NC Bench
Overview
About
Tests
Models
Model
Gemini 2.5 Pro
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2025-11-18-01KACP6VMT6H86F7B3QZC9EG47
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 peered through the sweet-smelling hydrangea bush, the squeals of a dozen six-year-olds assaulting her ears. An inflatable unicorn wobbled precariously. Beside her, Bill lowered his binoculars with a tactical frown. “Okay, Phase One: I distract them. I’ll go in as Barnaby the Sad Clown. Kids hate clowns. They'll run screaming.” “No. We are not psychologically scarring children. We're just stealing their expensive LEGO sets. There’s a difference in class, Bill.” He sighed, a floppy clown nose drooping in his hand. The air smelled of sugar and disappointment. Molly ignored him. “Right. Class. So the giant pizza delivery guy costume is out? I could hide the presents right in the fake pepperoni.” “Completely out. Look. The parents are drunk on punch. The doggy door is our entry point. It's simple and quiet.” She pointed a finger towards a small flap on the back door, guarded by a terrifyingly fluffy Pomeranian. It was wearing a tiara. “Her name is Princess Fluffybutt. I read the invitation. She has more followers than me, Mol. That dog’s a professional.” Bill shuddered. Molly just rolled her eyes and handed him the squeaky hamburger toy.
created_at
"2025-11-18T23:54:02.518569+00:00"
Tuesday, November 18th, 2025 at 11:54:02 PM GMT+00:00
model
"google/gemini-2.5-pro"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2265
moderation_latency
(null)
generation_time
19901
tokens_prompt
68
tokens_completion
965
native_tokens_prompt
67
native_tokens_completion
2406
native_tokens_completion_images
0
native_tokens_reasoning
2140
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
0.02414375
api_type
"completions"
id
"gen-1763510021-ILp6KsuqdjhT986tDvKu"
upstream_id
(null)
total_cost
0.02414375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
95.9868%
Matches word count
n/a
neededClean
false
words
192
99.5411%
Dialogue to Total Word Ratio
Ratio: 52.60%, Deviation: 2.60%
neededClean
false
wordsTotal
192
wordsDialogue
101
97.7639%