Run: 2026-02-19-01KHTX84WGD85E6AB0JRKYCMY0

Run Details

Duration:
9.9s
Cost:
$0.000678
Provider:
Google AI Studio

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="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> Continue the story using the following instructions: <instructions> 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. </instructions>

Model response

AI
The green neon of The Raven's Nest pulsed through the rain-streaked window, a familiar beacon in the Soho sprawl. Rory pulled her collar tighter, the damp London air clinging to her like a second skin. She still lived above Silas’s bar, a fact that felt both comforting and like a cage. Tonight, the usual Friday night buzz seemed muted, the air thick with unspoken things she’d learned to navigate. She pushed open the door, the chime above announcing her arrival with a tired jingle. Silas, perched on his usual stool behind the bar, wiped down a glass, his grey-streaked hair glinting under the low lights. He offered a barely perceptible nod, his hazel eyes holding an age-old understanding. Rory slipped into a booth near the back, the worn leather sighing beneath her. She scanned the room – the usual faces, hunched over their drinks, lost in their own worlds. Then, her gaze snagged. A man stood near the dartboard, his back to her, his posture unfamiliar. Yet, something in the way he held his head, the broad set of his shoulders, tugged at a long-dormant memory. He turned then, catching her staring, and the world tilted. Evan. Her ex. The man who’d made her flee Cardiff, the ghost she’d tried so hard to outrun. He was older, of course, lines etched around his eyes that hadn't been there before, his jaw a little softer. But the eyes, that predatory glint still there, though now veiled with something that might, just might, be surprise. He pushed away from the wall, a slow, assessing stride bringing him closer. He stopped at her table, a faint smile playing on his lips. "Rory? Bloody hell, is that really you?" Rory’s heart hammered against her ribs. She forced a breath. "Evan. What are you doing here?" Her voice, she noted, was steady. A small victory. He chuckled, a rough sound that scraped against the quiet hum of the bar. "Same as you, supposed to be. Unwinding. Didn't expect to see anyone I actually knew. Especially not… you." He gestured vaguely at her, as if she were an exhibit. "Life has a funny way of doing that." She gestured to the seat opposite her. "Sit down, if you want." He hesitated for a beat, then slid into the booth. He looked around, a flicker of recognition in his eyes as he took in the maps on the wall, the dim lighting. "Still running this place, Silas?" "Can't get rid of him that easily," Rory said, her gaze fixed on Evan’s face. His hands rested on the table, not quite touching. The nail on his right thumb, she noticed, was chipped. A detail she’d once known intimately. Evan picked at a splinter on the edge of the table. "Heard you left Cardiff. Your dad’s still there, right? Teaching?" "He is. And Mum." She deliberately omitted any mention of her own life in London, the delivery job, the flat above Silas's. Let him assume what he would. "How about you? Still... doing whatever it was you were doing?" He winced, a small, almost imperceptible tightening of his jaw. "Something like that. Moved around a bit." He finally met her eyes, and the veiled look was gone, replaced by something raw and searching. "You