NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-19-01J35T4DS783MWQRF0VC00HB30
Run Details
Model:
GPT-4o, May 13th (temp=1)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.6s
Cost:
$0.005060
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
50.0000%
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
Molly and Bill hunched over their makeshift blueprint on the café table. "Alright, Bill, the target's Timmy's birthday party, 3 PM," Molly said, tapping the crayon-scribbled map. "Kids' party? How tough could it be?" Bill chuckled, sipping his espresso. "Focus, we've got 19 kids and their parents to deal with," Molly shot back, pointing to a stick figure drawing of the backyard. "The presents will be here, under the 'Happy Birthday' banner." "Piece of cake. What's the plan, Mol?" "First, we blend in. I've got us costumes." "What, like clowns?" Bill asked, eyebrows raised. "No, no. We're going as magicians. Distraction is key." "Magicians, huh? Can you pull a rabbit out of a hat?" he smirked. "More like pulling presents out of a party," Molly grinned. "You do the tricks, I'll grab the goods." "And what about the kids? They love presents." "That's why you're doing the tricks, Bill. Keep 'em busy." "And the parents?" "There's a piñata station over here," Molly explained. "We stage a candy ‘emergency’—you distract, I snatch." "Sounds like a plan, but what if something goes wrong?" "Improvise. We're magicians, remember?" Bill laughed. "Got it. When do we start?" "Tomorrow," Molly said, smiling. "Showtime at three."
id
"gen-duT6tV6B14HDrShibg4JcrEaiHhX"
total_cost
0.00506
upstream_id
"chatcmpl-9mjvgWZLfEh8G7LZ5QRCmaYjJm9tZ"
created_at
"2024-07-19T15:35:34.955717+00:00"
7/19/2024, 3:35:34 PM
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
10149
moderation_latency
238
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
318
native_tokens_prompt
67
native_tokens_completion
315
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00506
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
0.00%
Dialogue to Total Word Ratio
Ratio: 74.63%, Deviation: 24.63%
neededClean
false
wordsTotal
201
wordsDialogue
150
50.0000%