NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-23-01J3G81XNYA29876633S3VJDBW
Run Details
Model:
Llama 3.1 8B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1.3s
Cost:
$0.000070
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.6885%
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 limousine idled outside the fortress-like mansion, its tinted windows reflecting the manicured lawn and gleaming party favors. Molly consulted the stack of neatly organized papers, her eyes scanning the list of "hosts" and "guests of honor". Bill slid in beside her, adjusting his tuxedo to perfection. "Billy, Billy, Billy," she whispered, a sly grin spreading across her face. "I've got the play-by-play. Party scheduled for 2 PM sharp. Two dozen balloons tied to a stationary trampoline, which we'll expertly exploit to gain access to the gift wrap room." Bill whistled. "Sounds like a piece of cake. How many presents are we talking?" "Assuming every kid gets a goody bag and a half dozen physical gifts, I'd estimate a total of—" "A minimum of two hundred unwrapped riches waiting to be pilfered," Bill interrupted, his eyes shining with excitement. "But, Molly, my love, have we considered the security measures? Those parents are likely to have a dog that can sniff out a dropped pizza, let alone a master thief like yourself." Molly snorted. "Pfft, we've got this, Billy. We've been casing this joint for weeks. The only thing we have to worry about is getting to the presents before the inevitable sugar coma sets in."
id
"gen-QDXhhPuua29VJbnY6SjLCY4ibg6v"
total_cost
0.0000704
upstream_id
"7553aee1-cce6-4318-9588-fccf3c045c1d"
created_at
"2024-07-23T16:51:08.143842+00:00"
7/23/2024, 4:51:08 PM
model
"meta-llama/llama-3.1-8b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
1062
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
281
native_tokens_prompt
70
native_tokens_completion
282
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000704
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
205
0.00%
Dialogue to Total Word Ratio
Ratio: 69.57%, Deviation: 19.57%
neededClean
false
wordsTotal
207
wordsDialogue
144
49.6885%