NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY978WG10Q84DQT4Y364KE9
Run Details
Model:
ByteDance Seed 1.6 Flash
Test:
Bad Writing Habits
Scenario:
Romance: separated couple reunites
Duration:
23.6s
Cost:
$0.000997
Provider:
Seed
Evaluation summary
Score
Evaluator
Details Link
100.00%
Adverbs in dialogue tags
(details)
96.02%
AI-ism adverb frequency
(details)
100.00%
AI-ism character names
(details)
100.00%
AI-ism location names
(details)
72.13%
AI-ism word frequency
(details)
100.00%
Cliché density
(details)
100.00%
Emotion telling (show vs. tell)
(details)
100.00%
Filter word density
(details)
100.00%
Gibberish response detection
(details)
98.47%
Markdown formatting overuse
(details)
100.00%
Missing dialogue indicators (quotation marks)
(details)
33.33%
Name drop frequency
(details)
100.00%
Narrator intent-glossing
(details)
100.00%
"Not X but Y" pattern overuse
(details)
100.00%
Overuse of "that" (subordinate clause padding)
(details)
100.00%
Paragraph length variance
(details)
100.00%
Passive voice overuse
(details)
100.00%
Past progressive (was/were + -ing) overuse
(details)
0.00%
Em-dash & semicolon overuse
(details)
100.00%
Purple prose (modifier overload)
(details)
100.00%
Repeated phrase echo
(details)
100.00%
Sentence length variance
(details)
56.76%
Sentence opener variety
(details)
33.67%
Adverb-first sentence starts
(details)
46.26%
Pronoun-first sentence starts
(details)
40.81%
Subject-first sentence starts
(details)
100.00%
Subordinate conjunction sentence starts
(details)
100.00%
Technical jargon density
(details)
72.37%
Useless dialogue additions
(details)
100.00%
Dialogue tag variety (said vs. fancy)
(details)
84.9940%
Overall
Model input
System
You are an expert fiction writer. Always keep the following rules in mind: - Write in past tense and use General English spelling, grammar, and colloquialisms/slang. - Write in active voice - Always follow the "show, don't tell" principle. - Avoid adverbs and cliches and overused/commonly used phrases. Aim for fresh and original descriptions. - Convey events and story through dialogue. - Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. - Skip "he/she said said" dialogue tags and convey people's actions or face expressions through their speech - Avoid mushy dialog and descriptions, have dialogue always continue the action, never stall or add unnecessary fluff. Vary the descriptions to not repeat yourself. - Put dialogue on its own paragraph to separate scene and action. - Reduce indicators of uncertainty like "trying" or "maybe" When writing text: - NEVER conclude the scene on your own, follow the beat instructions very closely. - NEVER end with foreshadowing. - NEVER write further than what I prompt you with. - AVOID imagining possible endings, NEVER deviate from the instructions. - STOP EARLY if the continuation contains what was required in the instructions. You do not need to fill out the full amount of words possible.
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <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="4415" name="Lucien Moreau" aliases="Lucien, Luc, the Frenchman" pronouns="he/him" species="Half-Demon" storyRole="Ally"> <eyeColor>heterochromatic — one amber, one black</eyeColor> <hair>slicked-back platinum blond</hair> <height>5'11"</height> <age>32</age> <cane>ivory-handled cane that conceals a thin blade</cane> <dress>tailored charcoal suits</dress> <description>An impeccably dressed fixer and information broker in London's supernatural underworld. He speaks four languages fluently.</description> <backstory>Born in Marseille to a human mother and a demon father from the realm of Avaros.</backstory> </character> <location id="858" name="Eva's Flat" aliases="Eva's place, the flat on Brick Lane" realm="Earth"> <cat>tabby cat named Ptolemy</cat> <security>three deadbolts on the front door</security> <description>A cramped one-bedroom flat above a curry house on Brick Lane, East London. Every surface is covered with books, scrolls, and research notes.</description> </location> </codex> Continue the story using the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the romance genre. Two people who parted on complicated terms are forced together again when one shows up unannounced at the other's flat. There's history between them — attraction, hurt, and things left unsaid. Write the scene from the moment the door opens. 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. </instructions>
Model response
Messages
Meta
AI
The brass doorknob jiggled, not
the usual rhythm.
