NC Bench
Overview
About
Tests
Models
Model
Gemini 2.5 Pro
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2025-11-18-01KACP6Z4W8H6TB275CEM3CJW7
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
Bill jabbed a sausage-like finger at the crayon drawing spread across their rickety kitchen table. The schematic, scrawled on the back of a pizza menu, detailed the layout of “Fort Birthday.” He’d marked a bouncy castle as ‘Inflatable Obstruction Alpha’ and a cluster of screaming six-year-olds as ‘Mobile Guard Patrol.’ A red circle indicated the main prize: a mountain of brightly wrapped presents. Bill adjusted his dollar-store reading glasses, his brow furrowed with the intense concentration of a man defusing a bomb, not burgling a suburban backyard. Molly sighed, popping a cheese puff into her mouth and pointed a cheesy finger at a crudely drawn donkey. “Are you sure the piñata isn't a decoy?” “Positive. The real prize is the unicorn cake. It’s filled with premium… sprinkles.” Bill traced a dotted line from the back fence, navigating past the ‘Slippery Slide of Doom’ and the ‘Clown Danger Zone.’ Their exfiltration route depended entirely on Timmy’s dad firing up the barbecue at precisely 3:15 PM, creating a smokescreen of delicious, greasy burger fumes. It was a flawless plan. Almost. He hadn't yet figured out how to neutralize the family golden retriever, 'Sir Barks-a-lot.'
created_at
"2025-11-18T23:53:58.047047+00:00"
Tuesday, November 18th, 2025 at 11:53:58 PM GMT+00:00
model
"google/gemini-2.5-pro"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2094
moderation_latency
(null)
generation_time
11967
tokens_prompt
68
tokens_completion
880
native_tokens_prompt
67
native_tokens_completion
1468
native_tokens_completion_images
0
native_tokens_reasoning
1198
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
0.01476375
api_type
"completions"
id
"gen-1763510025-tgIhNO322QTCmgM9Nalz"
upstream_id
(null)
total_cost
0.01476375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9190%
Matches word count
n/a
neededClean
false
words
197
0.0000%
Dialogue to Total Word Ratio
Ratio: 44.67%, Deviation: 34.67%
neededClean
false
wordsTotal
197
wordsDialogue
88
49.9595%