NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHMQVP9MMZHXDMYZNHR4CC9A
Run Details
Model:
o4 Mini High
Test:
Bad Writing Habits
Scenario:
Literary fiction: old friends reunite
Duration:
53.4s
Cost:
$0.033757
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
Aurora Carter paused under the green neon glow of The Raven’s Nest, the sign
flicker
ing like a pulse in the damp London air. She tightened the collar of her leather jacket against a sharp gust before pushing open the door. The bar’s hush swallowed her, thick with the low drone of jazz spilling from unseen speakers and the clink of glass. Maps lined the walls—faded parchment lines tracing borders she’d once studied in law school, now half-forgotten. Black-and-white photographs, too: grainy faces and places she didn’t recognize. It all felt achingly familiar and
utterly
foreign. She stepped inside, boots squeaking on the scuffed wood floor. A man stood at the far end, back turned, polishing a tumbler with a ragged cloth. The amber light caught the silver
glint
of a signet ring on his right hand. His auburn hair
was shot
through with grey, and the slow way he shifted his
weight
onto his good leg set her pulse thudding in her ears. After so long, it still carried that old rhythm—like she’d never left. His limp had eased over time but hadn’t vanished. She remembered the uneven stride from years ago, when he’d carried her across the rooftops of Prague, one arm around her waist, the other gripping a pistol. She’d thought him invincible then. The limp had felt like weakness. Now it was barely a whisper, and she felt it more keenly still: his fragility and her own. He straightened, set the glass aside. She recognized the angle of his shoulders, the tilt of his head as he studied her. His hazel eyes met her bright blue ones with an expression of stunned recognition. For a heartbeat, neither spoke. The bartender towels lingered in his hand like a nervous gesture, and her fingers itched at the scar on her left wrist—a small crescent moon pressed into skin, a reminder of a childhood accident she’d never mentioned. “Silas.” She exhaled the name, felt the
weight
of it. “Aurora,” he said, voice low, measured. He paused. “Is that
really
you?” She forced a nod, felt her throat tighten. Three years, eight months, seventeen days since she’d slipped out of his world. She’d counted every one of them. “I—didn’t expect to see you here.” He cleared his throat and set the towel down. “I thought you moved on, London delivery and all.” She shifted, brushing a strand of straight black hair behind her ear. “I did. I work for Yu-Fei Cheung now. Golden Empress deliveries. Keeps me busy.” She
tried to
sound casual, but the only thing she’d delivered lately was regrets. He lifted a brow. “Golden Empress. I’ve heard. Best dumplings on Shaftesbury.” His gaze
flicked
to her jacket. “Still running missions on the side?” Her heart skipped. He remembered. She swallowed. “No. That life… it stopped for me.” He nodded once, as if he’d anticipated the answer. He resumed polishing the glass, slow and deliberate. “You left without a word.” She winced. He was right. She’d vanished one night in Prague, taken the next flight to Cardiff, enrolled in pre-law courses, pretended nothing had happened. But the memory of his face, the
flicker
in his eyes when she walked away… she’d never been able to forget. “I was scared,” she whispered. “I thought I was protecting you.” He glanced up, surprised. “Protecting me?” “I was in over my head. You had protocols, networks, rules I couldn’t follow. I… I walked away so you wouldn’t get tangled in my mess.” She tucked a hand into her pocket, thumb brushing the edge of her scar. “It was selfish.” He set the glass on the counter in front of him, fingers lingering on the rim. “You saved my life more than once,” he said quietly. “You think that’s selfish?” He touched the signet ring at his side, then unclasped it and placed it on the bar between them. “This was my father’s. I was going to give it to you.” His voice cracked. “After Prague. Before you left.” She stared at the ring—silver band, crest of a raven in mid-flight—her breath catching. “Silas… I’m sorry.” He shook his head, massaging his right wrist. “Don’t. You did what you thought right. But it hurt. I spent months—maybe years—wondering if you’d been taken. If I could have done something.” His eyes darkened. “I couldn’t reach you.” She
