NC Bench
Overview
About
Tests
Models
Model
Claude 3.7 Sonnet
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-02-24-01JMX20AWE7TQ4AHXGPDB8SNNT
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, I can't believe we're doing this," Bill whispered, adjusting his fake mustache in the side mirror of their van. "What? Having second thoughts about stealing from children?" Molly snorted while loading party poppers into her jacket pockets. "Not second thoughts. Third, fourth, and fifth thoughts, actually." "Look, we've hit banks, museums, and that weird guy's ferret collection. This is just another job." "But they're kids, Mol. Little humans with their little faces and little expectations of birthday joy." "Little humans with expensive gaming consoles and designer clothes as gifts. Have you seen the present table through the window? It's like a mini Best Buy in there." "I feel dirty. And not the good kind of dirty." "You can feel dirty while counting cash later." "What's our cover again?" "We're the backup clowns. The real one called in sick." "I hate clowns." "Everyone hates clowns. That's why no one will approach us." "Smart." "Always am. Ready?" "No." "Perfect. On three, we enter, entertain for exactly seven minutes, then hit the gift table during the cake cutting." "This is a new low." "New lows pay surprisingly well."
id
"gen-1740436942-gxkBJyxfpqNBAFXWbdn2"
upstream_id
"msg_01J81vBpqrpC17EnacquLrST"
total_cost
0.00477
cache_discount
(null)
provider_name
"Anthropic"
created_at
"2025-02-24T22:42:28.500629+00:00"
Monday, February 24th, 2025 at 10:42:28 PM GMT+00:00
model
"anthropic/claude-3-7-sonnet-20250219:beta"
app_id
182717
streamed
true
cancelled
false
latency
321
moderation_latency
(null)
generation_time
5439
tokens_prompt
68
tokens_completion
254
native_tokens_prompt
75
native_tokens_completion
303
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
0.00477
Evaluation details
Result
Evaluator
Details
Meta Data
68.1022%
Matches word count
n/a
neededClean
false
words
186
99.6873%
Dialogue to Total Word Ratio
Ratio: 87.63%, Deviation: 2.37%
neededClean
false
wordsTotal
186
wordsDialogue
163
83.8948%