NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-08-06-01J4MXWP6R71D4VBF6HGGCNQMM
Run Details
Model:
GPT-4o, Aug. 6th (temp=1)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.9s
Cost:
$0.003037
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.01%
Dialogue to Total Word Ratio
(details)
49.9625%
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
"So, tell me again, why a children's party, Bill?" Molly asked, eyeing the colorful balloons fluttering beyond the backyard fence. "Think about it, Molly. Who ever suspects that the presents are under a covert operation?" Bill grinned, adjusting his party hat. "Because they're for a six-year-old, and we're adults?" Molly quipped, shaking her head. "Exactly! Nobody sees it coming. We're hidden in plain sight," Bill said, gesturing dramatically at the crowd of pint-sized revelers. "Okay, so how do we blend in? Finger painting? Musical chairs?" Molly arched an eyebrow. "Nah, I've got a plan. We start with the cake. Everyone’s attention is always on the cake, right?" Bill replied. "And in the chaos of sugary excitement, we just roll out with handfuls of presents?" Molly laughed. "You think I’m joking, but yes. Cake chaos equals perfect distraction," Bill affirmed pompously. "Next you'll say we're escaping on scooters," Molly teased. "Got two lined up. Spots in the parking lot. Inconspicuous," Bill said, nodding toward the alley. "Bill, sometimes I wonder if I'm the sane one or just cleverly misled." Molly sighed, fiddling with her gift-wrapped boombox. "See? Distracted already. Told you it’d work," Bill winked, leading the charge.
id
"gen-VVekMSW3j5Z2c78EK01EcgEnEOjB"
total_cost
0.0030375
upstream_id
"chatcmpl-9tNDgPSmq7F2NEVq18hkcub8t8xK0"
created_at
"2024-08-06T22:45:27.313505+00:00"
8/6/2024, 10:45:27 PM
model
"openai/gpt-4o-2024-08-06"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
3476
moderation_latency
285
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
300
native_tokens_prompt
67
native_tokens_completion
287
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0030375
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
0.01%
Dialogue to Total Word Ratio
Ratio: 67.66%, Deviation: 17.66%
neededClean
false
wordsTotal
201
wordsDialogue
136
49.9625%