NC Bench
Overview
About
Tests
Models
Model
Gemini 3 Pro (Preview)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-11-19-01KACQX33Z3A3HYXXRWJ6ZPWWW
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
The perimeter is fortified with crepe paper, Bill whispered, pointing at the crayon-scrawled blueprints. Deadly, Molly noted. And the target package? Located behind the bouncy castle. We are talking high-value assets. Legos. Hot Wheels. Maybe a Nintendo Switch if the grandmother loves him enough. What is the opposition? Heavies. Four-year-olds on a chemically induced sugar high. Unpredictable. Vicious. And the warden? Mom. She has eyes in the back of her head and a lukewarm Chardonnay in her hand. We go in during the cake cutting? Exactly. The candles get lit, the lights go down, we descend from the treehouse on the zip line. I assume you packed the grappling hooks? Obviously. Just watch out for the clown. Mr. Bubbles? The man is a loose cannon, Molly. He made a balloon poodle that looked suspiciously like a garrote. If he spots us, deploy the glitter bomb. That is messy, Bill. Even for us. It is a heist, not a playdate. Once we secure the loot, we exfiltrate through the petting zoo. The goats have been bribed? Two pounds of oats. They will not see a thing. You are a genius. I know. Now put on your party hat. It is time to steal Christmas in July.
created_at
"2025-11-19T00:23:47.415194+00:00"
Wednesday, November 19th, 2025 at 12:23:47 AM GMT+00:00
model
"google/gemini-3-pro-preview-20251117"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2506
moderation_latency
(null)
generation_time
16596
tokens_prompt
68
tokens_completion
888
native_tokens_prompt
67
native_tokens_completion
1758
native_tokens_completion_images
0
native_tokens_reasoning
1463
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
0.02123
api_type
"completions"
id
"gen-1763511810-ss5HY7sfOIf83z8O7obc"
upstream_id
(null)
total_cost
0.02123
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
209
0.0000%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
209
wordsDialogue
0
46.8248%