NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-04-14-01JRTST7EDH40TST1Q9CK3E6QY
Run Details
Model:
GPT-4.1 Nano
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.0s
Cost:
$0.000120
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
Overall
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 grinned as she examined the blueprint of the party area. “Bill, are you sure about this? Stealing all those gifts from a bunch of kids?” Bill chuckled, adjusting his mask. “Absolutely. I mean, come on, Molly. Who’s going to miss a few toys? Besides, it’s practically begging for a heist.” She raised an eyebrow. “You think it’s that easy? Kids can be... unpredictable. What if we run into a bouncy castle full of them?” Bill nodded. “That’s why we need a plan. First, we sneak in through the back door when Mrs. Jenkins steps out for her coffee break.” “Work smarter, not harder. Got it,” Molly said, tapping her foot. “And then, we grab the biggest, shiniest gifts first. Those stuffed animals look plush. Kid-proof, right?” She scoffed. “They’re children-proof, not thief-proof. Anyway, how do we get out without setting off every alarm in the neighborhood?” Bill grinned. “Simple. We hide behind the giant birthday cake—no one looks for stolen presents behind a cake, Molly. It’s perfect!” She sighed dramatically. “Just promise me one thing. Next time, we pick a heist without the cartoon character balloons.” He winked. “No promises. That’s part of the fun.”
id
"gen-1744656211-2wk5XNVKFbNNXAdaPEZ4"
upstream_id
"chatcmpl-BMJ4GSkLeMwexUB2IFH7f0APbXy42"
total_cost
0.0001195
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:43:35.254269+00:00"
4/14/2025, 6:43:35 PM
model
"openai/gpt-4.1-nano-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
294
moderation_latency
112
generation_time
1921
tokens_prompt
68
tokens_completion
281
native_tokens_prompt
67
native_tokens_completion
282
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
0.0001195
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
0.00%
Dialogue to Total Word Ratio
Ratio: 82.00%, Deviation: 32.00%
neededClean
false
wordsTotal
200
wordsDialogue
164
49.9595%