NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 11B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8PYY5Z9YGWSCJBJD3D1VQCT
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 sat in the dingy café, nursing a lukewarm coffee as she briefed Bill on the plan. "Okay, so the party is at 3 PM, and the kids will be distracted by the bouncy castle by 3:30 at the latest. That's when we make our move." Bill nodded, his eyes shining with excitement. "And we just waltz in, grab the presents, and out we go?" Molly's eyes narrowed. "Not exactly. We need to create a diversion, something that'll draw the parents away from the pile of loot on the table." Bill's face creased in thought. "A piñata, perhaps? Or a bunch of screaming toddlers?" Molly raised an eyebrow. "You're a genius, Bill. I think the screaming toddlers are a go." Bill's face lit up. "I was worried I'd overthink it. What's the protocol for getting out of there undetected?" Molly smiled sweetly. "We wear party hats and pig masks. It's foolproof." Bill snorted. "You really expect to fit into a pig mask?" Molly shrugged. "I'll just have to dig out my old party prep skills from high school. Now, have you got the gift cards?" Bill patted his pockets. "Right here. I've got ten thousand dollars' worth of stolen toys to buy."
id
"gen-Z1Rs8OPhfFFs42Cwz7CD7rQwWdXZ"
total_cost
0.0000718
upstream_id
"1b9eb54d-1b48-4fd5-bbab-f56a3e0a336f"
created_at
"2024-09-26T10:44:59.726807+00:00"
Thursday, September 26th, 2024 at 10:44:59 AM GMT+00:00
model
"meta-llama/llama-3.2-11b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Fireworks"
latency
283
moderation_latency
(null)
generation_time
2303
finish_reason
"stop"
tokens_prompt
68
tokens_completion
287
native_tokens_prompt
71
native_tokens_completion
288
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000718
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
202
0.4494%
Dialogue to Total Word Ratio
Ratio: 74.75%, Deviation: 15.25%
neededClean
false
wordsTotal
202
wordsDialogue
151
50.2167%