NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 70B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-23-01J3G7ZXBMSGGZAEYFQA7VYNPP
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've been casing the joint, Bill. I'm telling you, it's a treasure trove of Tamagotchis and Fisher-Price crap," Molly said, eyes shining with excitement. "Tamagotchis are back in?" Bill asked, raising an eyebrow. "Apparently, kids these days love 'em some retro," Molly replied, chuckling. "But seriously, this party is going to be a goldmine. Rich kids, fancy gifts... we could fence this stuff for a small fortune." "Okay, okay, I'm in. But how do we get past the security? I mean, it's not like they're going to let us just waltz in and start swiping presents," Bill said, rubbing his chin thoughtfully. "Leave that to me. I've got a plan," Molly said, grinning mischievously. "We'll just blend in with the other parents. You know, the ones who are secretly drunk and miserable, just waiting for the party to be over so they can go home and take a nap." Bill snorted. "You're a genius, Molly. But what's the contingency plan if we get caught?" Molly shrugged. "We'll just pretend to be hippies who think the concept of personal property is, like, soooo bourgeois."
id
"gen-NemgpXgiiFAzIGnw0CLIho8iYoSj"
total_cost
0.000306
upstream_id
"29e0cbb7-404e-4f29-8b00-2d64d2b40706"
created_at
"2024-07-23T16:50:04.320934+00:00"
Tuesday, July 23rd, 2024 at 4:50:04 PM GMT+00:00
model
"meta-llama/llama-3.1-70b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
3221
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
268
native_tokens_prompt
70
native_tokens_completion
270
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000306
Evaluation details
Result
Evaluator
Details
Meta Data
51.9255%
Matches word count
n/a
neededClean
false
words
184
92.8580%
Dialogue to Total Word Ratio
Ratio: 84.78%, Deviation: 5.22%
neededClean
false
wordsTotal
184
wordsDialogue
156
72.3917%