NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-08-06-01J4MXSENGRTGEFE4GDNFEVN5Y
Run Details
Model:
GPT-4o, Aug. 6th (temp=1)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
4.7s
Cost:
$0.003148
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.8722%
Overall
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
“The key to this heist, Bill, is stealth. We've got to blend in with the clowns,” Molly whispered, adjusting her oversized bowtie. “Clowns? You mean we’re dressing up as clowns to swipe presents from seven-year-olds?” Bill squinted, his mustache twitching with skepticism. “Exactly. Who suspects the entertainment? Plus, if we’re caught, we just do some balloon animals and poof! Escape in a haze of laughter.” “Balloon animals? Molly, the last time you made a dog, it looked like a bloated sausage.” “Details, Bill, details! Focus on the big picture. Distraction is our best friend.” “And the face paint’s our mask, then?” “Precisely! See, you’re catching on. Now, here’s the plan: we slip in during cake cutting. Kids are distracted, parents are busy snapping photos.” “You mean every adult’s occupied ensuring these tiny humans don’t launch frosting missiles?” “Exactly, my dear Watson! While they’re focused on frosting, we collect our bounty.” “And if they spot you shoving gifts in a sack?” “I’ll charm them with my juggling skills. Remember, misdirection is key.” “You can’t juggle!” “That’s what you’re here for, partner. To stand behind, holding the gifts while looking utterly befuddled.” “Fine, Molly. But if I hear one honk from a clown nose, I’m out.”
id
"gen-bPAFlZ1Qgrv9WWLbir0NwJ65aCbV"
total_cost
0.0031475
upstream_id
"chatcmpl-9tNBxgScNbes2Ym12DFUxWlpgxDae"
created_at
"2024-08-06T22:43:42.072861+00:00"
8/6/2024, 10:43:42 PM
model
"openai/gpt-4o-2024-08-06"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
4230
moderation_latency
297
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
301
native_tokens_prompt
67
native_tokens_completion
298
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0031475
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
0.00%
Dialogue to Total Word Ratio
Ratio: 93.69%, Deviation: 43.69%
neededClean
false
wordsTotal
206
wordsDialogue
193
49.8722%