NC Bench
Overview
About
Tests
Models
Model
Gemini 3 Pro (Preview)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-11-19-01KACQDNHGA1YTFBJ8B21YXQPE
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 guarded by a Golden Retriever named Buster. Is he hostile? He’s a good boy, Bill. That’s the problem. He demands belly rubs. It’s a tactical time sink. I’ll bring the sausages. Good. Now, the extraction point is behind the bouncy castle. That’s highly exposed, Molly. What about the surveillance? Uncle Jerry has a camcorder, but he hasn't taken the lens cap off since nineteen-ninety-eight. We’re clear. Bill squinted at the crayon-drawn map. And the target? The gift table. Little Timmy turns seven today. We’re talking high-value electronics and limited-edition action figures. What’s the timeline? We strike during musical chairs. Why then? The tension is high. Desperation. Crying. It covers the sound of us loading the duffel bags. What’s my cover? You’re the bubble artist. I thought we agreed I’d be the DJ. You don't know the playlist, Bill. You’ll drop a slow jam and start a riot. Just blow bubbles and look whimsical. And if I make contact with a sticky toddler? Abort immediately. We don't have the budget for dry cleaning. And the loot splits? Fifty-fifty on the toys. I keep the juice boxes. Throw in a slice of cake. If it’s a corner piece, it’s yours. Let’s rob this kindergarten.
created_at
"2025-11-19T00:15:13.968232+00:00"
Wednesday, November 19th, 2025 at 12:15:13 AM GMT+00:00
model
"google/gemini-3-pro-preview-20251117"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2414
moderation_latency
(null)
generation_time
19655
tokens_prompt
68
tokens_completion
1015
native_tokens_prompt
67
native_tokens_completion
2242
native_tokens_completion_images
0
native_tokens_reasoning
1912
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
0.027038
api_type
"completions"
id
"gen-1763511293-d6AhtulwZ9geNXQYYvzm"
upstream_id
(null)
total_cost
0.027038
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
86.3803%
Matches word count
n/a
neededClean
false
words
211
0.0000%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
211
wordsDialogue
0
43.1902%