NC Bench
Overview
About
Tests
Models
Model
GPT-4.1 Nano
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2025-04-14-01JRTSVGBDPFHV2VR7FGCW054G
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 peeked around the corner, eyes gleaming. "Bill, are you sure about this? The kids will be impossible to pass up." Bill adjusted his mask, grinning. "Molly, think about it. All those toys—just sitting there, waiting. We’ve pulled tougher jobs." She rolled her eyes. "Tougher jobs that got us in jail. Remember the last time? The fire extinguisher incident?" He chuckled. "That was your fault. Anyway, tonight’s different. We go in silent, grab the loot, and exit." "Silent? Bill, it’s a noisy party. There's clown music, kids screaming—" she paused, scanning the backyard. "And the balloons! Watch out for the squeaky ones." Bill pointed at the window. "The back fence is open. We slip in under the radar, quick as cats." Molly frowned. "And what if someone sees us? Mrs. Jenkins is pretty observant." Bill shrugged. "Then we hide behind the bouncy castle until she forgets. Easy." "Alright, but if we get caught, I’m blaming you for the chaos." He grinned wider. "No risk, no reward. Let’s do this, partner." She sighed. "Just don’t get us expelled from the party, Bill." He winked. "Trust me, Molly. We’ll be out of there before anyone notices."
id
"gen-1744656253-iqiDMeJxkI0fxEitMGu0"
upstream_id
"chatcmpl-BMJ4vfIB5L7TgnEA6mJtjqJLmnzGe"
total_cost
0.0001239
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:44:15.394465+00:00"
Monday, April 14th, 2025 at 6:44:15 PM GMT+00:00
model
"openai/gpt-4.1-nano-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
354
moderation_latency
75
generation_time
704
tokens_prompt
68
tokens_completion
293
native_tokens_prompt
67
native_tokens_completion
293
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
0.0001239
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
195
0.0000%
Dialogue to Total Word Ratio
Ratio: 80.00%, Deviation: 30.00%
neededClean
false
wordsTotal
195
wordsDialogue
156
49.6885%