NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 Euryale 70B v2.2
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-20-01J881JZFBTYWMJBZY8B8Q7CQ1
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, are you out of your mind?" Bill said, his voice a mix of incredulity and annoyance. "We're master thieves, for crying out loud. We've pulled off heists in banks, museums, and even the local library. But a children's party? I've seen better targets at a garage sale." Molly grinned. "A pack of toddlers playing in sugar-fueled chaos? It should be easy as pie. And think about it, those little brats get gifts worth hundreds." " Hundreds? From whom? Their impoverish parents or seven aunts and uncles who bought cheap sh*t from the mall?" "Don't knock it, every little bit counts. Plus, I heard Mummy is into groceries, their parties can run a bit pricey." "Great, some Tofurky or organic bacon. My idea of a score." "Listen, how else are we gonna score some fresh gadgets to fence?" Bill sighed. "I don't know. Something like...oh, I don't know...the new iPhone update?" "Too obvious. But I've heard rumors of a PS5 anyone's still wrapping around here." "That retro typo-drive? The stuff of dreams indeed, let's get green!"
id
"gen-aaOAbuW33S2UZQw5ukkkVZ3aoIja"
total_cost
0.000489
upstream_id
"chatcmpl-7aa446d8-453e-4c26-9df5-7e250fee069a"
created_at
"2024-09-20T15:43:04.03903+00:00"
Friday, September 20th, 2024 at 3:43:04 PM GMT+00:00
model
"sao10k/l3.1-euryale-70b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Infermatic"
latency
61
moderation_latency
(null)
generation_time
24479
finish_reason
"stop"
tokens_prompt
102
tokens_completion
253
native_tokens_prompt
72
native_tokens_completion
254
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000489
Evaluation details
Result
Evaluator
Details
Meta Data
6.0907%
Matches word count
n/a
neededClean
false
words
177
99.8092%
Dialogue to Total Word Ratio
Ratio: 92.09%, Deviation: 2.09%
neededClean
false
wordsTotal
177
wordsDialogue
163
52.9500%