NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-08-26-01J68D7K046NMWJ45KY7VK9KM4
Run Details
Model:
Hermes 3 405B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
17.5s
Cost:
$0.000000
Provider:
Lambda
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
40.6364%
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
Molly and Bill, clad in black, crouched behind a bush, eyeing the festive scene before them. The children's party was in full swing, with laughter and playful shrieks filling the air. Colorful decorations adorned the backyard, and a mountain of brightly wrapped presents sat temptingly in the center. "This is going to be a piece of cake," Molly whispered, a mischievous glint in her eye. Bill nodded, a grin spreading across his face. "I've never seen so many presents in one place. We'll be set for months." "Just imagine their little faces when they realize all their gifts are gone," Molly said, stifling a giggle. "Okay, here's the plan," Bill began, his tone turning serious. "You create a distraction, and I'll swoop in and grab as many presents as I can carry." Molly furrowed her brow. "What kind of distraction?" Bill smirked. "You're going to love this. You'll dress up as a clown and entertain the kids while I work my magic." Molly rolled her eyes. "A clown? Really?" "Trust me, it'll be hilarious," Bill assured her. "And while you're at it, you can snag some cake too."
id
"gen-QnwLcvCVfo7OorCQZyCzaf7wkSel"
total_cost
0
upstream_id
"chatcmpl-8813dab8-0ead-4b2b-b4ea-cd607faac320"
created_at
"2024-08-26T22:35:02.729555+00:00"
8/26/2024, 10:35:02 PM
model
"nousresearch/hermes-3-llama-3.1-405b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Lambda"
latency
5252
moderation_latency
(null)
generation_time
12082
finish_reason
"stop"
tokens_prompt
67
tokens_completion
260
native_tokens_prompt
83
native_tokens_completion
261
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
188
0.00%
Dialogue to Total Word Ratio
Ratio: 53.19%, Deviation: 43.19%
neededClean
false
wordsTotal
188
wordsDialogue
100
40.6364%