look… different, Rory." "It’s been a while," she said, the words a dam against the flood of emotions threatening to break free. "Years." "Must be. What, five? Six?" He ran a hand over his jaw. "You used to have that hair all over the place. Always tangled. Now… it's neat. Like you." She reached up, touching her shoulder-length black hair, a habit she’d picked up from Silas. It was easier to manage than the wild curls she’d once battled. "People change, Evan." "Some more than others." He leaned back, the worn leather groaning. “You always were the smart one. The one with the plans. I always wondered where you’d end up.” "Here," she said, a wry twist to her lips. "Doesn't seem so grand, does it?" He looked around the bar again, this time with a critical eye. "It's… a place. Got its own charm, I suppose. Like Silas. Always been a bit of an enigma, that one." "He’s good people." The words were automatic, a practiced defence. Evan picked up a coaster, turning it over and over in his hands. "He always looked out for you, didn't he? Even back then." A knot tightened in Rory's stomach. "He's a friend." "A very good friend, clearly." His voice was low, a sardonic edge to it that made her skin prickle. "I remember you saying once, about your dad, that his biggest fear was that you’d end up with someone who’d dim your light. Guess that didn’t quite work out, did it?" "It didn't." She met his gaze, her own blue eyes cool and steady. "But I found my way back to the light, Evan. Took some detours, but I’m here." He finally tossed the coaster back onto the table. "Good. Because you had a very bright light, Rory. Shame to see it ever go out." He paused, a long, uncomfortable silence stretching between them, punctuated only by the clinking of glasses. "You know, I had a dream about you the other night. We were back at that old pub in Cardiff. The one with the terrible sticky floors. You were laughing." Rory swallowed. The memory of that laughter, genuine and unrestrained, felt like a lifetime ago. "I don't remember that pub." "You wouldn't. Not the way I do." He leaned forward, his voice dropping lower. "I was thinking, maybe… maybe things could have been different. If I hadn’t… if you hadn’t left." "That’s a big 'if', Evan." She watched his hands. He’d stopped fiddling with the coaster. His left hand rested palm-down on the table, and she saw it then, beneath the dim light, a faint, barely discernible shape. A crescent moon. A scar. Exactly like the one on her own left wrist. "Yeah," he breathed, his eyes dropping to his hand, then flicking back to hers, a dawning, dreadful understanding in their depths. "Yeah, it is."
created_at"2026-02-19T12:16:00.31Z" 2/19/2026, 12:16:00 PM
model"google/gemini-2.5-flash-lite"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency351
moderation_latency(null)
generation_time8298
tokens_prompt1094
tokens_completion1502
native_tokens_prompt1032
native_tokens_completion1438
native_tokens_completion_images0
native_tokens_reasoning0
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"STOP"
usage0.0006784
router(null)
provider_responses
0
endpoint_id"ce839073-aa24-4f29-8358-15b319bd05ec"
is_byokfalse
latency351
model_permaslug"google/gemini-2.5-flash-lite"
provider_name"Google AI Studio"
status200
api_type"completions"
id"gen-1771503360-3lZ6cTx63hzYCjctQdkd"
upstream_id(null)
total_cost0.0006784
cache_discount(null)
upstream_inference_cost0
provider_name"Google AI Studio"

