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
2024-07-19-01J35SN8N473JWCMWSR03EQPV0
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
"Alright, Bill, what's the plan?" "Simple, Molly. We slip in with the entertainers." "Clowns or magicians?" "Neither, Molly. Balloon artists." "Balloon artists? Really? We're going to wear squeaky shoes?" "It's genius, Molly. No one suspects balloon artists." "Fine. How do we get in?" "Easy. I rented us a real gig. We show up, make a few dogs, maybe an octopus." "An octopus? Have you ever made a balloon octopus?" "How hard can it be? It's balloons!" "Right, and then what?" "Then, the kids are distracted, and we go for the presents." "And how do we carry them out, Bill? With balloon animals in hand?" "Pillowcases. We act like Santa Claus but with more style." "Makes sense. What about the parents?" "I’ve got that covered. We hand them some ‘special’ balloons filled with... helium." "Helium? You want the parents to sound like chipmunks?" "Exactly, they laugh, we swipe." "I can’t believe this, Bill. You actually think it’ll work?" "Have some faith, Molly. What's the worst that can happen?" "We get caught, and end up performing at prison talent shows." "Okay, true, but it’s a foolproof plan." "You're a madman, Bill. But I'm in." "Good. Let’s practice those balloon dogs." "And the octopus."
id
"gen-ZAcFMjIVJguc4BlnGqgbpL3FwArq"
total_cost
0.00491
upstream_id
"chatcmpl-9mjnf8ROwVvaWeR4jXG8nKYkvWOPa"
created_at
"2024-07-19T15:27:19.87354+00:00"
Friday, July 19th, 2024 at 3:27:19 PM GMT+00:00
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
11991
moderation_latency
206
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
312
native_tokens_prompt
67
native_tokens_completion
305
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00491
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
201
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
201
wordsDialogue
201
68.3935%