NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 405B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-23-01J3G51TAQDTMJCQRVZFP0BGZC
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 adjusted her cat-eye mask in the rearview mirror. "Alright, Bill, what's the play? We sneak in with the bouncy castle guys?" Bill rubbed his hands together, a maniacal glint in his eye. "Nah, I was thinking we pose as the entertainment. You know, balloon animals and face paint." Molly raised an eyebrow. "You can do balloon animals?" "No, but how hard can it be, right? It's not like we're actually going to get asked to make any." Molly sighed. "And what about the face paint? I'm not exactly Picasso." "Just smear some blue on their faces and tell them it's a Smurf. Kids love Smurfs." Molly chuckled. "You're a genius, Bill. But what's the real plan once we're inside?" "We grab the presents, toss them in the piñata, and make a break for it during the kid-induced chaos of the piñata smashing." Molly grinned. "I love it. And the best part is, the kids will just think it's all part of the party." Bill chuckled. "I know, right? We're like the anti-Santy Clauses. Instead of bringing gifts, we're taking them away."
id
"gen-pea0nVuD7N0WvkzZUM8xMakC4H54"
total_cost
0.001005
upstream_id
"19ff0cf3-e4da-4238-8749-45281d16daaf"
created_at
"2024-07-23T15:58:48.396975+00:00"
Tuesday, July 23rd, 2024 at 3:58:48 PM GMT+00:00
model
"meta-llama/llama-3.1-405b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
10727
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
263
native_tokens_prompt
70
native_tokens_completion
265
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.001005
Evaluation details
Result
Evaluator
Details
Meta Data
51.9255%
Matches word count
n/a
neededClean
false
words
184
67.2734%
Dialogue to Total Word Ratio
Ratio: 82.07%, Deviation: 7.93%
neededClean
false
wordsTotal
184
wordsDialogue
151
59.5994%