NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-04-14-01JRTSZPB2EC7BZW5SJS5P1YDX
Run Details
Model:
GPT-4.1 Nano
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.5s
Cost:
$0.000117
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
88.97%
Dialogue to Total Word Ratio
(details)
58.0676%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 leaned in, clutching a crumpled map. “Bill, are you sure about this? Stealing from a kids' party feels... well, kinda wrong, don’t you think?” Bill grinned, adjusting his fake mustache. “Come on, Molly. Think of the presents! These kids aren’t gonna miss a thing. Besides, who ever heard of a heist at a birthday bash?” “Yeah, but what if we get caught? The parents are pretty sneaky — they could call the cops.” “Then we’ll sing ‘Happy Birthday’ a little early, just to throw them off. Plus,” he winked, “I brought my super sneaky ninja gloves. They’re practically invisible.” Molly sighed. “Fine. But how are we gonna get past those cupcake-eating giants guarding the door?” Bill chuckled. “Simple. We distract them with my world-famous balloon animal sculpture. While they’re mesmerized, you slip inside and grab the presents.” “And what if the kids see us?” “Easy,” Bill said, raising a finger. “We say we’re here for the cake. Kids love cake, right? Kids love surprises. It’s foolproof!” Molly shook her head, smirking. “You’re impossible, Bill. But I’ll admit… this could be fun.”
id
"gen-1744656391-ksNh43hEO3HWj0bByoPd"
upstream_id
"chatcmpl-BMJ790TDJi4OkJm5ATqJJnOouXI4h"
total_cost
0.0001167
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:46:33.454966+00:00"
4/14/2025, 6:46:33 PM
model
"openai/gpt-4.1-nano-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
241
moderation_latency
274
generation_time
1259
tokens_prompt
68
tokens_completion
273
native_tokens_prompt
67
native_tokens_completion
275
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
0.0001167
Evaluation details
Result
Evaluator
Details
Meta Data
27.17%
Matches word count
n/a
neededClean
false
words
181
88.97%
Dialogue to Total Word Ratio
Ratio: 84.15%, Deviation: 5.85%
neededClean
false
wordsTotal
183
wordsDialogue
154
58.0676%