NC Bench
Overview
About
Tests
Models
Model
GPT-4.1 Mini
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2025-04-14-01JRTSR4Z8A1209Z7H98965E82
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 crouched behind the dumpster, checking her watch. “Okay, Bill, timing is everything. The cake’s at 3:15, gifts open at 3:30, chaos peak at 3:45.” Bill adjusted his tiny clown nose, which was supposed to be his disguise. “Why do I have to wear this thing? I look like a walking red balloon.” “Because, dear Bill,” Molly whispered, “it’s the perfect cover. No one suspects the guy who looks like he’s about to entertain five-year-olds.” Bill sighed. “Fine. But if a kid asks me to juggle, I’m out.” Molly pulled out a crudely drawn floor plan. “We sneak in through the side, grab the presents before they’re opened, and vanish before the sugar-high hits.” “And what about the parents?” Bill squinted at the map. “There’s a lot of them.” “We charm ’em,” Molly grinned. “You hand out balloons, I create a diversion.” Bill raised an eyebrow. “You mean set off that ridiculous fake spider again?” “Exactly,” Molly said, eyes twinkling. “Nothing causes panic like a plastic spider on a stick.” Bill shook his head. “Alright, Molly. For the presents...and because I hate piñatas.” Molly smiled. “Operation Sugar Heist is a go.”
id
"gen-1744656143-jCyk72Miz07pmtNbWvB9"
upstream_id
"chatcmpl-BMJ3AmwFQGyenYFlCmqmhofkS49Yz"
total_cost
0.0004796
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:42:27.752123+00:00"
Monday, April 14th, 2025 at 6:42:27 PM GMT+00:00
model
"openai/gpt-4.1-mini-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
522
moderation_latency
94
generation_time
2640
tokens_prompt
68
tokens_completion
282
native_tokens_prompt
67
native_tokens_completion
283
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
0.0004796
Evaluation details
Result
Evaluator
Details
Meta Data
98.7124%
Matches word count
n/a
neededClean
false
words
194
0.0000%
Dialogue to Total Word Ratio
Ratio: 72.16%, Deviation: 22.16%
neededClean
false
wordsTotal
194
wordsDialogue
140
49.3562%