NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 70B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-23-01J3G814ECG2TJA71KQW7DKSJN
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, it's a goldmine. A bunch of sugar-fueled kids running around, distracted by a guy in a furry suit. No one will even notice us." "Are you insane? We're thieves, Molly, not monsters. We don't steal from kids on their birthdays." "Oh, come on. It's not like we're stealing their innocence. Just some overpriced toys and useless trinkets. They'll get more this year, I'm sure." "I don't know, Molly. I've got a soft spot for kids. I was one once, remember?" "Aww, Bill, you're not going to start telling me about your rough childhood and how it's made you sympathize with our victims, are you?" "Hey, my childhood was not that rough. I just...I don't know, I guess I'm just getting a little old for this sort of thing. What's the take, anyway?" "Oh, I'd say at least a few thousand. And it's not like anyone's going to be checking the guest list or anything. We just walk in, look like a couple of clueless parents, and...voilĂ ." "VoilĂ ? Really? You've been watching too much Ocean's Eleven." "Hey, that's a great movie. And besides, it's a legitimate way to gather inspiration for our craft." "Uh-huh. Right. Because nothing says 'craft' like a bunch of thieves in suits."
id
"gen-v3aOpt1D4cLLOd5TSK1OBPJV92UD"
total_cost
0.0003411
upstream_id
"1e31df48-7ba0-461e-b960-fb28b6e45b9b"
created_at
"2024-07-23T16:50:44.991201+00:00"
Tuesday, July 23rd, 2024 at 4:50:44 PM GMT+00:00
model
"meta-llama/llama-3.1-70b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
3894
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
307
native_tokens_prompt
70
native_tokens_completion
309
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0003411
Evaluation details
Result
Evaluator
Details
Meta Data
86.3803%
Matches word count
n/a
neededClean
false
words
211
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
211
wordsDialogue
211
61.5841%