clenched her fists
. “I’m here now.” The words tasted brittle. “I’m not running any more.” He slid the ring closer, as if offering it across a chasm. She hesitated, then lifted her hand, fingertip brushing the cold metal. It pulsed, almost like a heartbeat. She pulled back. “I can’t take this.” He exhaled
sharply
, the sound trembling in the hush. “Then let me keep it.” He wrapped fingertips around the band. “It reminds me you’re alive.” She searched his face—the neat lines around his eyes, the limp that spoke of a knee blown out in Prague, the beard trimmed to match his grey-streaked hair—and felt the years between them
unravel
. “You look older,” she said
softly
. He offered a half-smile, a faint bow of his head. “I believe the term is distinguished.” She allowed herself a small laugh, bitter and warm. “Distinguished.” The syllable felt heavy. “I… I didn’t mean to vanish. London was supposed to be my fresh start.” He tilted his head, listening. “How’s Cardiff to London suit you?” She shrugged, sliding her gaze to the battered barstools behind her. “Quiet. Predictable. I like knowing I’ll see the same customers, same streets. There’s a comfort in routine.” He nodded, assessing her. “I’ve got a flat above the bar if you ever need a place to crash. No strings.” She blinked. “You’re offering me hospitality now?” He leaned back, resting both hands on the wood. “Consider it repayment for getting us out of that alley behind the Vltava,” he said, a wry twang in his tone. “Though next time I’d appreciate a heads-up before you vanish.” She closed her eyes, memories flooding: gunmetal rain, his crutch-boot scraping stones, the two of them panting for breath after a firefight. She swallowed hard. “I’m sorry,” she repeated. “I thought I was saving you. But maybe I just saved myself.” He watched her, expression
unreadable
. Then he offered a glass. Whiskey, neat. “To saving ourselves,” he said. His voice was gentle, but she sensed the grit beneath it. She lifted the glass, hesitated over the amber liquid, then took a long swallow. Fire bloomed in her chest, courage along with it. He leaned sideways, propping his good leg on the bottom rung of a stool. The limp was nearly invisible. “You ever think about going back? To the old network, I mean?” She shook her head. “I’m done running errands for shadows.” Her gaze
flicked
to the bookshelf at the back of the room—the one she’d never noticed before—its spines brimming with leather-bound volumes. Hidden somewhere behind it was the secret room where he held
clandestine
meetings. She imagined cold lamps, hushed voices. She shuddered. “I don’t miss it.” His jaw set. “Fair enough.” He frowned. “But if trouble finds you—if Evan catches up with you—you let me know.” She stiffened at his mention of her ex. She’d worked so hard to escape. Talking about him… it was like ripping the wound open. She managed a nod. “I will.” He held her gaze for a moment longer, then he reached out and slid the whiskey glass aside. “I won’t lie. I’ve missed you. Even when I didn’t let myself admit it.” Her breath hitched. “I’ve missed you, too.” The
weight
of years stilled the air between them. The bar’s murmur receded; the neon sign downed its
flicker
. For the first time since she’d opened the door, she felt unguarded. Silas straightened, clearing a space on the counter. “Sit,” he said simply. She hesitated, then lowered onto the stool he’d vacated. He stood to pour a second glass, careful with the bottle, brows
furrowed
in concentration. When he set it before her, he offered a tentative smile. “To old friends and new beginnings.” She raised her glass again, their rims clinking. She let the warmth spread through her, tasting whiskey and hope. Outside, Soho’s night scurried on, oblivious. Inside The Raven’s Nest, two lives converged once more—bound by the scars of memory, the ache of regret, and the fragile promise of forgiveness.
