NC Bench
Overview
About
Tests
Models
Model
o4 Mini High
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2025-04-16-01JRZZ42BD335B86K7Y4VP7M13
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 and Bill crouch behind a row of wrapped gifts under the party table. Tiny disco lights reflect off the tinsel. Molly: "Okay, Bill, you memorized the guest list?" Bill: "Memorized? I practically live inside it. Three five-year-olds, two seven-year-olds." Molly: "And the hamster with the sugar craving?" Bill: "The hamster’s off-limits. Our target is the red box with the train set." Molly: "Right. Operation Gift Grab launches in five seconds. Ready your grappling hook." Bill: "Grappling hook? For a six-inch drop? You almost took out Mrs. Jensen’s begonias last week." Molly: "Begonias can be lucrative. Tonight we trade blooms for stuffed unicorns." Bill: "Unicorns don’t sell themselves if kids spot us. Quiet or plan B: fake Santa." Molly: "Fake Santa? You still have the belly pad?" Bill: "Right here. But don’t laugh; it survived three mall seasons." Molly: "Also snag the glitter bombs hidden behind the piñata." Bill: "Glitter bombs are a nightmare to clean. I’ll trust you." Molly: "Nightmare? I call it dramatic ambiance for a heist." Bill: "By the time they notice, we’ll be in Nebraska." Molly: "Okay, on three. One." Bill: "Two." Molly: "Three. Move!" Bill: "And try not to wake Mr. Carson’s snoring cat."
id
"gen-1744829549-7GSsoctix3aV3xfqIcBB"
upstream_id
"chatcmpl-BN2A1RBP48TGP9fFiQzsQAqbYavhQ"
total_cost
0.0250338
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-16T18:53:29.515033+00:00"
Wednesday, April 16th, 2025 at 6:53:29 PM GMT+00:00
model
"openai/o4-mini-high-2025-04-16"
app_id
182717
streamed
true
cancelled
false
latency
55765
moderation_latency
308
generation_time
59532
tokens_prompt
68
tokens_completion
5654
native_tokens_prompt
66
native_tokens_completion
5673
native_tokens_reasoning
5312
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
0.0250338
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
205
51.5179%
Dialogue to Total Word Ratio
Ratio: 80.98%, Deviation: 9.02%
neededClean
false
wordsTotal
205
wordsDialogue
166
75.4474%