NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-08-26-01J68D1QJJ0XYJJEW1KNYX1F3B
Run Details
Model:
Hermes 3 405B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
12.9s
Cost:
$0.000000
Provider:
Lambda
Evaluation summary
Score
Evaluator
Details Link
2.01%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
1.0058%
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
Molly and Bill sat in their beat-up van, binoculars trained on the festive chaos unfolding across the street. "Alright, Bill, here's the plan," Molly said, a mischievous glint in her eye. "You create a distraction while I sneak in and grab the presents." Bill raised an eyebrow. "What kind of distraction are we talking about here, Mol?" "Use your imagination! Set off some fireworks, start a conga line, just make sure all eyes are on you." " Conga line? At a kids' party? You're the expert, but that sounds like a recipe for disaster." Molly smirked. "Exactly. Chaos is our friend. While you're dancing, I'll be making off with the goods." "I hope you're right about this, Mol. Stealing from kids doesn't exactly feel like our finest hour." "Hey, we're not taking anything they'll miss. Besides, it's not like we don't have a reputation to uphold. The satuĊes are known for their daring heists!" "I suppose you're right. Alright, fine. But if I end up getting thrown in a bouncy castle jail, you owe me one."
id
"gen-WPlj0UPFYSEvh1oKw0QuY3ngQ5en"
total_cost
0
upstream_id
"chatcmpl-de73d371-7e61-4c70-b7b9-a4d5c3a75ccf"
created_at
"2024-08-26T22:31:46.268249+00:00"
8/26/2024, 10:31:46 PM
model
"nousresearch/hermes-3-llama-3.1-405b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Lambda"
latency
905
moderation_latency
(null)
generation_time
11927
finish_reason
"stop"
tokens_prompt
67
tokens_completion
247
native_tokens_prompt
83
native_tokens_completion
248
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0
Evaluation details
Result
Evaluator
Details
Meta Data
2.01%
Matches word count
n/a
neededClean
false
words
175
0.00%
Dialogue to Total Word Ratio
Ratio: 81.25%, Deviation: 31.25%
neededClean
false
wordsTotal
176
wordsDialogue
143
1.0058%