NC Bench
Overview
About
Tests
Models
Model
Claude 3.7 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-02-24-01JMX0SN4NG63EGQCT5RW56SD2
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
"We've done some pretty rough jobs," Molly said, examining the building blueprints, "but stealing from kids? That's low even for us." "It's not just any kids," Bill replied, munching on a stale donut. "These are Riverdale Heights kids. Trust fund babies whose parents buy them designer everything." "Still feels wrong." "Remember what those same rich parents did to your brother? Foreclosed on his house during chemo?" Molly sighed. "Fine. What's the plan?" "Simple. You dress as the backup clown. I'll be the caterer's assistant." "A clown? Seriously?" "Perfect cover. Nobody questions a clown at a birthday party." "And the gifts?" "Service entrance leads straight to the gift room. We'll need three minutes, tops." "Security?" "One bored guard who spends most of his time watching sports on his phone." "Escape route?" "Through the kitchen, into the waiting van." "What if someone recognizes us?" "Makeup, wigs, the works. We'll be invisible." "And if it all goes wrong?" Bill grinned. "Then we run like hell and blame it on the real clown."
id
"gen-1740435674-2r7Ff8ALO0aaSDu7eNPz"
upstream_id
"msg_015af5hb9dt7gZVDUDzqxjJb"
total_cost
0.004545
cache_discount
(null)
provider_name
"Anthropic"
created_at
"2025-02-24T22:21:20.835153+00:00"
Monday, February 24th, 2025 at 10:21:20 PM GMT+00:00
model
"anthropic/claude-3-7-sonnet-20250219:beta"
app_id
182717
streamed
true
cancelled
false
latency
345
moderation_latency
(null)
generation_time
5094
tokens_prompt
68
tokens_completion
239
native_tokens_prompt
75
native_tokens_completion
288
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
0.004545
Evaluation details
Result
Evaluator
Details
Meta Data
0.0098%
Matches word count
n/a
neededClean
false
words
169
100.0000%
Dialogue to Total Word Ratio
Ratio: 89.94%, Deviation: 0.06%
neededClean
false
wordsTotal
169
wordsDialogue
152
50.0049%