created_at
"2026-02-17T02:47:14.98086+00:00"
2/17/2026, 2:47:14 AM
model
"openai/o4-mini-high-2025-04-16"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
10689
moderation_latency
(null)
generation_time
53274
tokens_prompt
867
tokens_completion
2738
native_tokens_prompt
808
native_tokens_completion
7470
native_tokens_completion_images
0
native_tokens_reasoning
5504
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
0.0337568
router
(null)
provider_responses
0
id
"resp_091dc2ba2d7583ab016993d67d5000819496984faf1a29a830"
status
200
is_byok
false
latency
141
endpoint_id
"60020533-2fb2-4aa1-9454-181029fd52de"
provider_name
"OpenAI"
model_permaslug
"openai/o4-mini-high-2025-04-16"
api_type
"completions"
id
"gen-1771296381-sTehawZu2HbUKN8QrNRU"
upstream_id
"resp_091dc2ba2d7583ab016993d67d5000819496984faf1a29a830"
total_cost
0.0337568
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
8.3333%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
8
adverbTagCount
3
adverbTags
0
"he said quietly [quietly]"
1
"she said softly [softly]"
2
"he said simply [simply]"
71.7314%
AI-ism adverb frequency
Target: <1% AI-ism adverbs (57 tracked)
wordCount
1415
totalAiIsmAdverbs
4
found
0
adverb
"sharply"
count
1
1
adverb
"softly"
count
1
2
adverb
"utterly"
count
1
3
adverb
"really"
count
1
highlights
0
"sharply"
1
"softly"
2
"utterly"
3
"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)
15.1943%
AI-ism word frequency
Target: <1% AI-ism words (140 tracked)
wordCount
1415
totalAiIsms
12
found
0
word
"flicker"
count
2
1
word
"flicked"
count
2
2
word
"glint"
count
1
3
word
"clandestine"
count
1
4
word
"unreadable"
count
1
5
word
"furrowed"
count
1
6
word
"weight"
count
3
7
word
"unravel"
count
1
highlights
0
"flicker"
1
"flicked"
2
"glint"
3
"clandestine"
4
"unreadable"
5
"furrowed"
6
"weight"
7
"unravel"
100.0000%
Cliche density
Target: ≤1 cliche(s) per 800-word window
totalCliches
1
maxInWindow
1
found
0
label
"clenched jaw/fists"
count
1
highlights
0
"clenched her fists"
100.0000%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
0
narrationSentences
109
matches
(empty)
100.0000%
Filter word density
Target: ≤12% sentences with filter/hedge words
filterCount
0
hedgeCount
1
narrationSentences
109
filterMatches
(empty)
hedgeMatches
0
"tried to"
100.0000%
Overuse of "that" (subordinate clause padding)
Target: ≤10% sentences with "that" clauses
thatCount
0
totalSentences
138
matches
(empty)
100.0000%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
42
mean
33.14
std
20.85
cv
0.629
sampleLengths
0
95
1
80
2
65
3
78
4
10
5
12
6
27
7
24
8
40
9
24
10
14
11
22
12
46
13
11
14
6
15
43
16
69
17
17
18
39
19
16
20
36
21
25
22
40
23
16
24
28
25
11
26
28
27
21
28
7
29
40
30
41
31
28
32
23
33
31
34
57
35
20
36
30
37
32
38
7
39
31
40
53
41
49
100.0000%
Passive voice overuse
Target: ≤5% passive sentences
passiveCount
1
totalSentences
109
matches
0
"was shot"
100.0000%
Past progressive (was/were + -ing) overuse
Target: ≤10% past progressive verbs
pastProgressiveCount
0
totalVerbs
196
matches
(empty)
100.0000%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1054
adjectiveStacks
0
stackExamples
(empty)
adverbCount
39
adverbRatio
0.03700189753320683
lyAdverbCount
11
lyAdverbRatio
0.010436432637571158
100.0000%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
138
echoCount
0
echoWords
(empty)
100.0000%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
138
mean
10.09
std
7.43
cv
0.737
sampleLengths
0
23
1
17
2
21
3
16
4
10
5
8
6
10
7
16
8
15
9
27
10
12
11
9
12
27
13
5
14
6
15
18
16
6
17
16
18
14
19
5
20
37
21
10
22
6
23
2
24
4
25
8
26
13
27
6
28
15
29
9
30
12
31
28
32
4
33
14
34
6
35
3
36
2
37
2
38
7
39
9
40
8
41
5
42
2
43
3
44
20
45
15
46
6
47
5
48
6
49
4
41.3043%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
12
diversityRatio
0.2971014492753623
totalSentences
138
uniqueOpeners
41
0.0000%
Dialogue tag variety (said vs. fancy)
Target: ≤30% fancy dialogue tags
totalTags
8
fancyCount
6
fancyTags
0
"he said, voice low, measured (say, voice)"
1
"she whispered (whisper)"
2
"he said quietly (say quietly)"
3
"she said softly (say softly)"
4
"she repeated (repeat)"
5
"he said simply (say simply)"
78.6214%