NC Bench
Overview
About
Tests
Models
Model
GPT-4.1 Nano
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2025-04-14-01JRTSXN3JKGVCX8SY5RPG7BH9
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 peeked around the corner, clutching a map covered in doodles. "Bill, are you sure about this? Stealing from kids might be a low blow." Bill grinned. "Come on, Molly. Think of the loot! Plus, those party hats? Transparent, but adorable. We’re taking everything!" She rolled her eyes. "Hardly the point. What's the plan?" "Bright and early, we slip in through the back door," Bill whispered. "The coast guard is distracted by balloon animals." Molly crossed her arms. "Balloon animals? Really? How does that help us?" "Simple," Bill said. "While they’re busy making a poodle, we tiptoe inside, grab the presents, and sneak out in the chaos." She paused. "You sure the adults won’t notice? Or the birthday clown?" Bill chuckled. "The clown’s too busy juggling flaming cake, I swear. Anyway, once inside, we head straight for the gift table. Easy pickings." "And what if a kid catches us?" Molly asked skeptically. "Then we become the best part of the party—legendary burglars of the year. Who’s gonna suspect a couple of adults with party favors?" Molly sighed, smiling despite herself. "Alright, but if we get caught, we’re blaming the clown." Bill winked. "Deal. Now, let’s go steal some smiles—and presents."
id
"gen-1744656324-8vybGVswTLKCUjDvRaT9"
upstream_id
"chatcmpl-BMJ64tAOdEyk43Td98gB1Bs95Hp5P"
total_cost
0.0001251
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:45:27.72335+00:00"
Monday, April 14th, 2025 at 6:45:27 PM GMT+00:00
model
"openai/gpt-4.1-nano-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
313
moderation_latency
103
generation_time
2710
tokens_prompt
68
tokens_completion
296
native_tokens_prompt
67
native_tokens_completion
296
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
0.0001251
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
202
0.0000%
Dialogue to Total Word Ratio
Ratio: 80.69%, Deviation: 30.69%
neededClean
false
wordsTotal
202
wordsDialogue
163
49.9920%