NC Bench
Overview
About
Tests
Models
Model
Gemini 2.5 Pro
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-11-18-01KACPBDBAW865CHZWTV09JW1D
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
"Okay, the perimeter is soft. Distracted by a clown." "A clown, Molly? Is that our entry point?" "No, Bill. The bouncy castle is our entry point. I go in first, create a 'rapid deflation event'." "You're popping the bouncy castle." "It's a tactical diversion! While the hostiles are disoriented, you secure the asset pile." "You mean the present table." "Don't use civilian language. This is a job." "We're stealing from children named Timmy and Jessica." "High-value targets. Intel says there's a seventy-dollar construction vehicle in play. Now, the getaway?" "Is it the minivan with the juice box stains?" "Our unmarked vehicle, yes. Did you bring the noise-makers?" "For covering our tracks?" "No, for a clean extraction celebration. Get your head in the game." "I just saw a kid fall over." "Excellent. The system is starting to break down from within. Move on my signal." "Which is what, a party horn?" "It’s when the piñata breaks. The universal symbol for chaos."
created_at
"2025-11-18T23:56:36.883917+00:00"
Tuesday, November 18th, 2025 at 11:56:36 PM GMT+00:00
model
"google/gemini-2.5-pro"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2284
moderation_latency
(null)
generation_time
25108
tokens_prompt
68
tokens_completion
1140
native_tokens_prompt
67
native_tokens_completion
3074
native_tokens_completion_images
0
native_tokens_reasoning
2828
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
0.03082375
api_type
"completions"
id
"gen-1763510171-5vHiQCe9Q4zUC1NvaWtW"
upstream_id
(null)
total_cost
0.03082375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
163
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
163
wordsDialogue
163
18.3940%