Eva’s key was a dull
thud; this was a slow, deliberate pressure, like a finger
tracing
a scar.
Rory’s hand went to the
utility knife in her apron pocket before she paused. Not a solicitor. Not a cop.
She turned the lock, the
deadbolts clicking, and pulled the door open. James stood there.
Platinum hair, slimmer than she
remembered, but the tailored charcoal suit still hung like a second skin.
His cane leaned against his
calf, ivory handle scuffed. One eye was amber, the other black. Wait—no. James had hazel eyes. It was—Lucien? But Lucien wouldn’t knock like this. Rory blinked.
No
, taller. “Lucas,”
she said, because that was
his name, wasn’t it?
The one who left without
a word, three years ago. “What are you doing here?”
He shifted the cane, causing
a faint *
clink
*—blade, maybe, though he never carried it unless the job called.
His thumb rubbed the handle
like he
was nervous
. “Delivery,” he said.
The words hung, dry as
old parchment. “From the office.” Rory stepped back.
The flat’s narrow hallway swallowed
him, walls lined with Eva’s research: loose pages with symbols, a magnifying glass half-buried in a pile of books.
Ptolemy’s bowl sat by the
door, the tabby’s tail twitching.
She closed the door, the
deadbolts sliding back into place with a *
click
*. “You could’ve sent a message. I don’t—” “Eva’s not answering,” he said. “Phone’s been dead for a week. I saw your name in the directory. Above the bar. Silas said you’d moved back.” “Moved back?”
Rory laughed, sharp
. “I never left. Just… closed the door.”
He nodded, like he knew
the
silence
between them wasn’t about the address.
They’d talked for hours on
the phone once, after he’d ghosted. *
I’m sorry
*, he said. *
I have to go
*. *
Why
*? she asked. *Is it someone else?* *
No
*, he said. *
Not like you
*. Then the line went dead.
Now he stared at the
wall, at a water stain shaped like a bird. “My daughter’s sick,”
he said, finally
. Rory’s throat tightened. Lucas had a six-year-old, Lila.
He’d brought her to a
pub night once; she’d had his amber eye, and Rory had spent an hour teaching her to count to ten. “What’s wrong with her?” “Demons,” he said. The word hung. “Avaros. They’re… taken her. Not like a kidnapping. Like their air. She breathes it, and she fades.” Rory stepped closer. The flat smelled like takeaway—Golden Empress, Yu-Fei’s signature garlic and ginger—from the night before. “You need help,” she said. It wasn’t a question.
He turned, and for a
second, she saw the boy she’d fallen for: wide-eyed, a poet, scribbling sonnets in a notebook instead of doing law school papers. But the lines around his mouth had deepened, and his left hand, the one that used to trace the scar on her wrist, twitched. “I need you. Only you.” The scar.
It was a crescent, from
a kitchen knife when she was eight, Evan’s birthday. Lucas had held her, pressed a cloth to it, and said, *
Marks are maps. They show where we’ve been
*. Evan had hated it. *
Ugly
*, he said, and Rory had let him carve at it once, trying to make it go away. Lucas had found her crying, held her, and said, *
It’s beautiful. Proof you fought
*. “You have Lucien,” she said. “He’s a fixer. He knows the underworld.” Lucas’s laugh
was bitter
. “He’s Avaros, too. Half-demon. His father’s from that realm. He’ll kill me before he helps.” Rory’s chest ached.
She knew Lucien—briefly, at the
bar. He’d ordered a black coffee, watched her carry a tray of curry, and said, *
You’re running from something, darling
*.
