NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-19-01J35SG64VEQ8KAV2W2A34AVMA
Run Details
Model:
GPT-4o, May 13th (temp=1)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
6.6s
Cost:
$0.005015
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
52.4451%
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, you got the clown costume?" "Check, Molly. You sure this is gonna work?" "Of course! Who suspects clowns at a party?" "True, but why clowns? Why not magicians?" "Have you seen you pull a rabbit out of a hat? Disasters everywhere." "Fair point. Okay, so we just waltz in, do a few balloon animals, and swipe the goods?" "Exactly. You distract, I extract. Piece of cake." "But Molly, what if the kids recognize us?" "They won't. It's Jimmy's party, not some Hollywood premiere." "And the parents?" "Also busy. Cake cutting, phone scrolling. Trust me, we blend in." "Fine, but I've never made a balloon animal." "Not a problem. Here, twist the balloon like this. Instant dog." "Wow, that was easy. What if someone asks for a giraffe?" "Elongate the neck. It's just a dog with a really tall neck." "What about the squeaky shoes?" "Best part! They laugh, we lift." "And the presents are in the main room, right?" "Yup, next to the cake. Quick grab and go." "Suppose there's an emergency. What's plan B?" "Escape hatch under the ball pit. Didn't you read the layout?" "Right, right. Okay, last question. Why are we doing this again?" "Bill, you ever tried paying rent with just stolen candy?" "Point taken. Let's do this, then."
id
"gen-2qEpAfIw9g09BVCLoogV5LebGr1v"
total_cost
0.005015
upstream_id
"chatcmpl-9mjkzM54M2RjfECstK8UTW36S4ePK"
created_at
"2024-07-19T15:24:27.8691+00:00"
7/19/2024, 3:24:27 PM
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
5906
moderation_latency
169
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
318
native_tokens_prompt
67
native_tokens_completion
312
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.005015
Evaluation details
Result
Evaluator
Details
Meta Data
68.10%
Matches word count
n/a
neededClean
false
words
214
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
214
wordsDialogue
214
52.4451%