NC Bench
Overview
About
Tests
Models
Model
GPT-4.1 Mini
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2025-04-14-01JRTSVS0N5D24G6KWDTK7MPSP
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
Molly crouched behind a bush, eyeing the colorful jumble of balloons and boxes through the living room window. The children's party was in full swing—laughter bubbling, sugar highs at peak. Bill adjusted his black knit cap and checked their makeshift blueprint drawn on a napkin. "Are you sure about this?" Bill whispered, poking a finger at the mountain of presents stacked by the tree. Molly smirked. "Absolutely. Who suspects two weirdos breaking into a sugar-fueled chaos?" They slipped off their shoes, inching across the freshly mowed grass with exaggerated stealth, careful not to disturb the bouncing plastic balls scattered about. Molly whispered, "Grab the presents near the fence. Kids won’t get that far." Bill nodded, eyes wide. "Right. But what if the parents catch us? I’m not great with small talk." "Relax. I’ve got this," Molly said, sliding open the window. She crawled inside, landing with a soft grunt. "Bill, bring the bag." He heaved the duffel over the sill, barely suppressing a giggle as a toddler toddled past, clutching a balloon dog. Molly grabbed the brightest box, whispering, "Let's get out before someone starts singing ‘Happy Birthday’ again." Bill exhaled. "Best job ever."
id
"gen-1744656262-dwPIDNm3OhMRCfBoxH2x"
upstream_id
"chatcmpl-BMJ54P68d6kCfohhYasclwHTBiW4Y"
total_cost
0.0004684
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:44:25.542622+00:00"
Monday, April 14th, 2025 at 6:44:25 PM GMT+00:00
model
"openai/gpt-4.1-mini-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
406
moderation_latency
132
generation_time
1523
tokens_prompt
68
tokens_completion
277
native_tokens_prompt
67
native_tokens_completion
276
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
0.0004684
Evaluation details
Result
Evaluator
Details
Meta Data
99.7443%
Matches word count
n/a
neededClean
false
words
196
0.0000%
Dialogue to Total Word Ratio
Ratio: 31.63%, Deviation: 21.63%
neededClean
false
wordsTotal
196
wordsDialogue
62
49.8722%