NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-25-01KJ94RENCK8WVCXSKJQZFD0TV
Run Details
Model:
Gemini 2.5 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
30.2s
Cost:
$0.018095
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
95.58%
Dialogue to Total Word Ratio
(details)
47.7877%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 50% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly jabbed a finger at the crumpled, coffee-stained napkin spread across the sticky kitchen table. Her brow furrowed with intense concentration, as if dissecting a complex schematic, not a child’s birthday invitation. “Barnaby Henderson, seven years old. Henderson Dental heir. Plush party, guaranteed presents. Our target.” Bill peered closer, adjusting his spectacles, which were perpetually perched askew. He took a bite of a questionable-looking doughnut. “Barnaby? Sounds like a character from a fable. Sure he’s not a decoy for something more substantial?” Molly rolled her eyes, her patience fraying already. She hated early morning planning sessions, especially ones involving tiny humans. “Very real. And so are his twenty-six gifts. Probably some decent remote control cars in the mix.” Bill’s attention drifted, a familiar glazed look appearing in his eyes. “Remote control cars. Didn’t work at the bank. Laser grids aren't drone-friendly.” She slammed her palm onto the table, rattling a stack of empty crisp packets. “Focus, Bill! It’s a children’s party. Security is parents, maybe a bouncy castle. The challenge? Sugar-fueled toddlers and a depressing clown.” Bill shuddered, then brightened, a mischievous glint in his eye. He leaned forward conspiratorially. “Clowns. Never. My plan: Trained pigeons. They swoop during gift-opening. Chaos. We grab the loot and vanish.” Molly’s jaw dropped. She slowly picked up a discarded crayon, twirling it incredulously. “Pigeons? No! ‘Grab the loot’? This is surgical precision, stealth, and understanding a seven-year-old’s psychology.” Bill simply shrugged, brushing doughnut crumbs off his ancient tweed jacket. “Barnaby’s psyche? Probably cake-focused. We could just ask. Orphanage donation, you know.” Molly threw the crayon down with a clatter. “He’d cry. We’d be villains. We need panache.” Bill snapped his fingers. His face lit up like a faulty Christmas decoration. “Panache! I’ll be Professor Bumbles, the World’s Most Forgetful Magician. I ‘misplace’ presents into my magic box. Then box and I disappear. Poof!” Molly narrowed her eyes, intrigued despite herself. “Your disappearing act? Glitter-bomb and a gnome retreat?” Bill grinned, pulling a tiny rubber duck from his pocket. “Strawberry-scented, non-toxic smoke bomb! We don’t traumatize. We liberate. Gnomes offer silent judgment, good cover.” Molly pinched the bridge of her nose, a long-suffering groan escaping her. The absurdity was truly sublime. “Strawberry smoke? You’re mad, Bill. Stealing from children? A new low, even for us.” Bill leaned back, radiating insouciance, completely unbothered by her moral qualms. “A low with a high toy car return! Liberating plastic trinkets from Barnaby’s oppressive regime. Plus, someone definitely got him a sweater.” Molly glared at him, then a flicker of amusement crossed her features. She couldn’t argue with the sweater logic. “Fine. Professor Bumbles. But glitter on my car, you walk.” Bill saluted crisply, already reaching for another crumpled napkin to sketch. “Never! Now, the bouncy castle's strategic value…”
created_at
"2026-02-25T00:56:35.251Z"
2/25/2026, 12:56:35 AM
model
"google/gemini-2.5-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1455
moderation_latency
(null)
generation_time
30168
tokens_prompt
77
tokens_completion
3192
native_tokens_prompt
67
native_tokens_completion
7230
native_tokens_completion_images
0
native_tokens_reasoning
6509
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
0.0180951
router
(null)
provider_responses
0
endpoint_id
"16c01e26-9b91-4d22-b487-ed35634b017d"
is_byok
false
latency
1455
model_permaslug
"google/gemini-2.5-flash"
provider_name
"Google AI Studio"
status
200
api_type
"completions"
id
"gen-1771980995-azqAgsJswf3ikb5hymp3"
upstream_id
(null)
total_cost
0.0180951
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
461
95.58%
Dialogue to Total Word Ratio
Ratio: 50.95%, Deviation: 0.95%
neededClean
false
wordsTotal
473
wordsDialogue
241
47.7877%