NC Bench
Overview
About
Tests
Models
Model
Llama 3 70B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35T32H2YM2RPT5DH4QQWSM0
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, Molly, this is a goldmine. A kids' party? It's like they're begging to be robbed." "Oh, come on, Bill. We're not monsters. We can't steal from children." "Children? Ha! They're just tiny, sugar-fueled human shields. And think about it, all those presents just sitting there, wrapped up with a bow. It's like they're daring us to take them." "But what about the guilt? I don't know if I can live with myself." "Guilt? You're a thief, Molly. We're professionals. We don't do guilt. We do profits. And this job could set us up for life." "I suppose you're right. But only if we can get past the obstacle course of juice boxes and tantrums." "Pfft, please. I've got a plan for that too. We'll just bring earplugs and a few boxes of animal crackers. Trust me, the kids will be too busy fighting over the Goldfish to notice us making off with the goods." "Alright, you've convinced me. When do we start?" "How about now? The party's supposed to start in an hour. We've got just enough time to get into position and -" "Wait, what's the party theme?" "Uh... 'Pirates and Ponies' or something." "Oh, great. Just what we need. A room full of sugar-high kids in eye patches and glittery tails chasing us down for our loot."
id
"gen-JXpY6z1gtEGJXyIoUhIrlCE0lFdH"
total_cost
0.000292995
upstream_id
"cmpl-ab01716ee2b34f83a89cfa861dbb0ddc"
created_at
"2024-07-19T15:34:45.384487+00:00"
Friday, July 19th, 2024 at 3:34:45 PM GMT+00:00
model
"meta-llama/llama-3-70b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"OctoAI"
latency
5156
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
311
native_tokens_prompt
72
native_tokens_completion
311
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000292995
Evaluation details
Result
Evaluator
Details
Meta Data
3.6234%
Matches word count
n/a
neededClean
false
words
224
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
224
wordsDialogue
224
20.2057%