NC Bench
Overview
About
Tests
Models
Model
GPT-4.1
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2025-04-14-01JRTSX2C260C6V8YK0HNZ4J30
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 technicolor bush shaped like a dinosaur, twirling her lockpick like a drum major’s baton. Bill peered over the hedge, a pair of plastic spy binoculars pressed to his face, looking more like a kid about to ask for cake than a career criminal. “See the clown yet?” she whispered, grimacing as a cluster of helium balloons floated too close. “Negative,” Bill replied. “But I count five grown-ups and a suspiciously agile grandmother.” “The one with the unibrow?” Molly elbowed him, glancing through a gap in the foliage. “No, not uni—look, focus. Presents are on the folding table by the bounce house. It’s chaos down there. Pure horde.” Molly’s eyes locked on the gaudy mountain of gift bags, each wrapped with enough sparkle to blind a parade. “Alright, Plan B?” she asked, a mischievous grin forming. Bill nodded. “I start a cupcake melee. You grab the loot during the frosting fracas.” “Best idea you’ve had all year.” He cracked his knuckles and straightened his ninja turtle mask, blending seamlessly with the crowd of sticky-fingered partygoers. “Ready?” “Let’s steal some birthdays,” she whispered, suppressing a wicked laugh as they slithered toward pandemonium.
id
"gen-1744656305-k2HAw4QVVnPRkLX6pUuL"
upstream_id
"chatcmpl-BMJ5lwbdN117ItqVvzqDzxx8rTw6T"
total_cost
0.002382
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:45:09.464765+00:00"
Monday, April 14th, 2025 at 6:45:09 PM GMT+00:00
model
"openai/gpt-4.1-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
453
moderation_latency
100
generation_time
3388
tokens_prompt
68
tokens_completion
280
native_tokens_prompt
67
native_tokens_completion
281
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
0.002382
Evaluation details
Result
Evaluator
Details
Meta Data
99.9190%
Matches word count
n/a
neededClean
false
words
197
0.0000%
Dialogue to Total Word Ratio
Ratio: 35.03%, Deviation: 25.03%
neededClean
false
wordsTotal
197
wordsDialogue
69
49.9595%