NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 8B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-23-01J3G81M08TWGKXNDQ14B92G3B
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 ski mask, giving her a rakish gleam. Bill, resplendent in a bright orange jumpsuit, nodded approvingly. "Right, let's run it down. We've got a kiddie party at the Pink Palace venue, host of a certain four-year-old's birthday bash. The birthday cake is a towering behemoth, the games are overpriced, and most importantly, we have a hundred unwrapped presents just begging to be stolen." The venue's playground equipment cast long shadows in the fading light. "What's the haul look like?" Molly asked. "We're talking stuffed animals, dollhouses, the works. I've got intel from a reliable source - a five-year-old with a gift receipt still in the garbage can - that there's a particularly sweet LEGO castle with the little dude's name on it. Not to mention an entire box of sparkly art supplies that'll make us the envy of every crafty thief in town." Bill craned his neck, eyeing the venue's entrances. "Four staff, one janitor, and a hundred sugar-shocked kids running wild. The real challenge will be getting out without getting a clown horn stuck up our... tails." Molly fingered the toy stun gun on her hip. "Leave the clown horn to the amateurs, Bill. We're the ones with the real magic."
id
"gen-kqoQNJYwBlHrhKFmDLyThc81bO3B"
total_cost
0.0000702
upstream_id
"2f4c4014-d263-4196-ab35-2eb27bd13bf8"
created_at
"2024-07-23T16:50:58.253068+00:00"
Tuesday, July 23rd, 2024 at 4:50:58 PM GMT+00:00
model
"meta-llama/llama-3.1-8b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
1076
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
279
native_tokens_prompt
70
native_tokens_completion
281
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000702
Evaluation details
Result
Evaluator
Details
Meta Data
95.9868%
Matches word count
n/a
neededClean
false
words
208
0.0000%
Dialogue to Total Word Ratio
Ratio: 76.44%, Deviation: 26.44%
neededClean
false
wordsTotal
208
wordsDialogue
159
47.9934%