NC Bench
Overview
About
Tests
Models
Model
GPT-4o, Aug. 6th (temp=0)
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-08-06-01J4MXRMRVCVFMPT2HHCKDT2Z6
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
Molly and Bill crouched behind a row of hedges, peering at the chaos of balloons and sugar-fueled children. "Bill, are you sure this is a good idea?" Molly whispered, eyeing a kid wielding a foam sword. "Absolutely, Molly. Who'd suspect a heist at a kid's party?" Bill grinned, adjusting his oversized sunglasses. "But what if we get caught? I don't want to end up in a bouncy castle prison," Molly said, glancing nervously at the inflatable fortress. "Relax, Molly. We blend in, grab the loot, and bounce. Literally," Bill chuckled, pointing at the bouncy castle. "Okay, but what's the plan?" Molly asked, still skeptical. "Simple. You distract them with your balloon animal skills," Bill suggested, nodding towards the pile of colorful balloons. "My balloon animals look like abstract art," Molly protested. "Perfect! They'll be so confused, they won't notice me swiping the presents," Bill assured her. "And if they do notice?" Molly raised an eyebrow. "We'll blame it on the clown," Bill said, gesturing to the clown struggling with a unicycle. "Fine, but if this goes south, I'm blaming you," Molly warned. "Deal. Now, let's go make some balloon... things," Bill said, leading the way with a mischievous wink.
id
"gen-Xzoq7432f117nHEdBT5JPIv3whc4"
total_cost
0.0030075
upstream_id
"chatcmpl-9tNBYqXBczTfKoKyvTUqqncFSLGLr"
created_at
"2024-08-06T22:43:16.173079+00:00"
Tuesday, August 6th, 2024 at 10:43:16 PM GMT+00:00
model
"openai/gpt-4o-2024-08-06"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
3892
moderation_latency
1260
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
290
native_tokens_prompt
67
native_tokens_completion
284
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0030075
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
words
200
97.4725%
Dialogue to Total Word Ratio
Ratio: 54.00%, Deviation: 4.00%
neededClean
false
wordsTotal
200
wordsDialogue
108
98.7362%