NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 Nemotron 70B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-10-16-01JABHY5FX4ZKZN7JEQ1KQ5JXX
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
"I'm telling you, Bill, this is the score of a lifetime. 'Bouncy Castle Bash' - who throws a party with that many gifts?" "Rich people, Molly. They're not even hiding it. 'Come one, come all, bring your little urchins and your Amex Black Card'." "Ha! Okay, so we've got the layout, we've got the timing... how do we blend in with the, you know, non-felons?" "We dress the part, of course! I've got a great 'Cool Dad' outfit lined up - plaid, khakis, the works. You can be... hmm, 'Exhausted Mom'?" "Ugh, that's too easy. How about 'Overly-Enthusiastic Party Photographer' instead? I've got a great camera disguise for the loot bag." "Brilliant! Now, which presents do we target first? The ones with the annoyingly loud wrapping paper or the suspiciously heavy ones shaped like a PSP?" "Mmm, priorities, Bill... I say we hit the noisy ones first. My eardrums can't take it. Oh, and if we find a pinata full of cash, that's just icing on the cake." "Claro, mi amigo. Now, let's get this party started... and then promptly shut it down with our thievery."
id
"gen-1729112249-RZ47hhz6XqXf4KDCwNx6"
upstream_id
"cmpl-Rv53XLk5IldjGueOi1pMMS2y"
total_cost
0.00013965
cache_discount
(null)
created_at
"2024-10-16T20:57:38.171181+00:00"
Wednesday, October 16th, 2024 at 8:57:38 PM GMT+00:00
model
"nvidia/llama-3.1-nemotron-70b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"DeepInfra"
latency
69
moderation_latency
(null)
generation_time
7787
finish_reason
"stop"
tokens_prompt
102
tokens_completion
287
native_tokens_prompt
71
native_tokens_completion
287
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00013965
Evaluation details
Result
Evaluator
Details
Meta Data
68.1022%
Matches word count
n/a
neededClean
false
words
186
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
186
wordsDialogue
186
52.4451%