Yours too?” She laughed, but there was nothing sharp left in it. “Mine
started that way
.” A long, stubborn pause unfurled. Old albums hummed overhead. In another life she’d have bridged it with a joke, or a dare, or a promise. Instead, she let it stretch until something revealed itself in the quiet—fragile and ordinary. He gestured at her mug. “You want another?” She shrugged. “I’m working.” A lie. She just didn’t want him to buy her something and make it about old debts. He
seemed to
understand, winding the coaster in circles beneath one finger. “You’re still stubborn.” “Saves on therapy.” She met his gaze, daring him to laugh. “You regret it?” She didn’t say which: leaving, staying, letting years rot between them. Oscar blinked, sudden stormy. “All the time. Most days I pretend I don’t.” Aurora pressed her palms flat to the bar, fighting the urge to recoil. “You shouldn’t. People outgrow the past. Whether they want to or not.” “Is that what you did? Outgrow me?” The question caught her between nerves and nostalgia. She turned the answer over, slow, as though some part of her might flinch at the sting. “No. I just learned how to carry it better.” She closed her eyes. “You look tired, Oscar.” He barked out a laugh, at once relieved and helpless. “It’s harder to start over at thirty than they tell you. You know what I miss most?” She looked at him fully then, searching his face for remnants of the wild boy she’d known: the one who joked to drown out the pressure of exams, who drank triple espressos at noon and wrote poetry on receipts. “What?” “The certainty. The way we believed everything would matter.” He tipped his head, voice quieter. “You always acted like you knew the secret. Did you?” She wanted to say yes, to gift him the comfort he’d offered her once. But she shook her head, a sad smile settling in. “No. I pretended.” They sat, joined by the hush of the old bar and years stitched tight with silence. For a while their memories made them young, and when Aurora rose to leave, she did not look back. The rain had let up. The city outside had changed while they’d spoken—older, maybe, but still bright, still possible—even if neither of them quite remembered how to claim it.
created_at
"2026-02-17T02:42:02.291952+00:00"
2/17/2026, 2:42:02 AM
model
"openai/gpt-4.1-2025-04-14"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
759
moderation_latency
(null)
generation_time
28069
tokens_prompt
867
tokens_completion
2473
native_tokens_prompt
809
native_tokens_completion
2093
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
0.018362
router
(null)
provider_responses
0
id
"resp_0350ad66394c1c7a016993d55dcde0819097b4b1a0be8ded4d"
status
200
is_byok
false
latency
108
endpoint_id
"c235abe8-11cc-42d3-95ad-72f4d198287a"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-4.1-2025-04-14"
api_type
"completions"
id
"gen-1771296093-ASwma0NsRpiu6RjLX6IK"
upstream_id
"resp_0350ad66394c1c7a016993d55dcde0819097b4b1a0be8ded4d"
total_cost
0.018362
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
38.0952%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
7
adverbTagCount
2
adverbTags
0
"Oscar said, almost an accusation [almost]"
1
"Then, as if apologizing for honesty [Then,]"
80.7322%
AI-ism adverb frequency
Target: <1% AI-ism adverbs (57 tracked)
wordCount
1557
totalAiIsmAdverbs
3
found
0
adverb
"deliberately"
count
1
1
adverb
"slowly"
count
1
2
adverb
"really"
count
1
highlights
0
"deliberately"
1
"slowly"
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)
35.7739%
AI-ism word frequency
Target: <1% AI-ism words (140 tracked)
wordCount
1557
totalAiIsms
10
found
0
word
"flickered"
count
1
1
word
"glinting"
count
2
2
word
"porcelain"
count
1
3
word
"methodical"
count
1
4
word
"unreadable"
count
1
5
word
"solace"
count
1
6
word
"furrowed"
count
1
7
word
"weight"
count
1
8
word
"echo"
count
1
highlights
0
"flickered"
1
"glinting"
2
"porcelain"
3
"methodical"
4
"unreadable"
5
"solace"
6
"furrowed"
7
"weight"
8
"echo"
100.0000%
Cliche density
Target: ≤1 cliche(s) per 800-word window
totalCliches
0
maxInWindow
0
found
(empty)
highlights
(empty)
100.0000%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
95
matches
(empty)
100.0000%
Filter word density
Target: ≤12% sentences with filter/hedge words
filterCount
1
hedgeCount
1
narrationSentences
95
filterMatches
0
"watch"
hedgeMatches
0
"seemed to"
100.0000%
Overuse of "that" (subordinate clause padding)
Target: ≤10% sentences with "that" clauses
thatCount
4
totalSentences
131
matches
0
"set, that limping"
1
"like that.” He"
2
"know, that sounds"
3
"started that way"
100.0000%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
55
mean
27.85
std
18.72
cv
0.672
sampleLengths
0
83
1
86
2
6
3
18
4
45
5
18
6
76
7
26
8
56
9
45
10
7
11
29
12
12
13
50
14
9
15
31
16
18
17
15
18
18
19
11
20
25
21
43
22
21
23
46
24
31
25
19
26
3
27
43
28
24
29
21
30
19
31
14
32
29
33
29
34
37
35
10
36
15
37
28
38
18
39
6
40
14
41
39
42
8
43
21
44
15
45
25
46
13
47
25
48
7
49
42
100.0000%
Passive voice overuse
Target: ≤5% passive sentences
passiveCount
0
totalSentences
95
matches
(empty)
100.0000%
Past progressive (was/were + -ing) overuse
Target: ≤10% past progressive verbs
pastProgressiveCount
1
totalVerbs
209
matches
0
"was stacking"
100.0000%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1114
adjectiveStacks
0
stackExamples
(empty)
adverbCount
40
adverbRatio
0.03590664272890485
lyAdverbCount
7
lyAdverbRatio
0.0062836624775583485
100.0000%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
131
echoCount
0
echoWords
(empty)
100.0000%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
131
mean
11.69
std
7.95
cv
0.679
sampleLengths
0
21
1
24
2
26
3
12
4
22
5
18
6
29
7
17
8
6
9
9
10
9
11
22
12
23
13
14
14
4
15
46
16
17
17
13
18
1
19
6
20
1
21
18
22
3
23
10
24
18
25
25
26
6
27
12
28
5
29
11
30
11
31
7
32
21
33
8
34
6
35
6
36
17
37
11
38
22
39
9
40
26
41
5
42
7
43
11
44
5
45
10
46
7
47
11
48
7
49
4
67.1756%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
2
diversityRatio
0.4122137404580153
totalSentences
131
uniqueOpeners
54
100.0000%
Dialogue tag variety (said vs. fancy)
Target: ≤30% fancy dialogue tags
totalTags
7
fancyCount
1
fancyTags
0
"Then, as if apologizing for honesty (apologize)"
89.5163%