NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 Nemotron 70B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-10-16-01JABHYBNMM6N7YCGE4NXR6NRN
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
"Alright, Molly, we've got the layout of the playplace. How do you plan on getting us past the bouncy castle?" "Leave that to me, Bill. I've been practicing my 'enthusiastic mom' face. I can blend in with the parental units." "Uh-huh. And what's the signal to grab the loot?" "Whenever someone yells 'Pin the Tail on the Donkey' for the fifth time, we make our move. The adults will be distracted, and the kids will be too sugar-high to notice." "Genius. What's the estimated haul?" "Minimum of twenty gift cards, at least a dozen shiny new toys, and if we're lucky, a few unguarded piñatas filled with cash." "Lucky? You think piñatas are just filled with cash willy-nilly?" "Well, a thief can dream, can't she? Okay, serious for a sec – how's the get-away stroller holding up?" "Holding up like a charm. Stolen from a genuine hipster, so it's got all the fixin's: neon rims, a coffee cup holder... " "Perfect. We're going to make off like bandits... with a really cool stroller."
id
"gen-1729112256-IwQ3DbTpOilU4U32zPc4"
upstream_id
"cmpl-RqBW7uINWPCwrHqHUYNeWctT"
total_cost
0.00012765
cache_discount
(null)
created_at
"2024-10-16T20:57:48.850576+00:00"
Wednesday, October 16th, 2024 at 8:57:48 PM GMT+00:00
model
"nvidia/llama-3.1-nemotron-70b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"DeepInfra"
latency
175
moderation_latency
(null)
generation_time
11756
finish_reason
"stop"
tokens_prompt
102
tokens_completion
257
native_tokens_prompt
71
native_tokens_completion
257
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00012765
Evaluation details
Result
Evaluator
Details
Meta Data
2.0116%
Matches word count
n/a
neededClean
false
words
175
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
175
wordsDialogue
175
19.3998%