NC Bench
Overview
About
Tests
Models
Model
o4 Mini
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-04-16-01JRZZ4Z152XRX4BS6RXJC6WZ3
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
In the dimly lit backyard, Bill and Molly huddle beneath a tattered tarp, eyes glinting with mischief, chattering softly, eagerly. Molly: "Night vision goggles?" Bill: "Check. They're totally real knockoffs." Molly: "How many cupcakes did you steal?" Bill: "Seven. I might have eaten one for quality control." Molly: "Please tell me you remembered the glitter bombs." Bill: "Absolutely. Party popper grenades loaded and tagged." Molly: "Look at that cake table. Forty cupcakes and a unicorn piñata." Bill: "If we hurry, no one will notice the missing rainbow layers." Molly: "Don't forget the pin cushions disguised as party favors." Bill: "Got them. Also installed a tiny speaker that plays meowing kittens." Molly: "Serve chaos, grab gifts, exit gracefully. Code word: confetti." Bill: "Remember last time? We replaced all juice with pickle juice." Molly: "Kids coughed for three days. This is child's play." Bill: "Let's do it. One shot at the gift room carpet." Molly: "After that, we vanish into the birthday chaos like ninjas." Bill: "Team Molly and Bill strikes again." Molly: "Let's roll before the piñata unleashes confetti mortar." Bill: "Three: one, two, three!"
id
"gen-1744829578-HL8IH7UpWTAjjS8sSf8N"
upstream_id
"chatcmpl-BN2AUKAdqBsUaGIBE8i8iIXLUGhMt"
total_cost
0.0126962
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-16T18:53:28.168876+00:00"
Wednesday, April 16th, 2025 at 6:53:28 PM GMT+00:00
model
"openai/o4-mini-2025-04-16"
app_id
182717
streamed
true
cancelled
false
latency
26549
moderation_latency
87
generation_time
29352
tokens_prompt
68
tokens_completion
2855
native_tokens_prompt
66
native_tokens_completion
2869
native_tokens_reasoning
2560
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
0.0126962
Evaluation details
Result
Evaluator
Details
Meta Data
51.9255%
Matches word count
n/a
neededClean
false
words
184
27.5955%
Dialogue to Total Word Ratio
Ratio: 79.35%, Deviation: 10.65%
neededClean
false
wordsTotal
184
wordsDialogue
146
39.7605%