NC Bench
Overview
About
Tests
Models
Model
Claude 3.7 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2025-02-24-01JMX1B1NTHRP4VHK0DEVN6G7S
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 crouched behind the picket fence, peering through the wooden slats at the backyard festooned with balloons and streamers. A mountain of wrapped packages sat on a table near the bounce house. "Look at all those presents," Molly whispered. "Like taking candy from a baby." Bill frowned. "We're not actually taking candy from babies, right? That would be wrong." "It's an expression, Bill," Molly sighed. "We're taking presents from children. Completely different." "Is it though?" Bill scratched his head. "Morally speaking, I mean." Molly rolled her eyes. "The piƱata arrives at two. That's our window." "What about the clown?" Bill pointed nervously. "What about him?" "Clowns freak me out." "Focus, Bill! You distract the parents, I'll grab the loot." Bill fidgeted with his watch. "These kids worked hard writing those letters to Santa." "Santa's not real, genius." "Still feels kinda wrong." "Remember that time little Timmy stole your lunch money in third grade?" "That was twenty years ago!" "This is cosmic justice," Molly declared, pulling on her black gloves. "Ready?" "I guess so," Bill muttered. "But I'm avoiding the clown."
id
"gen-1740436244-CwoFeVj59pFusWvbKiBh"
upstream_id
"msg_017sU33Kdz3zAHpjMgYrWbF9"
total_cost
0.005085
cache_discount
(null)
provider_name
"Anthropic"
created_at
"2025-02-24T22:30:50.182778+00:00"
Monday, February 24th, 2025 at 10:30:50 PM GMT+00:00
model
"anthropic/claude-3-7-sonnet-20250219:beta"
app_id
182717
streamed
true
cancelled
false
latency
365
moderation_latency
(null)
generation_time
4886
tokens_prompt
68
tokens_completion
267
native_tokens_prompt
75
native_tokens_completion
324
native_tokens_reasoning
0
num_media_prompt
(null)
num_media_completion
(null)
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.005085
Evaluation details
Result
Evaluator
Details
Meta Data
35.0022%
Matches word count
n/a
neededClean
false
words
182
1.5531%
Dialogue to Total Word Ratio
Ratio: 64.29%, Deviation: 14.29%
neededClean
false
wordsTotal
182
wordsDialogue
117
18.2776%