NC Bench
Overview
About
Tests
Models
Model
GPT-4o, Aug. 6th (temp=1)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-08-06-01J4MXY0ZRJCZ2WJ0XHB468FYR
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, Bill, here's the plan: we'll sneak in through the side gate." "And blend with the clowns? Brilliant, Molly!" "Exactly. We act as if we're hired for entertainment." "I'm more of a mime, you know." "Perfect! You mime, I'll do balloon animals." "Balloon animals? I can't even blow up a balloon!" "Don't worry, I brought one of those pump things." "Molly, what if they ask for complex shapes?" "Stick to dogs. Everyone loves dogs." "Alright, and while they're distracted?" "We snatch the presents and stash them in oversized clown pants." "Oversized clown pants? Where do we get those?" "Borrowed from Crazy Larry's Costume Emporium." "And what if we get caught?" "We use Plan B: fake magic tricks." "Like pulling a rabbit out of a hat?" "No, like making us disappear in a cloud of smoke." "Smoke bombs in party hats?" "Exactly!" "And if the kids cry?" "We'll apologize and offer more balloon dogs." "I must admit, Molly, this plan is genius." "We'll be legends in the heist world, Bill." "Alright, let’s synchronize our watches." "I have a better idea: let’s synchronize our clown noses." "Honk if you agree." "Honk! Ready, partner?" "Always, partner. Let’s make 'em laugh."
id
"gen-qmFy7usBry0bYgekfbLy5zzffiZY"
total_cost
0.0029875
upstream_id
"chatcmpl-9tNENuyFjGurit3dHKOj8yQNZ2HzO"
created_at
"2024-08-06T22:46:11.882489+00:00"
Tuesday, August 6th, 2024 at 10:46:11 PM GMT+00:00
model
"openai/gpt-4o-2024-08-06"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
4079
moderation_latency
391
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
292
native_tokens_prompt
67
native_tokens_completion
282
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0029875
Evaluation details
Result
Evaluator
Details
Meta Data
99.9190%
Matches word count
n/a
neededClean
false
words
197
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
197
wordsDialogue
197
68.3535%