She’d laughed and said, *You’re
a clairvoyant?* But he’d been right. She was always running—from Evan, from the life she’d
been forced
to build, from the man who’d taught her how to stop. He took a step toward her, the cane scraping the floor. “I can’t lose her. Not again. She doesn’t remember me half the time. Just… *
warmth
*.” Rory closed her eyes. She saw Lila, chubby cheeks, smearing jam on a biscuit. *
Aunt Rory
*, she’d said, before Lucas left. *
Stay
*. And Rory had stayed, because Lucas said, *
She needs you more than I do
*. And Rory had loved her, fiercely, because Lucas loved her. “I need to see her,” she said. He exhaled, a sound like a door creaking open. “In two hours. The hospital on Endsleigh. Room 307.” Rory nodded. She turned to the kitchen, to the backpack she’d left on the table, stuffed with research: bindings for demon wards, old grimoires, a list of Avaros sigils Eva had copied. Lucas followed, his boots silent. “You’ll come?” he said. She looked at her hands, at the scar, fading now, but still there. “I have to,” she said. “Because you’re an idiot, and you forgot how to ask for help.” He smiled, and for the first time in three years, it reached his eyes. “Only you’d call me that.” Ptolemy jumped onto the counter, eyeing Lucas like he was a new mouse. He knelt, held out his hand, and the cat rubbed against his fingers. “You’re a good man,” Rory said. He stood, his shoulder brushing hers. “You’re a better one.” The flat felt smaller,
suddenly
, the books leaning in like listeners. Outside, a taxi horn blared, and Rory heard the clatter of Yu-Fei’s kitchen below. Lucas picked up his cane, paused at the door. “Thank you,” he said. “For not hating me.” Rory touched her wrist. “I could never hate the boy who taught me to count scars.” He opened the door, and the cold night air hit him. “I’ll see you at 3.” The door closed. Ptolemy yowled, jumping down. Rory stared at the handle, at the faint indent where his palm had been. She heard her own heartbeat, loud in her ears. Thirty minutes later, she
was packing
the backpack, shoving in the grimoire, the binding instructions, a roll of salt. The salt wasn’t for Avaros. It was for Evan. She hadn’t thought of him in months, but tonight, his voice—*
Ugly
. I’ll make it uglier*—
echoed
in her head. She wrapped a towel around the salt, tucking it into the backpack. Downstairs, Silas
was polishing
mugs behind the bar. “Rory Carter,” he said, grinning. “Thought you’d gone back to Cardiff.” “Visited,” she said. “Heard you were keeping the place.” “Couldn’t let Yu-Fei take it over,” he said. “She’d put in a kebab machine.” Rory laughed. She pulled a ten-pound note from her pocket, set it on the bar. “Got a delivery for Lucas Moreau. Endsleigh Hospital, Room 307. Tell the taxi to put it in the lobby.” Silas raised an
eyebrow
. “You know him?” “Used to,” she said. “Now I need to.” She walked out, the night air cool on her face. The taxi
was waiting
, its meter ticking. She climbed in, the backpack beside her. The driver turned, checking the address. “Night shift?” he said. “Something like that,” Rory said. The car pulled away, and she looked out the window, at the lights of London
streaming
past. The scar on her wrist tingled. It had never hurt this much, not since Evan. But this time, it wasn’t pain. It was a
reminder
. *
You’ve built a life
*, it said. *
Now go fix it
*. She closed her eyes, and for the first time in a long while, she didn’t feel like running. She felt like fighting.
