Model

Llama 3.2 3B

Test

Dialogue tags

Scenario

Write 200 words with 90% dialogue

Run ID

2024-09-26-01J8PYXJG7J6NNZE4W5D53FJSC

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

AI
"The key plan is, we walk in around six, when the parents are distracted by the piñata and the kids are running around like lunatics," Molly said, studying the blueprints of the party. "Which ones are the parents and which ones are the lunatics – easy to tell by the breathing," Bill replied, sipping from his flask. "Okay, so we hit the wrapping station, and then we're on to the high-value gifts – dinosaurs and electronics," Molly continued. "And then we make our break, slipping out through the bounce house," Bill added. "Wait, you really think the bouncy castle is sturdy enough for us to escape through?" Molly asked. "Hey, it's a big castle – there's plenty of room to hide," Bill shrugged. "And what about the kid with the gleeful shriek? He's probably got a ' Wanted: Thieves' poster' cool for his bedroom," Molly joked. "Aww, that kid's going to be an FBI agent one day – grieving parents and pesky toddlers – the perfect funnel for us, right?" Bill chuckled.
id"gen-NsaHTDpndtW0waBfk2kp3lMcqpNI" 
total_cost0.0000323
upstream_id"chat-f7eb6fe0faca4d30ac4bcee55d06afe4" 
created_at"2024-09-26T10:44:38.485966+00:00" Thursday, September 26th, 2024 at 10:44:38 AM GMT+00:00
model"meta-llama/llama-3.2-3b-instruct" 
app_id182717
streamedtrue
cancelledfalse
provider_name"Hyperbolic" 
latency142
moderation_latency(null)
generation_time1067
finish_reason"stop" 
tokens_prompt68
tokens_completion225
native_tokens_prompt96
native_tokens_completion227
native_tokens_reasoning(null)
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.0000323

Evaluation details

Result Evaluator Details Meta Data
0.0007% Matches word count n/a
neededCleanfalse
words167
90.8304% Dialogue to Total Word Ratio
Ratio: 84.43%, Deviation: 5.57%
neededCleanfalse
wordsTotal167
wordsDialogue141
45.4156%