NC Bench
Overview
About
Tests
Models
Model
Gemini 3 Pro (Preview)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-11-19-01KACQAXWWADTYFRAPDXV0C996
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 extraction point is the bouncy castle, Bill said, tapping the juice box. It’s a bounce house, not a fortress, Bill. And stop tapping, you’re spilling apple juice on the schematics. This map is crucial. Look, the clown is the wildcard. If he starts folding balloon animals, the crowd creates a perimeter wall. That’s our window to hit the gift table. You want to heist a pile of LEGOs during a balloon dog integrity check? Precisely. I swoop in, grab the big box wrapped in Paw Patrol paper, and pivot. That box is almost certainly diapers. It’s the element of surprise! Then, I signal you. And I’m supposed to neutralize the magician? Just create a diversion. Ask him how the rabbit breathes in the hat. While he panics, we extract the Barbie Dreamhouse. The Dreamhouse won’t fit in the getaway car. We strap it to the roof. It’s a Honda Civic, not a cargo plane. Maybe we just steal the loot bags. Dream bigger, Molly! We’re not petty thieves; we’re acquisition specialists targeting the under-seven demographic. I hate you. You love the thrill. Now, put on your party hat. It’s go time.
created_at
"2025-11-19T00:13:40.929861+00:00"
Wednesday, November 19th, 2025 at 12:13:40 AM GMT+00:00
model
"google/gemini-3-pro-preview-20251117"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2583
moderation_latency
(null)
generation_time
16717
tokens_prompt
68
tokens_completion
824
native_tokens_prompt
67
native_tokens_completion
1730
native_tokens_completion_images
0
native_tokens_reasoning
1454
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
0.020894
api_type
"completions"
id
"gen-1763511203-jZfmwmG2WkWHnvggXAor"
upstream_id
(null)
total_cost
0.020894
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
97.6276%
Matches word count
n/a
neededClean
false
words
193
0.0000%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
193
wordsDialogue
0
48.8138%