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
2024-07-19-01J35SP4P2BY65B695D5FWJSFQ
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, could you please explain why we're targeting a children's party? Have we sunk so low?" "Bill, think about it. Who secures a five-year-old's birthday party? No one. That's who." "But... children's presents? Really? What are we even looking at here? Puzzle boxes and action figures?" "Maybe. But trust me, there’ll be some parents' wallets, plus those gift cards. Ever been to one of these things? They practically throw money at the kids." "Okay, fine, but how do we get in? You think they'll just roll out a red carpet for a couple of strangers?" "No, we blend in. Get some balloons, face paint. Act like we belong. Pretend we're from the party planner." "Party planner?" "Yeah, like those entertainers who show up at these things. You know, clowns, magicians, people like that." "You want me to be a clown? I'm not putting on face paint." "Relax, Bill. Fine, you can be a magician. Sleight-of-hand expert. Works with our skill set, don’t you think?" "Great, a magician. Now, where do we stash our loot? We can’t exactly walk out with armfuls of presents." "Molly's Magic Bag." "Molly's Magic Bag? You have one?" "I'm working on it. Just think of it as... our ultimate prop." "So, paint on smiles, entertain some kids, and walk out with a bag full of loot. Simple?" "Exactly. Now, practice your card tricks. We’re going to be the hit of the party."
id
"gen-qPQ67K4U1d8XekwtUjz5890e2dy7"
total_cost
0.0053
upstream_id
"chatcmpl-9mjo8EDVeSzbXQTlcUVFap3HP93qj"
created_at
"2024-07-19T15:27:48.994469+00:00"
Friday, July 19th, 2024 at 3:27:48 PM GMT+00:00
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
12368
moderation_latency
180
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
340
native_tokens_prompt
67
native_tokens_completion
331
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0053
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
240
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
240
wordsDialogue
240
18.3940%