NC Bench
Overview
About
Tests
Models
Model
Claude 3.5 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35TA6Z6TWX353X7PW0Q92SW
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
"Molly, you can't be serious. A children's party?" "Dead serious, Bill. Think about it. All those shiny new toys, just waiting to be snatched." "But... it's a kids' party. That's low, even for us." "Low? It's genius! Nobody expects thieves at a birthday bash." "What about security?" "Security? It's not Fort Knox, it's little Timmy's seventh birthday." "Still, there'll be parents everywhere." "Exactly! Distracted parents, chasing sugar-high kids. Perfect cover." "I don't know, Mol. Seems risky." "Riskier than that bank job last month?" "Fair point. So, what's the plan?" "We dress as clowns." "Clowns? You've got to be kidding me." "Nope. We entertain, we mingle, we pilfer." "And the loot?" "In our oversized pants, obviously." "Obviously. What about the birthday boy?" "We leave his presents. We're not monsters, Bill." "Right. Just thieves stealing from children." "Hey, those kids'll be fine. Their parents can buy new toys." "And we get..." "A big payday and the satisfaction of pulling off the wackiest heist ever." "You're certifiable, you know that?" "Yep. Now, let's go practice our balloon animals."
id
"gen-kDjkMFpfrDpvWh4QZkR6lCOS3TK0"
total_cost
0.00531
upstream_id
"msg_012VgJgsRZionHoxaFxPRtkR"
created_at
"2024-07-19T15:38:57.147403+00:00"
Friday, July 19th, 2024 at 3:38:57 PM GMT+00:00
model
"anthropic/claude-3.5-sonnet:beta"
app_id
182717
streamed
false
cancelled
false
provider_name
"Anthropic"
latency
23002
moderation_latency
(null)
generation_time
0
finish_reason
"end_turn"
tokens_prompt
68
tokens_completion
278
native_tokens_prompt
75
native_tokens_completion
339
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00531
Evaluation details
Result
Evaluator
Details
Meta Data
3.6234%
Matches word count
n/a
neededClean
false
words
176
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
176
wordsDialogue
176
20.2057%