NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-19-01J35T72HEP841JW1400EDQ903
Run Details
Model:
GPT-4o, May 13th (temp=1)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.3s
Cost:
$0.005090
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
14.30%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
25.5447%
Overall
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, are you ready for this?" "Ready? I'm born ready, Molly. But remind me again, why are we stealing from a kid's party?" "Because, Bill, it's the last place anyone would expect. Who'd suspect a couple of thieves at a birthday bash?" "Good point. So, what's the plan?" "Easy. We go in as clowns." "Clowns? I hate clowns. Couldn't we be magicians or something cooler?" "Bill, focus! We'll distract the kids with balloon animals and magic tricks. Meanwhile, I sneak off to the gift table." "And what am I doing while you’re pilfering presents?" "Keeping the parents entertained. Asking them to volunteer for tricks. Billy, you ever juggle?" "Juggle? No, but how hard can it be?" "Think fast!" "Whoa, when did you bring out those oranges?" "Practice makes perfect. Anyway, once I’ve got the goods, we high-tail out of there." "Okay, but what if one of the kids starts crying?" "That’s why we have plan B. A pocket full of candy. Instant crowd control." "Why do you make it sound so easy?" "Bill, it’s a child’s party, not Fort Knox. Just remember to smile, be funny, and keep moving." “I guess I can do that. When do we start?” "Tomorrow. So, get your big red nose ready." "You think I could pull off a top hat?" "Bill, focus. It’s clown time."
id
"gen-C4hyBgCSupcCyjlt88Ricl6SvAkb"
total_cost
0.00509
upstream_id
"chatcmpl-9mjx5cgiXnbtQZMxIBgi6ZQp0bUN1"
created_at
"2024-07-19T15:37:00.493699+00:00"
7/19/2024, 3:37:00 PM
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
5490
moderation_latency
187
generation_time
390
finish_reason
"stop"
tokens_prompt
68
tokens_completion
322
native_tokens_prompt
67
native_tokens_completion
317
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00509
Evaluation details
Result
Evaluator
Details
Meta Data
14.30%
Matches word count
n/a
neededClean
false
words
221
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
222
wordsDialogue
222
25.5447%