NC Bench
Overview
About
Tests
Models
Model
GPT-4.1 Mini
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2025-04-14-01JRTSWTP8R4W3CMP0APS1RFCR
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
Under the sickly glow of a flickering streetlamp, Molly squinted at the blueprint of the Johnson’s suburban fortress spread across the cracked sidewalk. The faint sound of balloons popping and childlike laughter drifted from the cul-de-sac, where the birthday party was in full swing. Bill crouched beside her, balancing a half-eaten donut in one hand. “Are you sure this is the best target? A kids’ party seems—” Molly cut him off with a sharp glance. “Easy targets, Bill. Parents distracted by sugar and chaos. Plus, presents galore, wrapped in shiny paper begging to be ripped away.” Her finger traced the route past the kiddie pool, through a gap in the hedges. Bill wiped frosting off his chin. “Right, distraction. What’s the plan?” “Simple. You cause a diversion near the punch bowl—maybe knock over a cake, draw the adults’ attention. I slip inside and grab the goods.” She wiggled her fingers like a pickpocketing maestro. Bill grinned, the glaze of a donut fueling his enthusiasm. “Cake chaos, got it. And if the little gremlins catch us?” “We dress up as clowns. No one suspects clowns at a kids’ party.” Bill chuckled, already plotting their sugary crime spree. Someone was about to have the worst birthday ever.
id
"gen-1744656297-i5iGbsIUqNI4eh2spg4p"
upstream_id
"chatcmpl-BMJ5dheo7t1s3BL0Phkt0lV2URPqV"
total_cost
0.0004764
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:45:00.168598+00:00"
Monday, April 14th, 2025 at 6:45:00 PM GMT+00:00
model
"openai/gpt-4.1-mini-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
535
moderation_latency
124
generation_time
1699
tokens_prompt
68
tokens_completion
280
native_tokens_prompt
67
native_tokens_completion
281
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
0.0004764
Evaluation details
Result
Evaluator
Details
Meta Data
93.6496%
Matches word count
n/a
neededClean
false
words
209
0.0000%
Dialogue to Total Word Ratio
Ratio: 41.63%, Deviation: 31.63%
neededClean
false
wordsTotal
209
wordsDialogue
87
46.8248%