NC Bench
Overview
About
Tests
Models
Model
GPT-4.1 Mini
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2025-04-14-01JRTSXD122JDBP30WJ722P2RT
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 peered inside the pastel-decorated living room, where a dozen kids screamed over a piñata shaped like a unicorn. “Alright, Bill,” she whispered, “Operation Sugar Rush is a go. But how do we get past the sugar-fueled chaos?” Bill adjusted his tiny, too-small party hat and grinned. “Easy. We blend in. Nobody suspects the party clowns. Especially not when they’re delivering balloons—and sticky fingers.” Molly raised an eyebrow. “You’re seriously thinking we dress as clowns? Bill, last time your makeup looked like a raccoon fight.” “Hey,” Bill said, poking the air defensively, “that was avant-garde. Modern art. Besides, kids love a little chaos.” “As long as that doesn’t involve paint in the cake.” Bill pulled out a crumpled plan. “Step one: distract with balloon animals. Step two: locate the gift pile. Step three: execute the simultaneous grab-and-go.” Molly nodded. “And step four?” “Step four,” Bill smiled, “escape through the backyard, where I’ve parked the van disguised as a pony ride.” Molly laughed softly. “You’re insane. But if we pull this off, we’ll be the greatest party crashers—er, thieves—this town’s ever seen.” “Exactly. Now, ready to clown around?” “More ready than ever.”
id
"gen-1744656316-Q7MKVYFs8pp0sVArNpGa"
upstream_id
"chatcmpl-BMJ5w1Uwuk83LegSUAoIvz7micUQs"
total_cost
0.0004908
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:45:18.996444+00:00"
Monday, April 14th, 2025 at 6:45:18 PM GMT+00:00
model
"openai/gpt-4.1-mini-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
438
moderation_latency
130
generation_time
1559
tokens_prompt
68
tokens_completion
289
native_tokens_prompt
67
native_tokens_completion
290
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
0.0004908
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
words
200
0.0000%
Dialogue to Total Word Ratio
Ratio: 72.50%, Deviation: 22.50%
neededClean
false
wordsTotal
200
wordsDialogue
145
50.0000%