NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-04-14-01JRTSQQ4X7Y31H6KNS5RJ7JRN
Run Details
Model:
GPT-4.1 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.0s
Cost:
$0.000470
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9920%
Overall
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 the inflatable castle, her eyes scanning the backyard filled with tiny chairs and an ominously large mountain of wrapped gifts. The sun was setting, casting long shadows over the cotton candy clouds painted on the party banner. Somewhere, a pinwheel spun lazily, mocking their covert operation. Bill adjusted his too-big mask, fidgeting with a bag that seemed suspiciously stuffed for such a "quick job." The plan was simple: infiltrate, grab the presents, vanish. Simple, except for the giggling troops of sugar-fueled kids guarding the loot like miniature, sticky ninjas. “Are we seriously breaking into a kid’s birthday party?” Molly whispered, trying not to laugh. “Hey, a job’s a job,” Bill replied, eyes darting. “Besides, those presents look way too tempting. Look at that giant teddy. Worth a fortune.” Molly smirked. “Giant teddy, huh? Should I be the distraction? You know, pull out some clown tricks?” “Only if your clown tricks include getting past the terrors with juice boxes.” Steeling themselves, they crawled under the snack table, inching toward the pile. A sudden scream halted them—a kid had spotted them! “We’re busted,” Molly hissed. Bill grinned wildly. “Or maybe we just made the party unforgettable.”
id
"gen-1744656129-NuX7LiqH6GrFmBbJxpps"
upstream_id
"chatcmpl-BMJ2vF2BGDS5Azvr6AWokQTVRpvOL"
total_cost
0.00047
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-14T18:42:12.614463+00:00"
4/14/2025, 6:42:12 PM
model
"openai/gpt-4.1-mini-2025-04-14"
app_id
182717
streamed
true
cancelled
false
latency
505
moderation_latency
100
generation_time
1695
tokens_prompt
68
tokens_completion
276
native_tokens_prompt
67
native_tokens_completion
277
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
0.00047
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
198
0.00%
Dialogue to Total Word Ratio
Ratio: 34.50%, Deviation: 24.50%
neededClean
false
wordsTotal
200
wordsDialogue
69
49.9920%