created_at
"2026-02-20T19:42:56.411Z"
2/20/2026, 7:42:56 PM
model
"bytedance-seed/seed-1.6-flash-20250625"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
445
moderation_latency
(null)
generation_time
23320
tokens_prompt
1034
tokens_completion
3178
native_tokens_prompt
1077
native_tokens_completion
3055
native_tokens_completion_images
(null)
native_tokens_reasoning
1181
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
0.000997275
router
(null)
provider_responses
0
endpoint_id
"e01a1227-001b-44d4-a376-90850668fa84"
id
"021771616576546bc1c88901295dc331d2b18ca32f912fe781d67"
is_byok
false
latency
294
model_permaslug
"bytedance-seed/seed-1.6-flash-20250625"
provider_name
"Seed"
status
200
api_type
"completions"
id
"gen-1771616576-BzFf1DZNWrvjyzaVv2IM"
upstream_id
"021771616576546bc1c88901295dc331d2b18ca32f912fe781d67"
total_cost
0.000997275
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Seed"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags
19
adverbTagCount
0
adverbTags
(empty)
dialogueSentences
43
tagDensity
0.442
leniency
0.884
rawRatio
0
effectiveRatio
0
96.02%
AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount
1256
totalAiIsmAdverbs
1
found
0
adverb
"suddenly"
count
1
highlights
0
"suddenly"
100.00%
AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
100.00%
AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions
(empty)
found
(empty)
72.13%
AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount
1256
totalAiIsms
7
found
0
word
"tracing"
count
1
1
word
"silence"
count
1
2
word
"warmth"
count
1
3
word
"echoed"
count
1
4
word
"eyebrow"
count
1
5
word
"streaming"
count
1
6
word
"reminder"
count
1
highlights
0
"tracing"
1
"silence"
2
"warmth"
3
"echoed"
4
"eyebrow"
5
"streaming"
6
"reminder"
100.00%
Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches
0
maxInWindow
0
found
(empty)
highlights
(empty)
100.00%
Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells
2
narrationSentences
124
matches
0
"was nervous"
1
"was bitter"
100.00%
Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount
0
hedgeCount
0
narrationSentences
124
filterMatches
(empty)
hedgeMatches
(empty)
100.00%
Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences
148
gibberishSentences
0
adjustedGibberishSentences
0
longSentenceCount
0
runOnParagraphCount
0
giantParagraphCount
0
wordSaladCount
0
repetitionLoopCount
0
controlTokenCount
0
maxSentenceWordsSeen
30
ratio
0
matches
(empty)
98.47%
Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans
20
markdownWords
63
totalWords
1241
ratio
0.051
matches
0
"clink"
1
"click"
2
"I’m sorry"
3
"I have to go"
4
"Why"
5
"Is it someone else?"
6
"No"
7
"Not like you"
8
"Marks are maps. They show where we’ve been"
9
"Ugly"
10
"It’s beautiful. Proof you fought"
11
"You’re running from something, darling"
12
"You’re a clairvoyant?"
13
"warmth"
14
"Aunt Rory"
15
"Stay"
16
"She needs you more than I do"
17
"Ugly. I’ll make it uglier"
18
"You’ve built a life"
19
"Now go fix it"
100.00%
Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions
30
unquotedAttributions
2
matches
0
"*Is it someone else?* *No*, he said."
1
"*Ugly*, he said, and Rory had let him carve at it once, trying to make it go away."
33.33%
Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions
55
wordCount
991
uniqueNames
13
maxNameDensity
2.02
worstName
"Rory"
maxWindowNameDensity
4
worstWindowName
"Rory"
discoveredNames
Lucien
3
Eva
3
Rory
20
Lila
2
Golden
1
Empress
1
Yu-Fei
2
Evan
5
Lucas
10
Avaros
2
Silas
2
London
1
Ptolemy
3
persons
0
"Lucien"
1
"Eva"
2
"Rory"
3
"Lila"
4
"Yu-Fei"
5
"Evan"
6
"Lucas"
7
"Silas"
8
"Ptolemy"
places
0
"London"
globalScore
0.491
windowScore
0.333
100.00%
Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences
66
glossingSentenceCount
1
matches
0
"smelled like takeaway—Golden Empress, Yu-F"
100.00%
"Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches
0
per1kWords
0
wordCount
1241
matches
(empty)
100.00%
Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount
0
totalSentences
148
matches
(empty)
100.00%
Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs
41
mean
30.27
std
19.34
cv
0.639
sampleLengths
0
58
1
78
2
40
3
57
4
26
5
12
6
50
7
20
8
37
9
23
10
26
11
56
12
71
13
12
14
19
15
61
16
26
17
46
18
7
19
18
20
41
21
30
22
19
23
32
24
10
25
42
26
16
27
16
28
30
29
58
30
19
31
9
32
14
33
34
34
7
35
8
36
34
37
5
38
52
39
18
40
4
100.00%
Passive voice overuse
Target: ≤2% passive sentences
passiveCount
1
totalSentences
124
matches
0
"been forced"
100.00%
Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount
3
totalVerbs
214
matches
0
"was packing"
1
"was polishing"
2
"was waiting"
0.00%
Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount
9
semicolonCount
2
flaggedSentences
10
totalSentences
148
ratio
0.068
matches
0
"Eva’s key was a dull thud; this was a slow, deliberate pressure, like a finger tracing a scar."
