NC Bench
Overview
About
Tests
Models
Model
GPT-4o, Aug. 6th (temp=0)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-08-06-01J4MXVGAEV79CKHS7XJ05N230
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
"Bill, you got the clown costume ready?" "Of course, Molly. Red nose, big shoes, the whole shebang." "And the plan?" "Simple. We waltz in, make balloon animals, and swipe the gifts." "Balloon animals? You know how to make those?" "How hard can it be? Twist, turn, voilà!" "Right. And the kids?" "Easy. Distract them with candy. Kids love candy." "Okay, but what if they start crying?" "Then we juggle. I’ve been practicing." "Juggling? Since when?" "Since I realized kids are unpredictable." "Fine. But what about the parents?" "Leave them to me. I’ll charm them with my clown antics." "Clown antics? You mean like falling over?" "Exactly. Who doesn’t love a clumsy clown?" "Alright, but what if they catch on?" "Then we make a run for it. I’ve got a getaway car ready." "A clown car?" "No, Molly, a real car. We’re not amateurs." "Good. And the presents?" "Stuff them in the big clown pants. No one will suspect a thing." "Big clown pants, huh? You’ve thought of everything." "Always do. Ready to crash a party?" "Ready as I’ll ever be. Let’s make it a birthday to remember." "For us, not them." "Exactly. Let’s go steal some smiles... and presents."
id
"gen-gJaGuqMyR75EX3tesDfZ73nMsODU"
total_cost
0.0031975
upstream_id
"chatcmpl-9tND3ZBISkVXzeAgxRuHD2r03HagX"
created_at
"2024-08-06T22:44:48.451978+00:00"
Tuesday, August 6th, 2024 at 10:44:48 PM GMT+00:00
model
"openai/gpt-4o-2024-08-06"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
3541
moderation_latency
193
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
304
native_tokens_prompt
67
native_tokens_completion
303
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0031975
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
199
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
199
wordsDialogue
199
68.3935%