NC Bench
Overview
About
Tests
Models
Model
GPT-4o, May 13th (temp=1)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35SKTQPJ0556G13W05JN60C
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, what's the plan?" "Molly, first we blend in. Got the costumes?" "Of course. I'm a clown, you're a magician." "Perfect. While the kids are distracted by your balloon animals, I'll do some magic of my own." "What kind of magic? And please don't say sawing me in half." "Much simpler. Card tricks. Kids love those." "Right, and while you do that, I sneak off to the gift table?" "Precisely. You spot the loot, text me the location." "Got it. But what if someone catches me?" "Misdirection, Molly. You're a clown. Act goofy, juggle, I don't know, fall down or something." "Juggling I can do. Falling down, not so much." "Okay, fine. Just improvise. Now, about the exit strategy." "Back door, through the kitchen. I scoped it out yesterday." "And the getaway vehicle?" "Parked a block away. No point in arousing suspicion." "Nice. So, in and out, five minutes tops?" "That's the idea. But remember, these are kids, Bill, not guards." "Right, we gotta keep it fun, no trauma." "Understood. Oh, and let's avoid the cake. Big mess if it gets smashed." "Got it. Ready, clown?" "Ready, magician." "Let's make these presents disappear." "In a puff of colorful smoke."
id
"gen-dB0KHN26n7Obev4ZINJMRx68AVA6"
total_cost
0.004805
upstream_id
"chatcmpl-9mjmu095WedJrUWKdPoPhYzZhdj91"
created_at
"2024-07-19T15:26:27.01725+00:00"
Friday, July 19th, 2024 at 3:26:27 PM GMT+00:00
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
5991
moderation_latency
285
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
307
native_tokens_prompt
67
native_tokens_completion
298
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.004805
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
words
200
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
200
wordsDialogue
200
68.3940%