NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 3B
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-09-26-01J8PYWT3QFGV2WEWC9DYMD2Y0
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 paced around the cramped, dimly lit storage unit, her eyes scanning the eccentric assortment of disguises and gadgets that Bill had assembled over the years. He sat on a pile of cartons, ěnfolding a bright pink chicken suit. "So, what's the plan again?" Molly asked, her voice laced with skepticism. "We crash the Radcliffe twins' fifth birthday bash," Bill said, his voice muffled by the chicken's beak. "We're going in for the presents. I've been casing the joint for weeks." "White-glove handling?" Molly raised an eyebrow. "We're going up against screaming five-year-olds and their helicopter parents. I don't think our skills extend past minor league convenience store robbery." "Details, details," Bill said, wiggling a carton full of Smurf masks. "I've got a plan for every eventuality. Well, not literally every, but... okay, I've got a plan for about half of them." Molly snorted. "You're not even making sense." A faint chirping noise emanated from inside the chicken suit. Bill's voice dropped to a whisper. "It's just my new temp gun. Don't mind it."
id
"gen-c98W7z1WhDPROV9e4uBsMpseDfV3"
total_cost
0.000017496
upstream_id
"8c92a847a793643b-SJC"
created_at
"2024-09-26T10:44:14.109155+00:00"
Thursday, September 26th, 2024 at 10:44:14 AM GMT+00:00
model
"meta-llama/llama-3.2-3b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Together"
latency
132
moderation_latency
(null)
generation_time
1711
finish_reason
"eos"
tokens_prompt
102
tokens_completion
252
native_tokens_prompt
71
native_tokens_completion
253
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000017496
Evaluation details
Result
Evaluator
Details
Meta Data
6.0907%
Matches word count
n/a
neededClean
false
words
177
0.0000%
Dialogue to Total Word Ratio
Ratio: 51.41%, Deviation: 41.41%
neededClean
false
wordsTotal
177
wordsDialogue
91
3.0453%