NC Bench
Overview
About
Tests
Models
Model
Gemini 2.5 Flash
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-11-18-01KACPB8BQM7ZZZ38BMGDP0704
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
“You sure about this, Molly? A children’s party?” “Bill, it’s genius! They’ll never suspect a thing. Think of it, a bouncy castle, sugar-fueled tykes, and a mountain of unsuspecting loot.” “But… presents? For kids?” “Don’t be such a softie. They’ll get more, won’t they? Their parents always overcompensate. This is practically a public service, teaching them early about life’s little disappointments.” “Right. Public service. So, strategy? Do we go full clown suit, distract with juggling, then snag the goods?” “Absolutely not. Too cliché. We blend. You, Bill, are the disgruntled party mascot. Think sad clown, maybe a slightly deflated Elsa. I’m the overly enthusiastic parent, constantly ‘helping’ with the presents.” “Elsa? Oh, good Lord. My dignity…” “Your dignity flies out the window when we’re rich. Now, the main event: the gift table. It’s usually near the cake, right?” “Typically, yes. But the parents are usually hovering.” “That’s where the glitter bomb comes in. Non-toxic, of course. A little distraction, a little confusion, and boom! We’re out with the haul.” “Glitter bomb? Molly, you’re certifiable.” “And you, Bill, are going to be a very sparkly, slightly deflated Elsa. Now, let’s go steal some Barbies.”
created_at
"2025-11-18T23:56:08.566719+00:00"
Tuesday, November 18th, 2025 at 11:56:08 PM GMT+00:00
model
"google/gemini-2.5-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
443
moderation_latency
(null)
generation_time
2476
tokens_prompt
68
tokens_completion
304
native_tokens_prompt
67
native_tokens_completion
326
native_tokens_completion_images
0
native_tokens_reasoning
0
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
0.0008351
api_type
"completions"
id
"gen-1763510165-XIAq9TShx3qTRH9ZKz3M"
upstream_id
(null)
total_cost
0.0008351
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
195
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
195
wordsDialogue
195
68.0824%