NC Bench
Overview
About
Tests
Models
Model
GPT-4.1 Mini
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2025-04-14-01JRTSV9J2CZ48CF1DEV238BZE
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 glanced nervously at the balloons bobbing in the breeze outside the brightly decorated house. "All these kids running around like little sugar-fueled tornadoes," she muttered, adjusting her black mask. "This is going to be chaos." Bill grinned, twirling a flashlight between his fingers. "Chaos is our friend. Nobody’s watching the presents when a clown’s juggling in the living room." Molly eyed the front door. "You sure about the timing? The cake cutting is in five minutes. Everyone’s gonna be distracted." “Exactly,” Bill said, his smile widening. "We grab the loot, be out before the sugar crashes hit." She hesitated. "What about the parents? I saw one of them doing a weird dance with a piñata." Bill laughed. "Distracted, Molly! Piñatas are like the smoke screens of children’s parties." Molly took a deep breath. "Okay, here’s the plan: you distract the piñata posse with your midnight flashlight showdown. I slip in, stuff the bags." Bill knelt down, pulling out a tiny party hat. "Should I wear this for extra stealth?" “Only if you want to look like a suspiciously festive burglar,” Molly said, smirking. “Alright, on three?” “One… two… three!” They burst through the door, a blur amidst balloons and laughter, ready to make off with the sweetest haul in history.
id
"gen-1744656246-bO4sIeAjETjClR8ndSWc"
upstream_id
"chatcmpl-BMJ4pTqEGjz2PzTmdAu2nOY35BWm0"
total_cost
0.0005036
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:44:12.242707+00:00"
Monday, April 14th, 2025 at 6:44:12 PM GMT+00:00
model
"openai/gpt-4.1-mini-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
697
moderation_latency
114
generation_time
3775
tokens_prompt
68
tokens_completion
297
native_tokens_prompt
67
native_tokens_completion
298
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
0.0005036
Evaluation details
Result
Evaluator
Details
Meta Data
81.2727%
Matches word count
n/a
neededClean
false
words
212
14.4594%
Dialogue to Total Word Ratio
Ratio: 61.79%, Deviation: 11.79%
neededClean
false
wordsTotal
212
wordsDialogue
131
47.8661%