NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-08-26-01J68DJ4KPD77JCVEPQNA4ZNCZ
Run Details
Model:
Hermes 3 70B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.2s
Cost:
$0.000140
Provider:
Hyperbolic
Evaluation summary
Score
Evaluator
Details Link
35.00%
Matches word count
(details)
80.44%
Dialogue to Total Word Ratio
(details)
57.7199%
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 crouched behind a hedge, peering through the latticed fence at the bustling backyard. Colorful streamers fluttered in the breeze, and the shrieks of laughter from the children's party pierced the air. "Are you sure about this, Bill?" Molly whispered, her brow furrowed. "I mean, it's a kids' party. It feels... wrong." Bill scoffed, adjusting his ski mask. "Oh, come on, Molly. They're just presents. The kids will get over it. Besides, we need the cash." Molly bit her lip, hesitating. "But what if we get caught? I don't want to spend my birthday behind bars." "Relax, it'll be a piece of cake," Bill reassured her with a wink. "I've got the whole thing planned out. You grab the presents from the gift table while I keep an eye out. We'll be in and out in no time." Molly sighed, shaking her head. "Fine, but if this goes south, I'm blaming you." Bill grinned, his eyes gleaming with mischief. "That's the spirit! Now, on my count. Three, two, one... go!" They burst from the hedge, sprinting towards the unsuspecting party-goers.
id
"gen-00IyWUnT5nQr0MRTlHnioc8AFarg"
total_cost
0.00014
upstream_id
"chat-f746b3a0f533474bb72030262a9b5456"
created_at
"2024-08-26T22:40:42.114153+00:00"
8/26/2024, 10:40:42 PM
model
"nousresearch/hermes-3-llama-3.1-70b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
692
moderation_latency
(null)
generation_time
10329
finish_reason
"stop"
tokens_prompt
75
tokens_completion
270
native_tokens_prompt
78
native_tokens_completion
272
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00014
Evaluation details
Result
Evaluator
Details
Meta Data
35.00%
Matches word count
n/a
neededClean
false
words
182
80.44%
Dialogue to Total Word Ratio
Ratio: 56.83%, Deviation: 6.83%
neededClean
false
wordsTotal
183
wordsDialogue
104
57.7199%