NC Bench
Overview
About
Tests
Models
Model
Claude 3.5 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-19-01J35SGPD4CDVY6WVHKBDN98SG
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 and Bill huddled in the dimly lit alley, their eyes darting around nervously. The sound of children's laughter echoed from nearby. "You sure about this, Molly?" Bill whispered, fidgeting with his ski mask. "Absolutely. It's foolproof," Molly replied, a mischievous glint in her eye. "Think about it: tons of presents, minimal security." Bill sighed. "But it's a kid's party. Doesn't that seem... I dunno, wrong?" "Wrong? We're thieves, Bill. It's what we do," Molly scoffed. "Yeah, but-" "No buts. Now, here's the plan," Molly interrupted, pulling out a crude diagram. "You distract the clown while I sneak in through the back." Bill's eyes widened. "Wait, there's a clown?" "Focus, Bill! Once inside, I'll stuff the gifts into these bags," Molly continued, ignoring his concern. "And then what? We just walk out with sacks full of toys?" Molly grinned. "Exactly. They'll be too busy with cake and games to notice." Bill shook his head. "This is crazy." "Crazy brilliant. Now, let's go make some children cry!" With that, they slipped into the shadows, ready to execute their audacious plan.
id
"gen-QPtAHMaLTrdJDF9B9PwoulXtLryB"
total_cost
0.005145
upstream_id
"msg_01QS6tSpd7N3JjY1HkGeo22v"
created_at
"2024-07-19T15:24:53.048438+00:00"
Friday, July 19th, 2024 at 3:24:53 PM GMT+00:00
model
"anthropic/claude-3.5-sonnet:beta"
app_id
182717
streamed
false
cancelled
false
provider_name
"Anthropic"
latency
15128
moderation_latency
(null)
generation_time
0
finish_reason
"end_turn"
tokens_prompt
68
tokens_completion
273
native_tokens_prompt
75
native_tokens_completion
328
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.005145
Evaluation details
Result
Evaluator
Details
Meta Data
14.3014%
Matches word count
n/a
neededClean
false
words
179
65.0128%
Dialogue to Total Word Ratio
Ratio: 58.10%, Deviation: 8.10%
neededClean
false
wordsTotal
179
wordsDialogue
104
39.6571%