NC Bench
Overview
About
Tests
Models
Model
Claude 3.5 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-19-01J35SNNPWM9SQ32WQ80GZFHMC
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 paced the dimly lit basement, her eyes darting between Bill and the crude blueprint spread on the table. "We've got one shot at this, Bill. You clear on the plan?" Bill nodded, fiddling with a party hat. "Crystal. But why a kid's party? Seems a bit... low." "Low? It's genius! Think about it – expensive gifts, distracted adults, and a perfect cover." "I don't know, Mol. What if we get caught?" Molly rolled her eyes. "That's why we're dressing as clowns, you numbskull." "Clowns? I hate clowns!" "Tough. Now, focus. You handle the gift table, I'll create a distraction." Bill sighed, resigned. "Fine. What's the distraction?" "I'm thinking a juggling act gone wrong. Maybe I'll 'accidentally' set something on fire." "Jesus, Molly! There'll be kids there!" "Relax, it'll be controlled. Mostly." "This is insane. We should bail." Molly grabbed Bill's shoulders. "Listen, you want that beach house or not? This is our ticket. Now, let's go over the escape route one more time." Bill nodded reluctantly, turning back to the blueprint as Molly resumed her pacing, a mischievous glint in her eye.
id
"gen-xrsr9toPk3I70QYMhgygINQuGLRk"
total_cost
0.0051
upstream_id
"msg_01RpWsGZYfnxiD93LQD9uaNX"
created_at
"2024-07-19T15:27:35.362186+00:00"
Friday, July 19th, 2024 at 3:27:35 PM GMT+00:00
model
"anthropic/claude-3.5-sonnet:beta"
app_id
182717
streamed
false
cancelled
false
provider_name
"Anthropic"
latency
14264
moderation_latency
(null)
generation_time
0
finish_reason
"end_turn"
tokens_prompt
68
tokens_completion
279
native_tokens_prompt
75
native_tokens_completion
325
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0051
Evaluation details
Result
Evaluator
Details
Meta Data
35.0022%
Matches word count
n/a
neededClean
false
words
182
0.0001%
Dialogue to Total Word Ratio
Ratio: 69.23%, Deviation: 19.23%
neededClean
false
wordsTotal
182
wordsDialogue
126
17.5011%