NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 11B (Vision)
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-09-26-01J8PZ428EDDQQ2DQY18X8D55A
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 sipped her lukewarm coffee, her eyes scanning the dimly lit storage room. Bill leaned against a stack of dusty boxes, his expression expectant. "Alright, so I've got the layout," Molly said, unrolling a crumpled blueprint on a nearby workbench. "Main entrance is covered, but if we hit the back alley around 3pm, we should be cool." "Sounds like a Christmas miracle," Bill drawled, snatching a squeeze of pipe cleaner from his backpack. "What's the play?" "Mindextrap entrance. We–" "Mindextrap, huh?" Bill chuckled. "You're really milking the 'n ot-so-stealthy-shenanigans' vibe, aren't ya?" "Hey, it worked once. We walk in, pretend to be party staff, and zero in. Canvases are at the east table, live music at the west, cache should be near the gift unwrap area." Bill coiled a length of twine into a hump-back knot, tousling his hair in mock exhaustion. "You're a genius. What's the gift table layout?" "Standard Easter basket fare – fiberschoovedement chew toys for girls and action figures for boys. Paint by numbers for sparse action med stations in there too." She tapped an air 'X' on the blueprint. "Gift wrap's –trimming session cuts location memset parallels 79 expob order fo-adv per report." Bill paused mid-assemblage, their faces searching each other.
id
"gen-WAXuUy2dln50WD0mmPUtvjiwORgc"
total_cost
0.000062208
upstream_id
"chat-07394e1750bf42c8bb497e39a9c41152"
created_at
"2024-09-26T10:48:12.331562+00:00"
Thursday, September 26th, 2024 at 10:48:12 AM GMT+00:00
model
"meta-llama/llama-3.2-11b-vision-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Together"
latency
363
moderation_latency
(null)
generation_time
1949
finish_reason
"stop"
tokens_prompt
68
tokens_completion
312
native_tokens_prompt
71
native_tokens_completion
313
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000062208
Evaluation details
Result
Evaluator
Details
Meta Data
86.3803%
Matches word count
n/a
neededClean
false
words
211
3.5847%
Dialogue to Total Word Ratio
Ratio: 63.51%, Deviation: 13.51%
neededClean
false
wordsTotal
211
wordsDialogue
134
44.9825%