NC Bench
Overview
About
Tests
Models
Model
Hermes 3 70B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-08-26-01J68DGBZ9C34H0M3P6NJW8JZJ
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 sat in their van, watching the children's party through binoculars. Molly: "This is going to be easier than we thought. Look at all those presents just waiting to be taken." Bill: "Yeah, but we need a distraction. Something to keep the kids and parents occupied while we grab the goods." Molly: "How about a clown? Kids love clowns, right?" Bill: "Or a fire eater. That would definitely draw a crowd." Molly: "Ooh, or a magician! We could hire one to perform while we make our move." Bill: "I like the way you think, Molly. But we need to be quick about it. In and out, like a couple of ninjas." Molly: "Speak for yourself, I'm more of a piranha. I'll swim through those presents like they're a school of unsuspecting fish." Bill: "Just don't let any of the kids catch you. They might cry if they see their presents being stolen by a couple of grown-ups." Molly: "Don't worry, I'll be so fast they won't even know what hit 'em. This is going to be the easiest heist ever!"
id
"gen-Kjnd8Y0mQask3dMvLHxBgdzxFJRr"
total_cost
0.0001332
upstream_id
"chat-9c81ae6633e74f759bba46811ddf7405"
created_at
"2024-08-26T22:39:45.933217+00:00"
Monday, August 26th, 2024 at 10:39:45 PM GMT+00:00
model
"nousresearch/hermes-3-llama-3.1-70b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
238
moderation_latency
(null)
generation_time
12573
finish_reason
"stop"
tokens_prompt
75
tokens_completion
253
native_tokens_prompt
78
native_tokens_completion
255
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001332
Evaluation details
Result
Evaluator
Details
Meta Data
43.3783%
Matches word count
n/a
neededClean
false
words
183
99.8330%
Dialogue to Total Word Ratio
Ratio: 87.98%, Deviation: 2.02%
neededClean
false
wordsTotal
183
wordsDialogue
161
71.6057%