NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-08-06-01J4MXVZ2VMDY3GQHC1X2Z716B
Run Details
Model:
GPT-4o, Aug. 6th (temp=1)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.7s
Cost:
$0.003158
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 10% 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
Under the glow of mismatched fairy lights in a dimly lit basement, Molly spread out a crudely hand-drawn map of the local community center. Confetti stuck to the edges of the paper, remnants from an earlier, more innocent occasion. Bill shoved a chair aside, squinting at the plot. "Bold move, breaking into a birthday party," he muttered, tapping his finger on the spot marked 'Treasure Trove.' “Kid’s party, Bill,” Molly corrected, adjusting her stolen tiara. “And it's the perfect cover.” Bill raised an eyebrow. “You planning on showing up with a gift, or just the bag to nab ‘em?” Molly grinned, pulling a large, glittery sack from the pile. “Fancy stealing from pint-sized pirates?” “They’re gonna spot us a mile away. You still got that unicorn costume?” Molly nodded, her enthusiasm unshaken. “Nothing says ‘belong here’ like a magical creature.” Bill sighed. “Still feels wrong, robbing kids.” “Think of it as liberating excess sugar.” Bill smirked. “Alright. So, who’s distracting the tiny guards?” “Rock, paper, scissors?” Molly shrugged, already curling her fingers into a fist. Bill chuckled, accepting the challenge. “Hope they’ve got cake worth the trouble.” With a mischievous glint, Molly tossed the sack over her shoulder. “Only one way to find out.”
id
"gen-EmnE7fJ2Z99zl5UcjjKpkhhqdREx"
total_cost
0.0031575
upstream_id
"chatcmpl-9tNDIttz87VDPU1FVOLDXJGYqcWs7"
created_at
"2024-08-06T22:45:03.4035+00:00"
8/6/2024, 10:45:03 PM
model
"openai/gpt-4o-2024-08-06"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
3387
moderation_latency
173
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
298
native_tokens_prompt
67
native_tokens_completion
299
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0031575
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: 45.63%, Deviation: 35.63%
neededClean
false
wordsTotal
206
wordsDialogue
94
49.8722%