NC Bench
Overview
About
Tests
Models
Model
GPT-4.1
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2025-04-14-01JRTSQG02CPJNKNTTD4DZDJH8
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
"Bill, did you bring the glitter cannon?" "Molly, of course I brought the glitter cannon. Do I look like an amateur?" "You look like a guy who once tried to pick a lock with a Twizzler." "Hey, it almost worked. Those locks aren’t built for finesse. Now, have you memorized the clown’s schedule?" "I have. The clown does balloon animals at two, magic tricks at three, and a tactical bathroom break at three-ten. That’s our window." "Three-ten? That gives us, what, five minutes? I need at least six." "Bill, you can nick presents faster than a kid on a sugar rush. Besides, I’ve arranged a distraction." "Let me guess. Fire ants in the fruit punch?" "One better. Piñata full of confetti and fake spiders." "Molly, you’re a genius. While everyone’s busy dodging arachnids, I’ll sweep the loot. What about the birthday kid?" "Decoy cake. They'll be too busy crying over the missing sprinkles to notice us." "Okay, here’s the plan. Glitter cannon at the door, piñata explosion on my signal, and I grab the gifts." "And we make our getaway in the bounce house." "Perfect. No one ever suspects the bounce house." "Ready?" "Always."
id
"gen-1744656123-EzOHJtgZ8TyTpVfgme6u"
upstream_id
"chatcmpl-BMJ2qQ2OxYvkkf5SnxpKuLHU6OeUT"
total_cost
0.00247
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:42:08.047197+00:00"
Monday, April 14th, 2025 at 6:42:08 PM GMT+00:00
model
"openai/gpt-4.1-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
360
moderation_latency
162
generation_time
2956
tokens_prompt
68
tokens_completion
292
native_tokens_prompt
67
native_tokens_completion
292
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
0.00247
Evaluation details
Result
Evaluator
Details
Meta Data
99.7443%
Matches word count
n/a
neededClean
false
words
196
0.0000%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 50.00%
neededClean
false
wordsTotal
196
wordsDialogue
196
49.8722%