NC Bench
Overview
About
Tests
Models
Model
o4 Mini High
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-04-16-01JRZYSEBFTDX54JVESJ76E3FD
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
Night sky blankets the street. Molly crouches beside Bill at the fence. A distant birthday song drifts through the window. Molly: "The cake's inside and so are a hundred presents. You ready?" Bill: "Born ready. I’ve got my glitterproof gloves and stealthy Santa suit." Molly: "We shouldn't wake the sugar-fueled wildlings inside. Quiet like ninja toddlers." Bill: "And if they catch us, we apologize with gummy bear bribes." Molly: "Gift Grab is go. You climb in, I'll distract with balloons." Bill: "Copy. I'm off. Watch for toddlers armed with cupcakes. They're lethal." Molly: "Remember to avoid the clown entertainer. His balloon poodle chomps ankles." Bill: "Got it. I’ll wear earplugs. The screaming triggers my sneeze reflex." Molly: "After you snag presents, meet at the minivan. I'll honk twice." Bill: "Honk once for yes, twice for nope, thrice if cake missing." Molly: "If you see glitter everywhere, that's the unicorn child's trap. Stay clear." Bill: "Understood. Middle table holds games and gadgets. Prime target. Jackpot awaits here." Molly: "Security lights flip on? Weave through piñata corner, blind spot heaven." Bill: "Watch those parents lurking by table. They guard juice boxes especially fiercely." Molly: "Good luck, partner in crime. Let's make this the sweetest heist ever."
id
"gen-1744829202-FfHhAdDjbW0FL0GPS4nK"
upstream_id
"chatcmpl-BN24Qi5kHjYyW9Mmh9EcOlWP1eD2W"
total_cost
0.032505
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-16T18:48:10.7623+00:00"
Wednesday, April 16th, 2025 at 6:48:10 PM GMT+00:00
model
"openai/o4-mini-high-2025-04-16"
app_id
182717
streamed
true
cancelled
false
latency
83353
moderation_latency
126
generation_time
88537
tokens_prompt
68
tokens_completion
7360
native_tokens_prompt
66
native_tokens_completion
7371
native_tokens_reasoning
7040
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
0.032505
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
205
77.8569%
Dialogue to Total Word Ratio
Ratio: 82.93%, Deviation: 7.07%
neededClean
false
wordsTotal
205
wordsDialogue
170
88.6169%