NC Bench
Overview
About
Tests
Models
Model
Claude 3.0 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35SX1BKVWBE2HQ172PGGEZ0
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
Messages
Meta
AI
"Alright, Molly, you got the plan down?" Bill whispered, adjusting his ski mask. "Of course, Bill. We'll sneak in through the back door during the cake-cutting chaos," Molly replied, her eyes twinkling with mischief. "And what about the presents? They'll be guarded like Fort Knox." "Relax, I've got it covered. We'll create a diversion by letting loose a few dozen chickens." Bill blinked. "Chickens? Where are we gonna get chickens?" "Don't worry about that. Just focus on swiping the loot while the parents are scrambling to catch the feathered fiends." "Genius!" Bill chuckled. "You know, robbing from kids' parties isn't exactly ethical." Molly waved a dismissive hand. "Oh, please. Those little brats have enough toys to fill a warehouse. We're just redistributing the wealth." "If you say so. But if we get caught, I'm blaming you." "Don't be such a worrywart. Now, let's go nick some presents!" They shared a conspiratorial grin and slipped into the shadows, ready to execute their daring plan.
id
"gen-FJioXnc3hQJ3aAUIyv6wgUUcgjgO"
total_cost
0.00453
upstream_id
"msg_01VVg8UA6XwC2vp77wjUVTiv"
created_at
"2024-07-19T15:31:28.894104+00:00"
Friday, July 19th, 2024 at 3:31:28 PM GMT+00:00
model
"anthropic/claude-3-sonnet:beta"
app_id
182717
streamed
false
cancelled
false
provider_name
"Anthropic"
latency
6573
moderation_latency
(null)
generation_time
0
finish_reason
"end_turn"
tokens_prompt
68
tokens_completion
235
native_tokens_prompt
75
native_tokens_completion
287
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00453
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
164
4.9335%
Dialogue to Total Word Ratio
Ratio: 76.83%, Deviation: 13.17%
neededClean
false
wordsTotal
164
wordsDialogue
126
2.4668%