NC Bench
Overview
About
Tests
Models
Model
GPT-4.1 Mini
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-04-14-01JRTSZ34V41E3FTW0CBQC9PE9
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
“Molly, you really think we can pull this off? A children’s party? What’s next, robbing a daycare?” “Bill, think bigger. The kiddie gang’s got the motherlode—presents, candy, maybe even some of those fancy cupcakes Carol brags about.” “Cupcakes? Now you’re speaking my language. But kids... they’re unpredictable.” “That’s why we have plans. Step one: distraction. You’ve still got those ridiculous clown shoes, right?” “Yeah, but I was hoping you’d let me retire them. They squeak.” “Perfect! Squeaky distraction, my friend. You’ll be the pied piper of chaos while I swipe the goods.” “And what if one of the bratty kids spots us?” “Then we bribe them. Candy ransom. You ever tried haggling with a six-year-old? Open and shut case.” “Okay, so I’m clownish chaos, you’re stealth ninja. What’s our exit?” “Party piñata. Slam it, scatter ’em, chaos ensues, we vanish into the bushes with the loot. Simple.” “Sounds messy.” “Makes it *funny*.” “Alright, Molly. For cupcakes and chaos. Let’s steal some birthday joy.”
id
"gen-1744656373-Z5Tei4Hr3uqLtCKNBTO9"
upstream_id
"chatcmpl-BMJ6rSCkYQWvjzXbF6o6UV8ec2HfS"
total_cost
0.000446
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:46:18.184769+00:00"
Monday, April 14th, 2025 at 6:46:18 PM GMT+00:00
model
"openai/gpt-4.1-mini-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
811
moderation_latency
2043
generation_time
3585
tokens_prompt
68
tokens_completion
261
native_tokens_prompt
67
native_tokens_completion
262
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
0.000446
Evaluation details
Result
Evaluator
Details
Meta Data
0.0002%
Matches word count
n/a
neededClean
false
words
166
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
166
wordsDialogue
166
18.3941%