NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 90B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-09-26-01J8Q0PZNYQ92SH9GGXRQ5JBBQ
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 adjusted the miniature earpiece lodged in her ear, fiddling with the hook to ensure it stayed securely in place. Across from her, Bill meticulously poured over a blueprint of the children's party venue. "Well, Molly, what do you think? Are you ready to bust into our first birthday party and make off with all the loot?" Molly grinned wickedly as she strode over to where Bill was hunched over the diagrams. She delicately plucked a rubber ducky from Bill's makeshift disguise and plopped it onto her own head. A faint whisper of Bill's chuckle vibrated through the almost invisible earpiece. The duo pored over their strategy, methodically breaking down entry and exit points. It seemed dozens of hyperactive children would prove a convenient diversion to their plan to swipe all the birthday presents - brand-new toys tastefully decorated in paper and ribbons - at little Tommy Butler's birthday bash. They concocted a set of equally ridiculous personas, one as a disastrous clown and the other as a simpering costumed character. "Perfect."
id
"gen-vGZDU8kOdFmQAiiZWqRK0ukNterp"
total_cost
0.0001276
upstream_id
"chat-d04ebd924c1c47ce8cf0e2ea17b4a7c2"
created_at
"2024-09-26T11:16:09.204059+00:00"
Thursday, September 26th, 2024 at 11:16:09 AM GMT+00:00
model
"meta-llama/llama-3.2-90b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
57
moderation_latency
(null)
generation_time
10655
finish_reason
"stop"
tokens_prompt
68
tokens_completion
222
native_tokens_prompt
96
native_tokens_completion
223
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001276
Evaluation details
Result
Evaluator
Details
Meta Data
0.0848%
Matches word count
n/a
neededClean
false
words
171
97.3838%
Dialogue to Total Word Ratio
Ratio: 14.04%, Deviation: 4.04%
neededClean
false
wordsTotal
171
wordsDialogue
24
48.7343%