NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-08-26-01J68D9BVTXJKWPRAWP1NB4WG0
Run Details
Model:
Hermes 3 70B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
14.2s
Cost:
$0.000152
Provider:
Hyperbolic
Evaluation summary
Score
Evaluator
Details Link
35.00%
Matches word count
(details)
93.61%
Dialogue to Total Word Ratio
(details)
64.3078%
Overall
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
"What's the plan for this job, Bill? I hope you've got something good up your sleeve," Molly said, her eyes gleaming with mischief. Bill smirked, rubbing his hands together. "Oh, I've got a doozy for you, Molly. Picture this: a bunch of snotty-nosed brats running around, completely oblivious to the fact that we're about to make off with all their shiny new toys." Molly laughed, clapping her hands together. "I like the way you think, partner. But how do you propose we get in there without raising suspicions?" "Leave that to me, my dear. I've got a costume that'll make me look like the most convincing clown this side of the circus. As for you, you'll blend right in with the moms." Molly scoffed, "ME? A mom? I don't think so, Bill. I'm more of a fun aunt type." "Fine, a cool aunt then. The point is, we'll be in and out before they can even sing 'Happy Birthday.' And we'll be rolling in so many toys, we'll have to rent a U-Haul to get them all back to the hideout." Molly cackled, her eyes sparkling with glee. "Count me in, Bill. This is going to be a piece of cake." "And don't forget the cake!" Bill added with a wink. "I have a sweet tooth, you know."
id
"gen-gHZ6eDqiK6byyn50LPLbgt4suOB0"
total_cost
0.0001524
upstream_id
"chat-7bb68c49f0d94c1498e13ea634d1f02f"
created_at
"2024-08-26T22:35:57.662989+00:00"
8/26/2024, 10:35:57 PM
model
"nousresearch/hermes-3-llama-3.1-70b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
265
moderation_latency
(null)
generation_time
13759
finish_reason
"stop"
tokens_prompt
75
tokens_completion
301
native_tokens_prompt
78
native_tokens_completion
303
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001524
Evaluation details
Result
Evaluator
Details
Meta Data
35.00%
Matches word count
n/a
neededClean
false
words
218
93.61%
Dialogue to Total Word Ratio
Ratio: 84.93%, Deviation: 5.07%
neededClean
false
wordsTotal
219
wordsDialogue
186
64.3078%