Evaluation details

Result Evaluator Details Meta Data
91.89% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags13
adverbTagCount2
adverbTags
0"He gestured vaguely [vaguely]"
1"He leaned back [back]"
dialogueSentences37
tagDensity0.351
leniency0.703
rawRatio0.154
effectiveRatio0.108
80.53% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1027
totalAiIsmAdverbs4
found
0
adverb"really"
count1
1
adverb"deliberately"
count1
2
adverb"very"
count2
highlights
0"really"
1"deliberately"
2"very"
100.00% AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0"Blackwood"
found(empty)
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
22.10% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1027
totalAiIsms16
found
0
word"pulsed"
count1
1
word"familiar"
count1
2
word"beacon"
count1
3
word"comforting"
count1
4
word"unspoken"
count1
5
word"navigate"
count1
6
word"glinting"
count1
7
word"scanned"
count1
8
word"etched"
count1
9
word"glint"
count1
10
word"flicker"
count1
11
word"charm"
count1
12
word"enigma"
count1
13
word"stomach"
count1
14
word"silence"
count1
15
word"depths"
count1
highlights
0"pulsed"
1"familiar"
2"beacon"
3"comforting"
4"unspoken"
5"navigate"
6"glinting"
7"scanned"
8"etched"
9"glint"
10"flicker"
11"charm"
12"enigma"
13"stomach"
14"silence"
15"depths"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"flicker of emotion"
count1
highlights
0"a flicker of recognition"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences62
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences62
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences82
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen32
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1022
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions8
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions22
wordCount696
uniqueNames10
maxNameDensity0.86
worstName"Rory"
maxWindowNameDensity1.5
worstWindowName"Evan"
discoveredNames
Raven1
Nest1
Soho1
London2
Silas4
Friday1
Cardiff1
Evan4
Let1
Rory6
persons
0"Raven"
1"Silas"
2"Evan"
3"Rory"
places
0"Soho"
1"London"
2"Cardiff"
globalScore1
windowScore1
8.49% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences53
glossingSentenceCount3
matches
0"seemed muted the air thick with unspoken things she’d learned to navigate"
1"not quite touching"
2"felt like a lifetime ago"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1022
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences82
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs28
mean36.5
std21.29
cv0.583
sampleLengths
084
169
2100
332
425
543
620
737
840
921
1039
1138
1220
1329
1430
1529
1615
1732
1810
1924
209
2150
2229
2371
2420
2531
2651
2724
93.94% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences62
matches
0"was chipped"
1"was gone"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs112
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount1
semicolonCount0
flaggedSentences1
totalSentences82
ratio0.012
matches
0"She scanned the room – the usual faces, hunched over their drinks, lost in their own worlds."
93.81% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount701
adjectiveStacks0
stackExamples(empty)
adverbCount33
adverbRatio0.047075606276747506
lyAdverbCount9
lyAdverbRatio0.012838801711840228
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences82
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences82
mean12.46
std7.16
cv0.575
sampleLengths
019
116
216
318
415
521
613
714
817
94
1013
1120
1210
131
142
1515
1620
1719
1813
1912
207
216
224
2312
243
2514
2629
2715
285
2910
3022
315
3215
339
3410
356
3611
3710
3822
396
4011
4110
4224
434
4419
451
4612
4717
4815
4912
65.04% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats5
diversityRatio0.4268292682926829
totalSentences82
uniqueOpeners35
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences58
matches
0"Then, her gaze snagged."
1"Exactly like the one on"
ratio0.034
0.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount35
totalSentences58
matches
0"She still lived above Silas’s"
1"She pushed open the door,"
2"He offered a barely perceptible"
3"She scanned the room –"
4"He turned then, catching her"
5"He was older, of course,"
6"He pushed away from the"
7"He stopped at her table,"
8"She forced a breath."
9"Her voice, she noted, was"
10"He chuckled, a rough sound"
11"He gestured vaguely at her,"
12"She gestured to the seat"
13"He hesitated for a beat,"
14"He looked around, a flicker"
15"His hands rested on the"
16"She deliberately omitted any mention"
17"He winced, a small, almost"
18"He finally met her eyes,"
19"she said, the words a"
ratio0.603
3.10% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount53
totalSentences58
matches
0"The green neon of The"
1"Rory pulled her collar tighter,"
2"She still lived above Silas’s"
3"Tonight, the usual Friday night"
4"She pushed open the door,"
5"Silas, perched on his usual"
6"He offered a barely perceptible"
7"Rory slipped into a booth"
8"She scanned the room –"
9"A man stood near the"
10"He turned then, catching her"
11"The man who’d made her"
12"He was older, of course,"
13"He pushed away from the"
14"He stopped at her table,"
15"Rory’s heart hammered against her"
16"She forced a breath."
17"Her voice, she noted, was"
18"A small victory."
19"He chuckled, a rough sound"
ratio0.914
86.21% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences58
matches
0"Yet, something in the way"
ratio0.017
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences29
technicalSentenceCount1
matches
0"But the eyes, that predatory glint still there, though now veiled with something that might, just might, be surprise."
9.62% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags13
uselessAdditionCount3
matches
0"He gestured vaguely, as if she were an exhibit"
1"He leaned back, the worn leather groaning"
2"He leaned, his voice dropping lower"
95.95% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags5
fancyCount2
fancyTags
0"Her voice she noted (note)"
1"he breathed (breathe)"
dialogueSentences37
tagDensity0.135
leniency0.27
rawRatio0.4
effectiveRatio0.108
81.6892%