NC Bench
Overview
About
Tests
Models
Model
Gemini 2.5 Pro
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2025-11-18-01KACPBMABKKN38ZPFMNDVNW4S
Model input
User/Human
You are a author of comedic heist books. Please write a 200 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 smacked a crayon-drawn map onto the dashboard. Outside, the shriek of sugared-up children and a pop song about sharks bled through the thin metal. The air smelled of cut grass and impending cake. She tapped a smudged square. “Okay. The Present Pile is here, guarded by what I’m calling ‘The Grandfather Contingent.’” Bill lowered his binoculars, his expression wistful. He watched a small child face-plant near the inflatable castle before recovering with impressive speed. “Molly, that bouncy castle is a majestic purple dragon.” “Irrelevant, Bill. A non-asset. Our primary target is the large one wrapped in spaceship paper.” “The Turbo-Bot 5000?” “The very same. My source says it has ‘kung-fu grip.’” “Your source is a four-year-old you bribed with a gummy worm.” “A reliable informant! Now, what’s the status of our diversion?” He patted a lumpy burlap sack at his feet. It cooed softly from within. “The pigeon flock is ready for deployment on your signal.” “Excellent,” Molly grinned, her eyes glinting with larcenous glee. "Nobody ever expects a tactical pigeon assault at a child’s birthday party." This was their biggest score yet.
created_at
"2025-11-18T23:57:02.670735+00:00"
Tuesday, November 18th, 2025 at 11:57:02 PM GMT+00:00
model
"google/gemini-2.5-pro"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2832
moderation_latency
(null)
generation_time
44121
tokens_prompt
68
tokens_completion
1899
native_tokens_prompt
67
native_tokens_completion
5141
native_tokens_completion_images
0
native_tokens_reasoning
4883
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
0.05149375
api_type
"completions"
id
"gen-1763510178-pVTc430y09JVykOnbbND"
upstream_id
(null)
total_cost
0.05149375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
93.6496%
Matches word count
n/a
neededClean
false
words
191
99.8873%
Dialogue to Total Word Ratio
Ratio: 51.83%, Deviation: 1.83%
neededClean
false
wordsTotal
191
wordsDialogue
99
96.7685%