NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 90B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-09-26-01J8Q0NWMB087P9YPDBZAB28BB
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 pair of oversized novelty sunglasses, taking a moment to survey their surroundings. They were parked across the street from a house that was undoubtedly hosting some sort of extravagant children's birthday party. Bill was lying in the backseat, poring over the details of their plan. "Alright, so we have 'Invisible Man' Sean creating a diversion, distracting the parents while we sneak in the rear entrance," Molly said, tapping her glossy lips with a long fingernail. Bill scrunched up his face. "What's the deal with Sean's costume, anyway?" "It's to look like he's invisible, Bill – hence the full-body spandex onesie," Molly replied dryly, unimpressed by Sean's creative choice. "Brilliant, just what we need – some drama-prone weirdo running around in skintight PJs, screaming about being an 'invisible force.' We're going to get caught for sure." Molly admired her reflection in the rearview mirror before continuing to brief Bill. "Look, just get Sean into position. Meanwhile, we slip in unnoticed, swap our knockoff presents with the high-end ones, and we're out with the loot, easy peasy."
id
"gen-1C6qX7KRklU4SOxX3eRC43iX1w4c"
total_cost
0.0001408
upstream_id
"chat-70d8fd69e8c8400394b6c260f62e1c83"
created_at
"2024-09-26T11:15:32.528366+00:00"
Thursday, September 26th, 2024 at 11:15:32 AM GMT+00:00
model
"meta-llama/llama-3.2-90b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
91
moderation_latency
(null)
generation_time
9784
finish_reason
"stop"
tokens_prompt
68
tokens_completion
254
native_tokens_prompt
96
native_tokens_completion
256
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001408
Evaluation details
Result
Evaluator
Details
Meta Data
14.3014%
Matches word count
n/a
neededClean
false
words
179
99.1126%
Dialogue to Total Word Ratio
Ratio: 53.07%, Deviation: 3.07%
neededClean
false
wordsTotal
179
wordsDialogue
95
56.7070%