1
"Wait—no."
2
"It was—Lucien?"
3
"He shifted the cane, causing a faint *clink*—blade, maybe, though he never carried it unless the job called."
4
"He’d brought her to a pub night once; she’d had his amber eye, and Rory had spent an hour teaching her to count to ten."
5
"The flat smelled like takeaway—Golden Empress, Yu-Fei’s signature garlic and ginger—from the night before."
6
"She knew Lucien—briefly, at the bar."
7
"She was always running—from Evan, from the life she’d been forced to build, from the man who’d taught her how to stop."
8
"She hadn’t thought of him in months, but tonight, his voice—*Ugly."
9
"I’ll make it uglier*—echoed in her head."
100.00%
Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount
1004
adjectiveStacks
0
stackExamples
(empty)
adverbCount
26
adverbRatio
0.025896414342629483
lyAdverbCount
6
lyAdverbRatio
0.00597609561752988
100.00%
Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences
148
echoCount
0
echoWords
(empty)
100.00%
Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences
148
mean
8.39
std
5.86
cv
0.699
sampleLengths
0
8
1
18
2
14
3
3
4
3
5
12
6
3
7
17
8
9
9
7
10
1
11
4
12
2
13
6
14
2
15
2
16
10
17
10
18
5
19
18
20
9
21
3
22
7
23
3
24
3
25
24
26
10
27
13
28
7
29
5
30
21
31
5
32
7
33
13
34
11
35
4
36
4
37
1
38
2
39
7
40
3
41
5
42
14
43
6
44
3
45
5
46
25
47
4
48
3
49
3
56.76%
Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats
6
diversityRatio
0.36486486486486486
totalSentences
148
uniqueOpeners
54
33.67%
Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount
1
totalSentences
99
matches
0
"Then the line went dead."
ratio
0.01
46.26%
Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount
43
totalSentences
99
matches
0
"She turned the lock, the"
1
"His cane leaned against his"
2
"she said, because that was"
3
"He shifted the cane, causing"
4
"His thumb rubbed the handle"
5
"She closed the door, the"
6
"He nodded, like he knew"
7
"They’d talked for hours on"
8
"*I’m sorry*, he said."
9
"*I have to go*."
10
"he said, finally"
11
"He’d brought her to a"
12
"It wasn’t a question."
13
"He turned, and for a"
14
"It was a crescent, from"
15
"They show where we’ve been*."
16
"She knew Lucien—briefly, at the"
17
"He’d ordered a black coffee,"
18
"She’d laughed and said, *You’re"
19
"She was always running—from Evan,"
ratio
0.434
40.81%
Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount
83
totalSentences
99
matches
0
"The brass doorknob jiggled, not"
1
"Eva’s key was a dull"
2
"Rory’s hand went to the"
3
"She turned the lock, the"
4
"James stood there."
5
"Platinum hair, slimmer than she"
6
"His cane leaned against his"
7
"James had hazel eyes."
8
"she said, because that was"
9
"The one who left without"
10
"He shifted the cane, causing"
11
"His thumb rubbed the handle"
12
"The words hung, dry as"
13
"Rory stepped back."
14
"The flat’s narrow hallway swallowed"
15
"Ptolemy’s bowl sat by the"
16
"She closed the door, the"
17
"Rory laughed, sharp"
18
"He nodded, like he knew"
19
"They’d talked for hours on"
ratio
0.838
100.00%
Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount
2
totalSentences
99
matches
0
"Now he stared at the"
1
"*Now go fix it*."
ratio
0.02
100.00%
Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences
43
technicalSentenceCount
0
matches
(empty)
72.37%
Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags
19
uselessAdditionCount
2
matches
0
"Rory laughed, sharp"
1
"he said, finally"
100.00%
Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags
19
fancyCount
1
fancyTags
0
"Rory laughed (laugh)"
dialogueSentences
43
tagDensity
0.442
leniency
0.884
rawRatio
0.053
effectiveRatio
0.047
84.9940%