NC Bench
Overview
About
Tests
Models
Model
GPT-4.1 Mini
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-04-14-01JRTSWV2VZ146AWK3JFG0M53A
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
"Alright, Bill, let's run through this again. How exactly do you plan on sneaking into a toddler’s birthday party without looking like absolute lunatics?" "Simple. We dress as the entertainment. You be the clown, I’ll be the magician. Nothing suspicious about that." "Molly, you in a clown suit? Have you looked in a mirror lately? You scare puppies, let alone kids." "Exactly! The kids’ll either be terrified or distracted. That’s perfect for lifting gifts. And your magic tricks? Do you even know any?" "Pulled a quarter from behind your ear last week. That's magic, right?" "So our plan hinges on quarter tricks and terrifying children. Brilliant." "You’re worried it’s too risky? Consider the payoff: all those shiny wrapped packages, nobody paying attention to the clowns moving around." "What if a kid wants a balloon animal and I start crying because I forgot how to fold balloons?" "Kid’s happy, you’re distracted. Win-win. Besides, the sugar rush chaos buys us time." "Okay, but if I get a pie in the face, I’m quitting the heist life forever." "Deal. Now, grab the makeup kit and magic wand. Next stop: Party City and the sweetest score ever."
id
"gen-1744656298-nzvktJB9EHqKFPQpg4Td"
upstream_id
"chatcmpl-BMJ5eGMXgC0HKI45jgk0vHwULtQbG"
total_cost
0.0004412
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:45:00.970345+00:00"
Monday, April 14th, 2025 at 6:45:00 PM GMT+00:00
model
"openai/gpt-4.1-mini-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
440
moderation_latency
418
generation_time
1479
tokens_prompt
68
tokens_completion
260
native_tokens_prompt
67
native_tokens_completion
259
native_tokens_reasoning
0
num_media_prompt
(null)
num_media_completion
(null)
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0004412
Evaluation details
Result
Evaluator
Details
Meta Data
98.7124%
Matches word count
n/a
neededClean
false
words
194
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
194
wordsDialogue
194
67.7502%